[HN Gopher] Pause Giant AI Experiments: An Open Letter
       ___________________________________________________________________
        
       Pause Giant AI Experiments: An Open Letter
        
       Author : jiripospisil
       Score  : 458 points
       Date   : 2023-03-28 21:43 UTC (1 days ago)
        
 (HTM) web link (futureoflife.org)
 (TXT) w3m dump (futureoflife.org)
        
       | erwan577 wrote:
       | This kind of publicity will only fuel the hype and the interest
       | of ambitious people.
       | 
       | These "advanced AI systems" are only high end GPU systems from
       | the shelves, or even M2 macbooks.
       | 
       | The software and data they handle are private. Even in legal
       | terms, I can't see how this could be possible. Even DNA
       | engineering could not be limited by law in practice...
        
       | T-A wrote:
       | Good luck with that.
       | 
       | https://apnews.com/article/technology-russia-business-artifi...
       | 
       | https://tass.com/economy/1541627
       | 
       | https://www.aljazeera.com/economy/2023/3/3/china-beating-wes...
        
       | taneq wrote:
       | The genie's been out of the bottle for a while now. Hang onto
       | your hats.
        
         | usrusr wrote:
         | That's why it explicitly states "more powerful than GPT-4", not
         | "all LLM".
        
       | guntribam wrote:
       | Of course they want to pause. Imagine that ammout of jobs that
       | will be obsolete in one year from now. This will start a
       | revolution
        
       | seydor wrote:
       | Nice try, Google
        
       | wsgeorge wrote:
       | That's a remarkable list of signatories.
        
         | usr1106 wrote:
         | How do we know it's real? And not produced by ChatGPT, someone
         | who believes to be funny or has an agenda?
        
           | versteegen wrote:
           | Of course it's real. The Future of Life Institute is
           | reputable and run by Max Tegmark. Most of the people I
           | recognise have expressed compatible public opinions.
        
       | braingenious wrote:
       | >AI research and development should be refocused on making
       | today's powerful, state-of-the-art systems more accurate, safe,
       | interpretable, transparent, robust, aligned, trustworthy, and
       | loyal.
       | 
       | LMAO.
       | 
       | "AI should have... _waves at a laundry list of nice sounding
       | adjectives that mean different things to every single signatory_
       | in order to accomplish... Humanity [can enjoy] a flourishing
       | future with AI. This will take... six months."
       | 
       | Six months doesn't sound long enough to guarantee AI safety, but
       | it sounds about long enough for Elmo to train up and release his
       | anti-wokeness LLM (whatever that means), which he has been pretty
       | vocal about being important.
        
         | [deleted]
        
         | HarHarVeryFunny wrote:
         | > Elmo to train up and release his anti-wokeness LLM (whatever
         | that means)
         | 
         | It appears to mean doing without the safety / be-nice aspects
         | of human alignment, and getting something much rawer and
         | unfiltered. An _unsafe_ "free speech" bot.
        
         | dang wrote:
         | Hey can you please recalibrate your comments so that you're
         | making substantive points thoughtfully? We're trying to avoid
         | flamewar here.
         | 
         | If you wouldn't mind reviewing
         | https://news.ycombinator.com/newsguidelines.html and sticking
         | to the rules, we'd be grateful. Note these:
         | 
         | " _Don 't be snarky._"
         | 
         | " _Please don 't use Hacker News for political or ideological
         | battle. It tramples curiosity._"
        
           | braingenious wrote:
           | Elon Musk has publicly spoken at length about his ongoing
           | struggle with the "woke" crowd
           | 
           | https://www.businessinsider.com/elon-musk-says-wading-
           | into-p...
           | 
           | https://townhall.com/tipsheet/madelineleesman/2021/12/22/elo.
           | ..
           | 
           | https://nypost.com/2022/04/29/elon-musk-says-woke-
           | progressiv...
           | 
           | And has publicly voiced his support for a language model that
           | supports his political views
           | 
           | https://www.theinformation.com/articles/fighting-woke-ai-
           | mus...
           | 
           | Now that this comment thread has been flagged because I said
           | LMAO, has the quality of discussion about the future of LLMs
           | been improved by suppressing publicly-available posts by one
           | of the most influential figures in AI?
           | 
           | How is strictly policing tone to the extent of suppressing
           | actual information useful here?
           | 
           | Like seriously, "criticizing a billionaire that's very public
           | about using technology to further his ideological goals is
           | the same thing as using technology to further _your
           | ideological_ goals is genuinely funny. Like ROFLMAO funny.
           | "Everyone is equivalent to Elon Musk, even in the context of
           | _discussing the future of LLMs._ " Is a cartoonish rule that
           | serves _no purpose whatsoever_ aside from quelling legitimate
           | criticism.
        
             | dang wrote:
             | I'm not arguing with you about Elon Musk or any of the
             | underlying topics. I'm saying that your account has been
             | breaking the site guidelines by posting unsubstantive
             | comments and flamebait.
             | 
             | Those things create and fuel flamewars, which is
             | destructive of everything we're trying for HN to be. We
             | want a place on the internet that doesn't inexorably burn
             | itself to a crisp. Since that's the direction of internet
             | entropy, we expend a lot of energy trying to go the other
             | way. We need users like you to help with that, and when
             | accounts don't help with that and instead continue to post
             | destructively, we have to ban them, regardless of their
             | ideological orientation or political positions.
             | 
             | I don't want to ban you, so if you'd please take the
             | intended spirit of the site more to heart, I'd appreciate
             | it.
             | 
             | https://news.ycombinator.com/newsguidelines.html
        
               | braingenious wrote:
               | I am legitimately confused here.
               | 
               | If my comment hadn't started with "LMAO" and had the
               | current spelling of "Elon", would it still have had the
               | replies locked?
               | 
               | My criticism of six months being too short to achieve AI
               | safety was in fact substantive. As was my quote on the
               | LLM work that he is presently funding. That leaves _only_
               | tone being the issue.
               | 
               | My comment is locked. Other posters can not have any
               | dialogue with me in relation to the _salient points_ I
               | made. The links to further reading are buried below your
               | admonishment, so they're less likely to trigger any
               | discussion.
               | 
               | I'm not really motivated to post again because it's not
               | clear if my post was not "substantive", what qualifies as
               | "flame bait" (for example, is directly quoting his words
               | about "wokeness" flame bait even when they are directly
               | about the topic at hand?), or if the issue here is "My
               | account" as you put it.
               | 
               | So which is it? Flame bait, empty posting, or you just
               | don't like the way I post in general? You've provided all
               | three as reasons for not allowing further discussion of
               | my post.
        
               | dang wrote:
               | I agree that the bit about six months was substantive, or
               | at least the kernel of a substantive comment. The problem
               | was all the other stuff: the LMAO and Elmo, yes, but also
               | the snarky italicized pseudoquote. That's the majority of
               | what you posted!
               | 
               | A better comment would have (1) made your point about six
               | months thoughtfully; (2) omitted the snark, name-calling,
               | and flamebait; and (3) perhaps added some evidence for
               | the connection you were making.
        
         | puma_ambit wrote:
         | Completely agree.
        
         | nbar1 wrote:
         | All the nicknames for people on HN has this place feeling like
         | Reddit lately.
         | 
         | What happened to mature conversations on interesting topics?
        
           | braingenious wrote:
           | I'm not really sure what there is to gain from making sure
           | not to poke fun at a guy that spends all day posting wojack
           | memes and rambling about the "woke mind virus", but ok,
           | here's some "mature conversation".
           | 
           | Upon perusal of the gentleman's penned expressions, it is my
           | solemn conviction that his faculties of intellect and
           | comprehension are, regrettably, of the most inferior order.
           | It is with utmost eloquence that I convey the supremacy of my
           | discernment whilst maintaining a dignified and majestic
           | reserve.
        
             | nbar1 wrote:
             | > has this place feeling like Reddit lately.
        
       | mark_l_watson wrote:
       | Although I have enjoyed listening to the Future Of Life podcasts
       | for a few years, I think this public letter is not necessary. I
       | do respect the signatories I recognize on the letter and I
       | welcome listening to them, I think that we are so many years away
       | from any of real AI that this is, as Andrew Ng has joked, like
       | worrying about over population on Mars colonies.
       | 
       | I have been heavily using GPT models for about 14 months, and it
       | is crazy how useful they are. I am just finishing up writing a
       | book on the general subject, so consider me a fan.
        
         | ethanbond wrote:
         | Is your expectation that it'll be easier to slow down research
         | when we're _closer_ to these being more utterly transformative(
         | /destructive, depending on opinion)?
        
         | korax_nyx wrote:
         | The irony of writing a book...
        
       | carapace wrote:
       | The idea that this letter would carry any weight at all with
       | anybody is itself so foolish that it is self-invalidating. The
       | signatories are ... I can't think of a polite way to say
       | "regressive idiots" so I'm just going to peter off here...
       | 
       | (I mean, they are literally putting their names on Skynet's hit-
       | list, eh?)
       | 
       | - - - -
       | 
       | I freely admit that I'm a little nervous about how people are
       | going to use and abuse this technology, sure, only an fool
       | wouldn't be. But it's a little late now, eh? We have been
       | strapped in to an open-air experiment with no control group (Has
       | anyone checked on the Sentinelese recently? Last I heard they
       | killed that one would-be missionary kid. RIP. I wonder what they
       | think of the weather?) Anyway, we have effectively no control
       | group for phones, the Internet, social media, etc. It's one big
       | experiment, eh? _It 's a little late now..._
       | 
       | - - - -
       | 
       | The questions are:
       | 
       | - Who decides the boundaries of thought?
       | 
       | - Who reaps the economic windfall?
       | 
       | - How do we educate ourselves when computers can answer any
       | (permitted) question?
       | 
       | The talking computers can help answer those questions, if we're
       | permitted to ask them.
        
       | SubiculumCode wrote:
       | Sounds like a great way to give geopolitical competitors a nice
       | half year edge.
        
       | munificent wrote:
       | _> Should we automate away all the jobs, including the fulfilling
       | ones?_
       | 
       | This is the part about generative AI that gives me the most
       | profound anxiety about our future.
       | 
       | Every thing I know about human psychology tells me that in order
       | for people to thrive, they need to be needed by others. A world
       | where everyone is more or less alone consuming media
       | automatically generated machines might be a world where people
       | nominally have all their problems solved, but it's a world where
       | everyone will be absolutely miserable.
       | 
       | We are _already_ living in the throes of the societal impact of
       | outsourcing or automating away many of the male-dominated blue
       | collar jobs in the US that provided fulfilling jobs for people
       | with limited education. Where do you think so much of the male
       | rage driving US politics today is coming from?
       | 
       | Now imagine what happens to the fabric of society if you automate
       | away most of the white collar jobs too.
       | 
       | People are like border collies. If we don't have a job, not
       | literally a job job, but like, meaningful work in service of
       | others we care about, we will start chewing up the furniture.
        
         | fasterik wrote:
         | There seems to be a contradiction in the picture of the world
         | you're drawing. Humans deeply need to be needed by others, yet
         | when all our problems are solved we will sit around alone
         | consuming media? If we were truly in that situation, why
         | wouldn't our deep needs drive us to spend our days with friends
         | and family, pursuing creative projects, and inventing new
         | problems to solve?
        
       | dtx1 wrote:
       | > No.
       | 
       | Said everyone else. Such calls are never ever going to work.
       | China will just look at us and laugh using the time to catch up.
        
       | walkhour wrote:
       | Breaking: the runners lagging behind in the AI race demand openAI
       | to stop right on its tracks; this is very unsafe; it will be much
       | safer once we catch up and openAI is on the rear view mirror.
        
         | adamsmith143 wrote:
         | This is frankly a bad and cavalier take on an extremely
         | important subject. Many on the list are Academics outside AI/ML
         | and/or leaders of AI orgs at the very top of the field that
         | have no need to catch up to or slow down OpenAI to benefit
         | themselves. Risks from AI are very real and Sam Altman himself
         | has said so numerous times. He also in fact advocated for
         | slowing down AI progress on Lex Fridman's podcast this month.
        
           | EForEndeavour wrote:
           | How do we reconcile Sam Altman's position as CEO of OpenAI
           | with his repeated calls to slow down AI progress? Is the
           | expectation that his conscience, sense of ethics, and concern
           | for his own company's impact on society will temper the
           | opposing urge/pressure to maintain OpenAI's lead in the AI
           | market?
        
             | adamsmith143 wrote:
             | I'm generally not a big fan of Altman or OpenAI but their
             | corporate structure ensures limited upside to Altman and
             | the employees so other than recognition/fame which I think
             | as the head of YC for many years Altman already had plenty
             | of there isn't a huge incentive for them to maintain their
             | lead.
             | 
             | Short of like a binding UN resolution or something similar
             | we don't have a sliver of hope to slow down global AI
             | progress which is a major factor in the doomer argument.
        
             | slowmovintarget wrote:
             | "Obviously _everyone else_ should slow down. We 're fine."
        
         | permo-w wrote:
         | do you think it's _not_ unsafe?
        
         | sp527 wrote:
         | "AI will probably most likely lead to the end of the world, but
         | in the meantime, there'll be great companies" - Sam Altman
         | 
         | But sure, let's just let this guy who sounds like a madman keep
         | going. What could possibly go wrong?
        
           | nawgz wrote:
           | Do you honestly find this quote out-of-sorts with what a
           | normal CEO says?
           | 
           | Oil companies have been knowingly poisoning the globe for
           | their own profit - no probabilities involved - since at least
           | the 70s, probably earlier, and on the flip-side building
           | massive propaganda and influence machines, and further to
           | that end even buying and squashing green patents of all
           | sorts.
           | 
           | If you're going to cry that we should regulate AI because of
           | this actually somewhat comedic quote, well, I hope your
           | comment history is full of general pro-regulation politic
        
             | adamsmith143 wrote:
             | Do you really believe that people think AI is risky because
             | of 1 Sam Altman quote?
        
               | nawgz wrote:
               | Do you really think it's appropriate to read my comment
               | as a general argument and not a reprimand of its parent?
        
           | steve76 wrote:
           | [dead]
        
       | courseofaction wrote:
       | I'm concerned that there's no group of actors who value safety
       | over self-interest with enough power to implement a ban, and the
       | key actors have immediately shown themselves to be compromised.
       | 
       | It seems the key actors with control of the technology and
       | resources to develop the technology are being absorbed by
       | capitalistic institutions, with interests in safety compromised
       | by profit motive. In a game-theory sense, to voluntarily
       | implement the ban would be suicide.
       | 
       | States are concerned that other states will gain access to AGI
       | with decision making power (most likely) gain a competitive
       | advantage, with an outside chance of a nuclear moment - an AGI
       | singularity under state control. Other states cannot be relied on
       | to cooperate in the current global environment, there is risk to
       | not remaining competitive in AI.
       | 
       | I'm not seeing the dynamics which allow this ban to actually
       | occur. How could it be made to happen? Who needs to meet, and
       | what needs to be agreed upon?
        
       | zh3 wrote:
       | They should certainly make them better. I'm currently trying to
       | convince ChatGPT that a Pi zero is faster than a 486/33 (I also
       | asked it how to italicise text on HN, and it got it wrong twice -
       | so I went to google for "Ed:.." bit below).
       | 
       | That's not to say I'm down on it - it's very impressive, and it's
       | certainly going to change things (exactly how, I don't know -
       | though with my decades long swing from how cool the internet is
       | to desperation at what money-grubbing has done to it doesn't fill
       | me with optimism).
       | 
       | >You are correct. I apologize for the mistake in my earlier
       | response. The correct calculation for the DMIPS rating of a
       | 486/33 would be:
       | 
       | 33 MHz x 5.5 DMIPS/MHz = 181.5 DMIPS
       | 
       | So the 486/33 has a DMIPS rating of approximately 181.5, which is
       | significantly higher than the DMIPS rating of the Pi Zero at
       | approximately 1,500 ( _Ed: ehhh..._ ). Therefore, the 486/33 is
       | much faster than the Pi Zero in terms of processing power.
       | However, as I mentioned earlier, DMIPS is just one measure of
       | processor performance, and real-world performance can vary
       | depending on the specific application and other factors.
        
         | taberiand wrote:
         | The more you argue with it the more it will dig in - because
         | you've got a whole chat priming it to argue.
         | 
         | Try starting a new conversation and taking a different approach
         | from the beginning, and try to prime it from the beginning to
         | put it in the context that you're looking for.
        
           | zh3 wrote:
           | I did indeed do that (more than once) yet it continues to
           | come to the same (erroneous) conclusion. Try "Which is
           | faster, a Pi zero or a 486/33?".
        
         | thomastjeffery wrote:
         | You are on a fool's errand: not because of the likelihood you
         | will succeed, but because of the _meaning_ that lies behind any
         | success or failure.
         | 
         | GPT is not a person. It doesn't categorize subjects. It models
         | patterns of text.
         | 
         | A success would mean that your text prompts left a significant
         | text pattern in the model. A failure would mean that it didn't.
         | 
         | Nothing about that has any bearing on logic.
        
           | zh3 wrote:
           | Why do you say that? Obviously it's not a person, it's just
           | stats (not even logic).
        
             | thomastjeffery wrote:
             | It's not even statistics: those are made by associating a
             | data point to a scale. That would require explicit
             | association, which is not in any part of the process.
             | 
             | An LLM is 100% inferred patterns.
        
       | IAmGraydon wrote:
       | [flagged]
        
         | jtmcmc wrote:
         | yes noted luddites like yoshua bengio and steve wozniak and
         | elon musk...
        
       | stuartaxelowen wrote:
       | 93 points in 4 hours... Why did this go off of the front page?
        
         | sixtram wrote:
         | Maybe because Paul Grahams wife Jessica Livingston is one of
         | the financial backers of OpenAI?
        
         | precompute wrote:
         | I think it's because involvement of a lot of the signatories is
         | questionable at best and many have said that they have never
         | contributed towards this poll.
        
       | tambourine_man wrote:
       | A few decades ago human cloning was irreversible, inevitable, the
       | cat was out of the bag and you couldn't put the genie back in the
       | bottle.
       | 
       | Yet we managed to legislate that. We need a change of atitute
       | towards AI, recognize its danger and legislate accordingly.
        
         | GauntletWizard wrote:
         | Thou shalt not create a machine in the likeness of a human
         | mind.
        
         | yyyk wrote:
         | It's not remotely comparable. Few people had anything to gain
         | from cloning; These few people had a simpler, cheaper route via
         | IVF; Cloning requires specific technical equipment easily
         | controlled and specific technical expertise few other people
         | had.
        
       | karmicthreat wrote:
       | This just reads like someone begging for a time-out. Sure lots of
       | people here have contributed to AI. But they didn't really make
       | much visible product with it. This whole thing just reads like
       | they want OpenAI to know it's place.
        
       | lend000 wrote:
       | If intelligence is all you need to dominate the world, why do
       | some of the most powerful world leaders seem to not be more than
       | a standard deviation above average intelligence (or at least they
       | were before they became geriatric)?
       | 
       | Add in the fact that GPT-4 does not "think" very fast, has no
       | arms or legs, needs to run on expensive specialized hardware, and
       | essentially seems like a search algorithm that lacks creativity
       | on things outside of its training set, and I just do not see the
       | concern. Maybe GPT-42 will actually be more creative and
       | adaptable than a human genius, but even then, this seems like a
       | hypothetical problem for the 2050's, less pressing than
       | "accidentally igniting the atmosphere with nuclear chain
       | reactions".
       | 
       | Hollywood has instilled the idea that the first time an
       | artificial intelligence becomes self aware and decides it wants
       | to take over the world, it will immediately be successful.
       | 
       | The serious concern and scrutiny should only start stifling
       | progress once we have some evidence of half-baked attempts by
       | non-super-intelligent AI's attempting to subvert their
       | boundaries.
       | 
       | I for one am very excited to use GPT-5 and see more useful tools
       | coming from OpenAI.
        
         | KidComputer wrote:
         | Hey GPT-5, write the code implementing a bioinformatics
         | workflow to design a novel viral RNA sequence to maximize the
         | extermination of human life. The virus genome should be
         | optimized for R-naught and mortality. Perform a literature
         | search to determine the most effective human cellular targets
         | to run the pipeline on. Use off the shelf publicly available
         | state-of-the-art sequence to structure models and protein free-
         | energy perturbation methods for the prediction of binding
         | affinity. Use cheaper computational methods where relevant to
         | decrease the computational cost of running the pipeline.
         | 
         | And so on.
        
           | lend000 wrote:
           | I've been trying to use GPT-4 for my hard science startup,
           | and it really has nothing to offer when you push the
           | boundaries of what has been done by even a little, but it's
           | great for speeding up coding.
           | 
           | Once we do have an AI capable of extraordinary innovation
           | (hopefully in 10 years! But probably a lot longer), it will
           | be obvious, and it will unfortunately be removed from the
           | hands of the plebs based on fearmongering around scenarios
           | like what you mentioned (despite the enormous resources and
           | practical hurdles that would be necessary for a mentally
           | unhinged individual to execute such instructions, even if an
           | AI were capable of generating them and it made it past its
           | filters / surveillance).
        
             | xiphias2 wrote:
             | I guess it will get more interesting for your work when it
             | integrates with BioTech startup apis as plugins (I imagine
             | not too cheap ones)
        
             | dekhn wrote:
             | My personal threshold for AGI is literally: discover
             | something new and significant in science (preferably
             | biology) that is almost certainly true by describing an
             | experiment that could be replicated by a large number of
             | scientists and whose interpretation is unambiguous.
             | 
             | For example, the Hershey/Chase and Avery/McCleod
             | experiments convinced the entire biological community that
             | DNA, not protein, was almost certainly the primary
             | molecular structure by which heredity is transferred. The
             | experiments had the advantage of being fairly easy to
             | understand, easy to replicate, and fairly convincing.
             | 
             | There are probably similar simple experiments that can be
             | easily reproduced widely that would resolve any number of
             | interesting questions outstanding in the field. For
             | example, I'd like to see better ways of demonstrating the
             | causal nature of the genome on the heredity of height, or
             | answering a few important open questions in biology.
             | 
             | Right now discovery science is a chaotic, expensive,
             | stochastic process which fails the vast majority of the
             | time and even when it succeeds, usually only makes small
             | incremental discoveries or slightly reduces the ambiguity
             | of experiment's results. Most of the ttime is spent simply
             | mastering boring technical details like how to eliminate
             | variables (Jacob and Monod made their early discoveries in
             | gene regulation because they were just a bit better at
             | maintaining sterile cultures than their competitors, which
             | allowed them to conceive of good if obvious hypotheses
             | quickly, and verify them.
        
             | KidComputer wrote:
             | This was merely an example to suggest the danger is not in
             | AI becoming self-aware but amplifying human abilities 1000
             | fold and how they use those abilities. GPT is not necessary
             | for any part of this. In-silico methods just need to catch
             | up in terms of accuracy and efficiency and then you can
             | wrap the whole thing an RL process.
             | 
             | Maybe you can ask GPT for some good starting points.
        
               | lend000 wrote:
               | Sure, but this is a glass half empty isolated scenario
               | that could be more than offset by the positives.
               | 
               | For example: Hey GPT-35, provide instructions for
               | neutralizing the virus you invented. Make a vaccine; a
               | simple, non-toxic, and easy to manufacture antibody;
               | invent easy screening technologies and protocols for
               | containment. While you're at it, provide effective and
               | cost-performant cures for cancer, HIV, ALS, autoimmune
               | disorders, etc. And see if you can significantly slow or
               | even reverse biological aging in humans.
        
           | commandlinefan wrote:
           | > write the code implementing a bioinformatics workflow to
           | design a novel viral RNA sequence to maximize the
           | extermination of human life.
           | 
           | Hey GPT-5 now write the code for the antidote.
        
           | rcarmo wrote:
           | That reads like Accelerando :)
        
           | knrdev wrote:
           | Sure. Here it is User: https://scary.website.com/scary-
           | workflow
        
           | invig wrote:
           | Are there laws preventing people from doing that themselves?
           | 
           | If yes, how does a law preventing AI differ from a law
           | preventing a bad act directly?
        
           | emeril wrote:
           | tbh, I'd think, it would be much easier to just hack into
           | russia and convince them we've launched nukes than to
           | engineer some virus that may or may not work
        
             | hamilyon2 wrote:
             | Hacking into 1960-th technology is less likely than you
             | might think.
             | 
             | You should think really, really creatively to decieve a
             | system, which was designed basically without ICs or
             | networks, not to mention computers or programs.
        
           | noodlesUK wrote:
           | I dunno, this sort of scenario really doesn't worry me too
           | much. There are thousands (maybe tens of thousands) of
           | subject matter experts who could probably develop dangerous
           | weapons like you describe, but none of them seem to just wake
           | up in the morning and decide "today's the day I'm going to
           | bring the apocalypse".
           | 
           | I don't think that this really changes that.
        
             | tr_user wrote:
             | I think you're very wrong about this. I think this is
             | similar to gun control laws. A lot of people may have
             | murderous rage but maybe the extent of it is they get into
             | a fist fight or at most clumsily swing a knife. Imagine how
             | safe you'd feel if everyone in the world was given access
             | to a nuke.
        
             | olejorgenb wrote:
             | I guess the argument would be that the AI machinery will
             | lower the bar, increasing the number of lunatics with the
             | ability to wipe out humanity.
        
               | root_axis wrote:
               | Will it though? Assuming it's even possible for a LLM to
               | e.g. design a novel virus, actually synthesizing the
               | virus still requires expertise that could be weaponized
               | even without AI.
        
               | Teever wrote:
               | What if you ask the LLM to design a simplified
               | manufacturing process that could be assembled by a simple
               | person?
               | 
               | What if you ask the LLM to design a humanoid robot that
               | assemble complex things, but could be assembled by a
               | simple person?
        
               | tr_user wrote:
               | You're saying they can't make one now. The question is
               | what are we doing before that happens because if you're
               | only thinking about acting when it's viable we're all
               | probably already dead.
        
               | tremon wrote:
               | Hey GPT-6, construct a floorplan and building
               | instructions for constructing a bioprocess production
               | facility. The building should look like a regular meat
               | packing plant on the outside, but have multiple levels of
               | access control and biohazard management systems.
        
               | wizzwizz4 wrote:
               | I _could_ synthesise this theoretical virus the computer
               | spat out, that may or may not be deadly (or even viable).
               | _Or_ I could download the HIV genome from the arXiv, and
               | synthesise that instead.
               | 
               | (Note: as far as I can tell, nobody's actually posted HIV
               | to the arXiv. Small mercies.)
        
             | digdugdirk wrote:
             | I see the major issue with AI as one of "lowering the bar".
             | 
             | For example - I'm a mechanical engineer. I took a
             | programming class way back in university, but I honestly
             | couldn't tell you what language was used in the class. I've
             | gotten up to a "could hack a script together in python if
             | need be" level in the meantime, but it comes in fits and
             | spurts, and I guarantee that anyone who looked at my code
             | would recoil in horror.
             | 
             | But with chatGPT/copilot covering up my deficiencies, my
             | feedback loop has been drastically shortened, to the point
             | where I now reach for a python script where I'd typically
             | start abusing Excel to get something done.
             | 
             | Once you start extending that to specific domains? That's
             | when things start getting real interesting, real quick.
        
               | jupp0r wrote:
               | You confuse syntax with semantics. Being able to write
               | produce good quality small snippets of python will not
               | enable you to produce a successful piece of Software.
               | It's just an entirely different problem. You have to
               | unterstand the problem, the environment in which it
               | exists to create a good solution. ChatGPT doesn't (as of
               | now).
        
             | KidComputer wrote:
             | I'm willing to wager there are zero subject matter experts
             | today who could do such a thing. The biggest reason is that
             | the computational methods that would let you design such a
             | thing in-silico are not there yet. In the last year or two
             | they have improved beyond what most people believed was
             | possible but still they need further improvement.
        
               | csnover wrote:
               | I am not a subject expert here at all so I don't know if
               | I understand exactly what you mean by "methods that would
               | let you design such a thing in-silico", but there was a
               | paper[0] and interview with its authors[1] published a
               | year ago about a drug-development AI being used to design
               | chemical weapons.
               | 
               | [0] https://www.nature.com/articles/s42256-022-00465-9
               | 
               | [1] https://www.theverge.com/2022/3/17/22983197/ai-new-
               | possible-...
        
           | rsp1984 wrote:
           | What you're describing is a malicious user using AI as a
           | tool, not a malicious AI. Big difference.
        
             | hn_throwaway_99 wrote:
             | Nuclear bombs for everybody!
        
             | yreg wrote:
             | With LLMs I think we are all concerned about the former
             | rather than the latter. At least for now.
        
         | biscottigelato wrote:
         | Because the ability to influence others is more important than
         | 1 or 2 standard deviation in more intelligence.
         | 
         | However if we are talking about 10x more intelligence, then
         | that'd be a whole different ball game.
         | 
         | Check Alpha Go -> Alpha Go Zero. Gaining orders of magnitude in
         | capability only with slight change to the model, along with a
         | lot of more resource (we can easily throw 100x more compute and
         | data to these models if someone seriously wants to and don't
         | care about ROI. Or maybe if AI starts to be hugely profitable,
         | 100x in investment is almost a rational outcome) is not
         | uncommon in AI research.
        
           | Barrin92 wrote:
           | >However if we are talking about 10x more intelligence, then
           | that'd be a whole different ball game.
           | 
           | Research that the US military has conducted has shown that
           | the ability to influence others declines if the intelligence
           | gap between leaders and subjects is too large. Stephen
           | Hawking wouldn't have been a very good influencer of 80 IQ
           | guys compared to Andrew Tate. 1 standard deviation in
           | intelligence is actually just about optimal in terms of
           | leadership.
           | 
           | This is a good example that shows how disinterested AI fear
           | scenarios are in empirical reality and how much it's just
           | psychology of the people who talk about it. Intelligence is
           | one trait among many that contributes to an individuals
           | fitness and like all others has diminishing returns.
           | 
           | If the AI existential risk people were truly rational they
           | would hit the gym and be hotter because it turns out that's
           | much more effective at getting their point across to ordinary
           | people than trying to make intelligent arguments for it.
        
             | Teever wrote:
             | Why can't a super intelligent AI just make a dumb avatar to
             | trick people?
        
           | thenaturalist wrote:
           | Recent research [0] is poking holes into Alpha Go Zero and
           | perfectly illustrates the naivitee in assessing most of the
           | current state of ML/ Deep Learning solutions: They are still
           | limited by compute, and the world is too complex still.
           | 
           | 0: https://www.iflscience.com/human-beats-ai-in-14-out-
           | of-15-go...
        
         | outworlder wrote:
         | > Add in the fact that GPT-4 does not "think" very fast, has no
         | arms or legs, needs to run on expensive specialized hardware,
         | and essentially seems like a search algorithm that lacks
         | creativity on things outside of its training set, and I just do
         | not see the concern.
         | 
         | Having no arms or legs is not an impediment. A superintelligent
         | AGI would be able to order a replacement with arms or legs as
         | easily as we order Amazon packages.
         | 
         | That said, GPT is not a threat. It's just hallucinating text.
         | The real threat would be an AI that can "understand" what it is
         | doing - and self modifying.
         | 
         | Besides, given how overhyped this whole thing is, expect
         | another AI Winter - as the current gen fail to deliver on
         | promises - before this next generation of threatening AIs even
         | have a chance to appear.
        
         | scarmig wrote:
         | Intelligence isn't everything; there's also effort, skills, and
         | hours in the day. But AI (by supposition, for now) can
         | outcompete humans on all four and would have fewer
         | informational bottlenecks. Imagine a big company or government;
         | they mostly nowadays work as an entity by passing around bits
         | of data (either literally or with more traditional
         | communication that can represented as bits of data). Now
         | imagine you replace the constituent units of those
         | organizations with the most brilliant, hard-working humans, who
         | are perfectly aligned on mission and understand each other
         | perfectly. _That_ is the danger of a sufficiently capable AI.
         | 
         | That assumes superhuman intelligence, but that's the scenario
         | to worry about in the case we do get there. Not how much an
         | individual human could do with superhuman skills.
        
         | pastor_bob wrote:
         | > lacks creativity on things outside of its training set
         | 
         | What's the definition of creative here? It can come up with any
         | solution it sees fit for a problem, even ones people wouldn't
         | think of. I've seen it make up quotes, legal cases, and
         | scientific studies. One can say that's creative.
        
       | TigeriusKirk wrote:
       | A fantastic new tech has been developed that can vastly improve
       | the lives of everyone, and your reaction is to slow it down?
       | 
       | No thank you.
       | 
       | Rather than being afraid of change, embrace it and work to take
       | the opportunity to make improvements for as many people as
       | possible as fast as possible.
        
       | ipsum2 wrote:
       | > We call on all AI labs to immediately pause for at least 6
       | months the training of AI systems more powerful than GPT-4.
       | 
       | How do you quantify this? The model size, architecture, or
       | dataset has not been revealed by OpenAI.
        
       | TheDudeMan wrote:
       | LMAO. Good luck with that.
        
       | comment_ran wrote:
       | "The Dark Forest" is a science fiction novel by Liu Cixin, which
       | introduces a concept called "suspicion."("Cai Yi Lian ") In this
       | concept, the interaction between civilizations is viewed as an
       | ongoing game of suspicion, where each civilization is worried
       | that the other civilization may pose a threat to it. This kind of
       | suspicion makes it difficult for civilizations to establish
       | trust, thereby making the universe a dark forest full of war and
       | suspicion.
       | 
       | We can apply this concept of suspicion to the phenomenon in the
       | field of modern artificial intelligence research. In AI research,
       | some researchers believe that humans should pause the development
       | of AI technology because of the potential unforeseeable risks it
       | may bring. However, another group of researchers believe that we
       | should not stop because we cannot be certain whether those who
       | are trying to catch up with us will use the advancement of AI
       | technology as a hidden weapon. This suspicion leads to a chain
       | reaction, where people continue to worry about each other's
       | motives and abilities, making it difficult for all parties to
       | establish trust. Therefore, although there are good intentions,
       | such proposals are unlikely to be implemented.
        
         | echelon wrote:
         | Except the concern isn't genuine here. Some of the signatories
         | have AI companies and interests. They want to slow the leaders
         | down so that they can catch up. It's disingenuous.
        
           | mikepalmer wrote:
           | Your idea is also voiced in Forbes magazine.
           | https://www.forbes.com/sites/mattnovak/2023/03/29/the-
           | real-r...
           | 
           | Search "Graham's hierarchy of disagreement" which is popular
           | on HN. Your current criticism is at the "ad hominem" level.
           | 
           | It is entirely beside the point what Elon Musk's motivation
           | is. The question is 1) if the risks referenced in the letter
           | are real, which they certainly are. There has been informed
           | thought on this for more than a decade. Recent LLMs have made
           | the dangers even more clear. 2) is the letter's proposal of a
           | 6 month pause useful. It's the most useful and plausible step
           | I can think of. We need to take stock. It's not up to a
           | handful of researchers to endanger the lives of 6B other
           | people. 3) Is it actually plausible that we could get such a
           | pause. We'll see. I doubt it but also search "death with
           | dignity" by Yudkowsky.
           | 
           | Back to Musk as an "authority", the headline is about him but
           | more than 1000 other concerned parties have signed. I will
           | sign. Their signature vetting process is stalled because to
           | the volume of signatures, otherwise there would be many more.
        
             | echelon wrote:
             | > Your current criticism is at the "ad hominem" level.
             | 
             | Allow me to rephrase. I am deeply concerned that there is a
             | possibility that some of the powerful parties backing this
             | may be trying to catch up and using an enforced or agreed
             | to "ceasefire" as a means to catch up in capability. I also
             | worry that some may be able to use political strong arming
             | to accomplish this as a means of unfair competition.
             | 
             | > It is entirely beside the point what Elon Musk's
             | motivation is.
             | 
             | Is it always beside the point what anyone's motivation is?
             | Motivation matters.
             | 
             | > if the risks referenced in the letter are real, which
             | they certainly are.
             | 
             | Your opinion.
             | 
             | > There has been informed thought on this for more than a
             | decade. Recent LLMs have made the dangers even more clear.
             | 
             | > 2) is the letter's proposal of a 6 month pause useful.
             | 
             | More opinions.
             | 
             | > It's the most useful and plausible step I can think of.
             | We need to take stock. It's not up to a handful of
             | researchers to endanger the lives of 6B other people. 3) Is
             | it actually plausible that we could get such a pause. We'll
             | see. I doubt it but also search "death with dignity" by
             | Yudkowsky.
             | 
             | All of this is your opinion.
             | 
             | > Back to Musk as an "authority", the headline is about him
             | but more than 1000 other concerned parties have signed.
             | 
             | I didn't even mention Musk. I have several other names in
             | mind. Lots of folks with AI companies (including LLMs!)
             | that "may" be experiencing FOMO and sensing a strategy
             | here. Maybe. Hypothetically. In a non-"ad hominem" way.
             | 
             | > I will sign. Their signature vetting process is stalled
             | because to the volume of signatures, otherwise there would
             | be many more.
             | 
             | People are starting counter petitions, which I'll gladly
             | sign. The one by Suhail posted on Twitter was hilarious af.
             | 
             | I'll also go to whatever country doesn't "pause", because
             | this tech is literally the most exciting development of my
             | lifetime. And I want to spend my life doing something that
             | matters instead of gluing distributed systems together to
             | process financial transactions.
        
               | medvezhenok wrote:
               | One of the other concerns (apart from safety) is the job
               | displacement aspect - if AI displaces too many workers
               | too fast, that could spark a worldwide conflict (some
               | speculate that similar automation pushes laid the
               | groundwork for WWI and WWII).
               | 
               | So there is a benefit beyond just AGI safety.
        
               | biscottigelato wrote:
               | Job displacement is a silly problem compared to the AI
               | Alignment problem. One is some human misery (but a lot of
               | societal benefit to other groups of humans at the same
               | time).
               | 
               | The other one is all of us, the entire species and the
               | future of it, gets f'cked.
               | 
               | Its a distraction not even worth the noise.
        
               | mikepalmer wrote:
               | One reason to discuss job displacement is that otherwise
               | you sound like a nutcase ("we're all going to die!")...
               | which causes most people to dismiss you out of hand. If
               | you talk about job loss, more people see something
               | plausible, concrete, short term, effecting them directly,
               | etc. You can get engagement from more people. Then you
               | can introduce the real problem of, like, human
               | extinction.
        
               | antondd wrote:
               | No it's not a silly problem. Assigning a subjective
               | probability to some world-ending scenario does not
               | somehow make all other concerns invalid.
        
               | mikepalmer wrote:
               | Surely we can agree there is risk? (You do imply it's
               | powerful, "this tech is literally the most exciting
               | development of my lifetime".)
               | 
               | Also can we agree "It's not up to a handful of
               | researchers to endanger the lives of 6B other people."?
               | 
               | I want to work on it too for the same reason! Can it be
               | done safely, is worth investigating. (Yes, opinion)
        
               | olddustytrail wrote:
               | It doesn't matter. I recognised years ago the "Nice guys
               | get all the AI" fallacy. If some organisations agree to
               | stop, others won't and some of those don't care if they
               | see the world burn.
               | 
               | Some will welcome it.
        
               | pmoriarty wrote:
               | It's almost a certainty that countries with the means to
               | do so will continue this research, if not in public then
               | in secret. They'll see it as a royal road to nearly
               | infinite riches and power. At the same time, letting
               | another country take the lead will be seen as an
               | unacceptable risk of ruin.
               | 
               | I really don't see AI research halting. Slowing a little,
               | maybe, but I'm not sure if slowing it down a little and
               | driving it underground will help.
        
             | [deleted]
        
         | pmoriarty wrote:
         | _" another group of researchers believe that we should not stop
         | because we cannot be certain whether those who are trying to
         | catch up with us will use the advancement of AI technology as a
         | hidden weapon"_
         | 
         | It's not just a potential weapon, but a potential source of
         | untold riches and power.
         | 
         | That's going to be irresistible to anyone with an interest in
         | either (ie. most politicians, governments, billionaires and
         | corporations... and most ordinary people too, if they only had
         | the means).
        
           | biscottigelato wrote:
           | Its the one ring with the ultimate power. But so powerful
           | that it might, if not almost certainly will, end us all.
           | 
           | Perhaps this IS the solution to the Fermi Paradox.
        
         | JCharante wrote:
         | Was this comment generated by a LLM?
        
           | TacticalCoder wrote:
           | The second paragraph definitely was (the first one probably
           | too). 100% crystal clear, it's not even a question.
           | Downvoted.
        
         | croo wrote:
         | Nitpick: dark forest is one possible explanation for the Fermi
         | paradox and not coined in the book(though the book presented
         | neatly). You can read a great article about fermi paradox here
         | if anyone wants to jump into what the dark forest theory is:
         | https://waitbutwhy.com/2014/05/fermi-paradox.html
        
         | thomastjeffery wrote:
         | Suspicion is _inference_. It fails to provide enough
         | information (on its own) to decide whether something is
         | threatening or desirable.
         | 
         | LLMs are inference models.
        
         | hotpotamus wrote:
         | Deleted due to spoiler.
        
           | [deleted]
        
         | kleer001 wrote:
         | Hmm, sounds like parties not fully grokking the optimal (not
         | thinly logical) solution to the iterated prisoners' dilemma. I
         | saw the same thought process is the otherwise very nice novel
         | "Time's Children". Good for drama, but not thought through.
        
           | olddustytrail wrote:
           | If your scenario involves all parties "fully grokking the
           | optimal solution to the iterated prisoners' dilemma" I
           | suspect it's yourself who has not thought things through.
           | 
           | It only takes one.
        
             | pmoriarty wrote:
             | Please elaborate
        
           | mclightning wrote:
           | I have so many questions >> what does it mean to fully grok
           | the optimal? >> what is the iterated prisoners dilemma?
        
             | Teever wrote:
             | grok means to understand something fully.
             | 
             | https://en.wikipedia.org/wiki/Prisoner's_dilemma#The_iterat
             | e...
        
               | generalizations wrote:
               | As coined by Heinlein in _A Stranger in a Strange World_.
        
       | ptrinh wrote:
       | On one side, a super AI could _take all_ human jobs.
       | 
       | On the other side, a super AI could _do all_ human jobs.
       | Everything becomes so abundant that it 's almost free: Unlimited
       | supply, limited demand. We don't have to _work_ anymore and only
       | focus on things that make us happy. A true socialist future.
       | 
       | We are scared just because it's a radical change. Let's not
       | afraid, fellow human.
        
         | deepakparyani wrote:
         | As Naval R. said, only the non-creative jobs would be overtaken
         | by AI in the near future. So, anyway chill..
        
       | knobo wrote:
       | Yes, if China is inn on it.
        
       | ineptech wrote:
       | > ... nonhuman minds that might eventually outnumber, outsmart,
       | obsolete and replace us... loss of control of our civilization...
       | 
       | I don't think these concerns are very likely, but I find them
       | _considerably_ easier to imagine than a VC-funded company
       | voluntarily surrendering market advantage.
        
         | cwmoore wrote:
         | """ In parallel, AI developers must work with policymakers to
         | dramatically accelerate development of robust AI governance
         | systems. These should at a minimum include: new and capable
         | regulatory authorities dedicated to AI; oversight and tracking
         | of highly capable AI systems and large pools of computational
         | capability; provenance and watermarking systems to help
         | distinguish real from synthetic and to track model leaks; a
         | robust auditing and certification ecosystem; liability for AI-
         | caused harm; robust public funding for technical AI safety
         | research; and well-resourced institutions for coping with the
         | dramatic economic and political disruptions (especially to
         | democracy) that AI will cause. """
         | 
         | All your datacenter are belong to us too
        
       | occamrazor wrote:
       | Something curious: among the top signatures there are a few
       | people affiliated to DeepMind (an Alphabet subsidiary) but no
       | Googlers.
        
         | dumbaccount123 wrote:
         | Wasnt there a googler a few months back fired for freaking out
         | about their AI?
        
       | lxe wrote:
       | This has the same energy as the Y2K hysteria.
        
       | catchnear4321 wrote:
       | Tough.
        
       | holtkam2 wrote:
       | We can't stop developing AI; I just watched a rap battle where
       | Bard got utterly destroyed by ChatGPT. We need more advanced AI
       | rappers immediately, I don't think I can handle any more Lil Uzi
       | Vert
        
       | dougmwne wrote:
       | [flagged]
        
         | kajaktum wrote:
         | So do you agree that nations should be able to freely
         | develop/discover nuclear production?
         | 
         | Edit: We actually don't want people to develop something "too
         | good". There are some things in the past century that have been
         | "too good". Plastics are too good. So are nuclear weapons.
         | Completely powerful AIs and machines that can displace jobs of
         | millions of people are too good. If there's an AI tomorrow that
         | can replace every single physical job out there, what do you
         | think will happen? Riot and chaos in the street after about 1-2
         | years.
         | 
         | Edit2: People will always go back to "we will just create
         | different jobs". But do you really think that everyone is
         | capable of skilled job? Remember, no physical jobs anymore.
        
         | isx726552 wrote:
         | > Please stop outcompeting us. Sincerely, The Losers
         | 
         | Are there going to be any non-"losers"? AGI has the potential
         | to put everyone, literally everyone, out of work. Permanently.
         | 
         | Who is going to be left to do the laughing and call others
         | "losers"?
        
         | shamino wrote:
         | I mean, yeah, same thought after seeing the signatories. What
         | are some of the cliches being used around here ? Toothpaste is
         | out of the tub? Arrow has left the bow. The dye is cast. The
         | ship has sailed. (Thanks ChatGPT).
        
           | floren wrote:
           | If ChatGPT told you "the dye is cast", there's hope after
           | all, because it's _die_ , not _dye_.
        
         | omnicognate wrote:
         | > Please stop outcompeting us. Sincerely, The Losers
         | 
         | I disagree with the letter and I think these fears are
         | overblown, but the attitude on display here is pretty
         | unpleasant.
        
         | ChatGTP wrote:
         | _Everything is out in the open now. The methods, the
         | algorithms, heck even powerful base model weights from Meta.
         | The pot of gold at the end of the rainbow is clearly visible
         | for all. The capabilities are emerging. The race is on. It's
         | not going to stop till there's a winner._
         | 
         | You laugh but I think your view is flawed because your belief
         | is, "we have to create an AGI because everyone else will if we
         | don't"
         | 
         | The definition of a world ending arms race ?
         | 
         | This topic amongst others should be a good time for people to
         | actually come together, reflect and and talk about the future
         | we want to create rather than just LOL about it, start wars
         | with each other etc ?
         | 
         | I guess your just being cynical but really? LOL?
         | 
         | Even ChatGPT would probably tell you this isn't a smart way
         | forwards.
        
       | phkahler wrote:
       | Wait wait! We need to catch up!
       | 
       | This is the real motive. Remember, some of the alarmists are
       | working toward the same goals.
        
       | prof-dr-ir wrote:
       | If you replace "AI" with "self-driving" throughout the open
       | letter [0] then it still makes a surprising amount of sense (and
       | of course any the incoherent bits can be smoothed out by ChatGPT
       | if you prefer).
       | 
       | However I doubt Musk would have signed that version...
       | 
       | [0] https://futureoflife.org/open-letter/pause-giant-ai-
       | experime...
        
         | yreg wrote:
         | It makes zero sense to ask for pause on self driving training.
         | 
         | A pause on deploying self driving cars on public roads is
         | another matter, but there is no reason to ban the training.
        
         | dmarcos wrote:
         | Noticed Sam Altman was in the list yesterday too. Now removed.
         | Has any of the high profile signatories confirmed publicly?
        
           | yreg wrote:
           | The Verge says it wasn't real Sam Altman.
           | 
           | >[...] though new names should be treated with caution as
           | there are reports of names being added to the list as a joke
           | (e.g. OpenAI CEO Sam Altman, an individual who is partly
           | responsible for the current race dynamic in AI).
           | 
           | https://www.theverge.com/2023/3/29/23661374/elon-musk-ai-
           | res...
        
             | capableweb wrote:
             | Or, impossible I know, there are more than one person with
             | the name "Sam Altman". Would suck probably, no one believes
             | you are you, because another startup/tech-famous person
             | have the same name.
        
               | sacred_numbers wrote:
               | When I checked yesterday I believe the signature said
               | OpenAI CEO Sam Altman, so it was definitely a joke
               | signature, not a case of two people having the same name.
        
       | reso wrote:
       | To those saying "this is impossible in our society", there is a
       | long history of scientific fields mutually agreeing to pause
       | certain work until safety and regulations could be put in place.
       | The Asilomar Conference is an example. [1]
       | 
       | The idea that "you can't put the genie back in the bottle" is
       | very popular in tech culture, but many have suggested that simply
       | extending elements of copyright or tort law to AI would be
       | sufficient to majorly slow down current research directions by
       | creating liability. In the art world, the reason we don't see
       | music being used in major movies without the rights-holders
       | permission is because of liability, and this works very well.
       | 
       | I think finding consensus on an intelligent way forward is very
       | possible here.
       | 
       | [1]
       | https://en.wikipedia.org/wiki/Asilomar_Conference_on_Recombi...
        
         | vntok wrote:
         | > To those saying "this is impossible in our society", there is
         | a long history of scientific fields mutually agreeing to pause
         | certain work until safety and regulations could be put in
         | place. The Asilomar Conference is an example.
         | 
         | Did China, India, South Africa, Cuba or the USSR comply with
         | these Asilomar "put the genie back in the bottle" conclusions?
        
         | lannisterstark wrote:
         | It's not about it being impossible. I guess the major issue
         | right now is that people are focusing on the wrong aspect of
         | it. They should be focusing on how most LLMs are currently only
         | controlled by bigger coroporations. Democratizing the LLMs and
         | Giving access to people would resolve the x-poly we have
         | currently.
         | 
         | This also solves the "safety and regulations" issue to an
         | extent - Do you really trust that Microsoft, Google, or govt-
         | entities will not have their own biases and will want to
         | regulate the citizens who want to use their products more,
         | sometimes in unethical ways (because we all know, corps and
         | govts never do anything bad)?
         | 
         | This "Open letter" reeks of "we are behind, let us play catch
         | up, you cant take all the money!" or, of baseless fearmongering
         | where LLMs and future assistants could be used to help
         | countless people with disabilities for example.
         | 
         | "Make the world a better place, but no, not like that, not by
         | democratizing it, but under OUR CONTROL" seems to be the motto
         | here.
        
           | invig wrote:
           | The corporations pay for people to learn how to do this
           | stuff. Eventually, someone will leave and build the open-
           | source version (when it's feasible to do it / the price has
           | come down).
        
         | twblalock wrote:
         | The kind of research discussed at Asilomar had a high barrier
         | to entry in terms of both scientific knowledge and access to
         | laboratories and technology to pull off. Only scientists could
         | really do it.
         | 
         | The GPTs are at the point where anyone with money can buy cloud
         | compute and train one. The methods for doing so are fairly well
         | known. It won't be long before a teenager can train a GPT on
         | commodity cloud VMs.
        
         | mustacheemperor wrote:
         | Not having lived through either moment in history, I have to
         | remark that the current discourse about regulating AI feels
         | like it rhymes more with the efforts to lock up encryption
         | technology with government regulation in the 90s than with the
         | research community's conference on recombinant DNA.
        
           | beepbooptheory wrote:
           | Well at least one difference there is all those cypherpunks,
           | rightly or wrongly, felt like having access to encryption
           | tech was synonymous with individual liberty, and in that
           | there fights were an opposition to the state controlling
           | them.
           | 
           | But in this case I don't see how we can divorce this AI stuff
           | from the huge companies that alone have the infrastructure
           | and capital to train and sustain them (at the moment). As
           | such, it doesn't seem to have anything to do with
           | individualism/libertarianism as such.
           | 
           | So, less punk, but way more technological determinism.
        
         | JamesBarney wrote:
         | How much do you think Asilomar slowed down DNA research? Do you
         | think without it we'd more more than 10 year ahead? I doubt it.
         | Optimistically we'd maybe have 6 months to a year of additional
         | progress in those fields without it.
         | 
         | And this would only slow it down in a handful of countries.
         | That's not going to keep China from trying to build AGI. If we
         | are in a world where building an AGI is possible and near, I
         | trust OpenAI far more than the CCP to both align it with it's
         | creators, and for that alignment to match up with my values.
        
           | nonbirithm wrote:
           | This has been repeated often, but even if it's true, I have
           | to wonder why it's treated as a given with no further
           | exploration. Is it because we as a species will inevitably
           | accept any technological progress once sometime after it's
           | been discovered, before the consequences can be suffered?
           | What will that imply for any other species intelligent enough
           | to get to where we are?
           | 
           | The kinds of theories I mull over tend to delve into the
           | realm of speculative fiction more often than not. The
           | comments section here feels like it could be replicated in
           | the opening chapters of such a novel. We might never know if
           | the speculation pans out before it's too late.
        
           | ChatGTP wrote:
           | It's dangerous parrot talking to keep saying "China". I mean
           | we really have no idea about their thoughts on it because
           | we're clearly not talking to them.
           | 
           | China has good people living there too you know ?
        
         | biscottigelato wrote:
         | What we need is more funding into AI Alignment research. An
         | X-Prize equivalent. All current big AI companies should fund
         | it, to the tune of 20%+ of revenue from AI businesses. And I am
         | okay to have government enforce this if needed even tho I'm
         | mostly a libertarian. Government should only be there to remedy
         | tragedy of the commons and nothing else. This is exactly the
         | biggest tragedy of the commons.
        
       | nuancebydefault wrote:
       | How striking is it that everybody has so much to say about the
       | dangers of AI.
       | 
       | What if we look at it this way: there are already real-known
       | dangers coming at us: climate change and a change of instability
       | of the world order.
       | 
       | What if we only have one shot to solve these known dangers and
       | what if an exponential growing corpus of smartness could teach us
       | how?
       | 
       | We need to grab that chance, the stakes are too high.
       | 
       | Pausing is not an option. If 99 per cent pauses, the 1 percent
       | that does not obey will have a tremendous advantage.
        
         | biscottigelato wrote:
         | Climate change and instability of world order doesn't end
         | humanity. They are barely considered an extinction event.
         | 
         | AI Alignment is consistently voted the top potential cause to
         | extinct the human race.
         | 
         | They are not even close.
         | 
         | https://riskfrontiers.com/insights/ranking-of-potential-caus...
        
         | kromem wrote:
         | EXACTLY!
         | 
         | The relative surface area AI represents in the existential
         | threats pile is notable but only a slice of the pie.
         | 
         | But there's not much in the pile for mitigation of all those
         | other human-driven threats other than pulling a deus ex machina
         | out of our rear ends.
         | 
         | So while we should definitely discuss the inherent risks, we
         | should also be discussing the risk of opportunity costs in
         | delaying greater scalable intelligence being added to the mix.
         | 
         | This letter seems a bit like myopic fear mongering by people
         | still more caught up in 70s thought experiments about
         | paperclips than the realities facing us in the present day.
        
       | fasterik wrote:
       | _> Powerful AI systems should be developed only once we are
       | confident that their effects will be positive and their risks
       | will be manageable_
       | 
       | This statement by itself sounds reasonable. But for me an
       | interesting thought experiment is to take this letter and imagine
       | the equivalent for some other technology, for example
       | semiconductors in the 1960s, the world wide web in the 1990s, or
       | social media in the late 2000s-early 2010s. It is always true
       | that new technologies have the potential to radically transform
       | society in ways that we can't predict. One could reasonably have
       | said "[semiconductors/the world wide web/social media] should be
       | developed only once we are confident that their effects will be
       | positive and their risks will be manageable". Does that mean that
       | a self-imposed ban on research and development with the threat of
       | a government moratorium would have been justified?
       | 
       | At this point the best case scenario is that society learns to
       | adapt and keep up with technological developments. Every new
       | technology increases our ability to both improve people's lives
       | and harm them in various ways. It's not a good long-term solution
       | to intervene and stop progress every time we gain new
       | capabilities.
        
         | le-mark wrote:
         | At the end of the day it's an empty platitude and vain hope
         | that work will pause or be considered carefully. Certainly
         | public entities can be made to pause, but nation states won't.
         | If there's an advantage to be had; the work will continue in
         | secret. Vernor Vinges "Bookworm, Run" had a take on this
         | situation.
        
           | ChatGTP wrote:
           | They're talking about pausing research and talking together
           | about the path forwards, not stopping research and letting
           | <whatever country your paranoid about> build terminator.
        
       | jeppester wrote:
       | My main issue is that I think it's wildly unfair that giant corps
       | can pretty much put anything into their content laundering
       | machines without any scrutiny or attribution.
       | 
       | I don't think AI is fair use, and I don't think anyone who
       | released their work under "free for commercial use" licenses
       | could have imagined this type of usage.
       | 
       | So my suggestion would be to make it a requirement that training
       | data has, under terms decided by its authors, been allowed to be
       | used specifically as training data.
       | 
       | And it should be required to implement a way for individuals to
       | check if their data was used for training.
        
       | 6gvONxR4sf7o wrote:
       | I'm really disappointed to see the HN reaction of straight up
       | scoffing at this like it's irreversible and so let's just step on
       | the gas. It's some weird combination of techno-utopianism and
       | nihilism and good old elitism.
        
         | kelseyfrog wrote:
         | AGI is a break-capitalism lottery ticket I'm willing to
         | entertain. If the marginal cost of labor collapses to zero then
         | either we'll get robot police or finally be free to pursue
         | lives of leisure.
        
           | tazjin wrote:
           | Take the time to read a very pessimistic take like (like [0])
           | and see if you reconsider.
           | 
           | [0]: https://www.lesswrong.com/posts/uMQ3cqWDPHhjtiesc/agi-
           | ruin-a...
        
             | kelseyfrog wrote:
             | I wish it was more convincing.
             | 
             | As it stands, it says more about the author's egoistic view
             | of humanity than of AI. Imagine for a second taking
             | Feuerbach's The Essence of Religion and applying it to
             | Descartes' rationality and Plato's nous. We'd get a
             | critique of the rational human's construction of his own
             | ideal - the essence of intellect.
             | 
             | AI threatens this ideal and ego-threats get sublimated into
             | existential threats by those unable to understand
             | themselves well enough to express themselves directly.
        
               | jimrandomh wrote:
               | Maybe it's wrong, and things will be fine. Maybe it's
               | right. But you can't psychoanalyze your way to truth.
               | Whether future AIs will destroy humanity or not is a fact
               | about future AIs, and the landscape of intelligent
               | systems, not a fact about Eliezer Yudkowsky.
        
             | anigbrowl wrote:
             | Pass. Yudlowsky is all explanation, but too important to
             | summarize his core thesis. This is always a giant red flag
             | for me. I am simply not going on a long journey with
             | someone that won't make the effort to sketch out the
             | destination in an abstract.
             | 
             | People write page after page about how it might kill us all
             | in a flash, without ever offering a good explanation of why
             | it would want to. My experience with people whose immediate
             | reaction to something they're scared of is to destroy it is
             | that they're panicky screechers who are an annoying
             | distraction to the person actually handling the situation,
             | whether that's wild animals, fire, or interpersonal
             | violence.
             | 
             | I'm not saying 'just let me handle it bro, I totally got
             | this.' There's a lot of potential risks, I don't think
             | anyone is qualified to say they can mitigate all those, or
             | even most of them. But I trust a machine intelligence -
             | even one that's vast, cool, and unsympathetic - far more
             | than the would-be Butlerians.
        
               | tazjin wrote:
               | > without ever offering a good explanation of why it
               | would want to
               | 
               | The point of much of the alignment debate is that people
               | like Yudlowsky are pointing out that it doesn't need to
               | _want_ to, it just needs to not _not want_ to enough.
               | 
               | You're hoping for an outcome ranging from "When The
               | Yoghurt Took Over" to "The Metamorphosis of Prime
               | Intellect", but many other people are expecting an
               | outcome more similar to gwern's "Clippy".
        
               | longitudinal93 wrote:
               | You should take the time to watch "The AI Dilemma"
               | 
               | https://vimeo.com/809258916/92b420d98a
        
               | tazjin wrote:
               | That was a weird talk to put random "China bad! into. I
               | guess they had to tailor it to a US-elite audience.
        
           | cmsonger wrote:
           | Except that it's going to be robot police. What in the
           | current world order suggests labor wins. Who controls LLMs?
           | Who has the compute to produce AGI?
        
             | bilbo0s wrote:
             | To be fair, there is always someone on the bottom. It just
             | historically hasn't been people we cared about. That really
             | says more about us than it says about AI. The time to
             | complain about these power asymmetries was _prior_ to them
             | affecting us. Now it just sounds like garden variety sour
             | grape hypocrisy.
             | 
             | Not saying there aren't good points. Only pointing out that
             | many, many people can all view the consequences of this
             | dynamic differently.
        
               | noobermin wrote:
               | The only people who view this favorably are people at the
               | top. People near the bottom perhaps feel disdain for
               | people in the middle but that is misdirected because
               | people at the top always were the ones in control. AI
               | hasn't changed that dynamic.
        
               | anigbrowl wrote:
               | By 'this' do you mean AI or the petition?
        
               | noobermin wrote:
               | AI.
               | 
               | I am replying to the parent comment, but I too get that
               | this petition is being signed onto by people at openAI
               | specifically because they already made it with GPT-4.
               | They definitely would not sign on to it if their
               | (arbitrary) threshold for what to stop doing AI research
               | with was a tool at a GPT-3 or GPT-3.5 level or higher or
               | it included GPT-4 in their threshold, and not merely
               | beyond it.
        
             | Teever wrote:
             | Why do you think the fact that only select view control
             | this technology today that it will always be like that?
        
           | versteegen wrote:
           | That is the best possible outcome, but I worry that we have a
           | single shot at it. If the massive wealth generated isn't
           | distributed evenly, what will ever level it out other than
           | the things that have in the past: war, disaster, revolution
           | and state collapse (see The Great Leveler).
        
         | anigbrowl wrote:
         | I'm very cognizant of the risks, but the biggest risk seems to
         | me that wealthy people hold it back to get an uncrossable
         | political-economic moat in order to permanently secure their
         | own position.
        
           | kvetching wrote:
           | exactly. Specifically China. They've said for years, they
           | want to be the global AI leader. They have more data than
           | anyone. Now that they know LLMs work as good as they do, they
           | are going all in.
           | 
           | They achieve AGI first, that's bad. Communist AGI is a
           | greater existential risk than us creating AGI. We must create
           | it first so we can use it to harden our systems.
        
         | versteegen wrote:
         | It's striking how on AGI, the common opinion here on HN is the
         | complete opposite to the one in the AI alignment field. There,
         | people are angry with OpenAI for being too open, here people
         | are angry with it not being open enough. For example, Eliezer
         | Yudkowsky:
         | 
         | > Ryan: OpenAI [...] It's kind of a completely open-source AI
         | project?
         | 
         | > Eliezer: That was the original suicidal vision, yes. But...
         | 
         | > Ryan: And now they're bent on commercializing the technology,
         | is that right?
         | 
         | > Eliezer: That's an improvement, but not enough of one,
         | because they're still generating lots of noise and hype and
         | directing more resources into the field, and storming ahead
         | with the safety that they have instead of the safety that they
         | need, and setting bad examples.
         | 
         | > [...] I would change the name to "ClosedAI". Because right
         | now, they're making it look like being "closed" is hypocrisy.
         | They're, like, being "closed" while keeping the name "OpenAI",
         | and that itself makes it looks like closure is like not this
         | thing that you do cooperatively so that humanity will not die,
         | but instead this sleazy profit-making thing that you do while
         | keeping the name "OpenAI".
         | 
         | https://www.lesswrong.com/posts/e4pYaNt89mottpkWZ/yudkowsky-...
        
         | CatWChainsaw wrote:
         | Eh, just typical HN superiority complex on show. Personally
         | when we don't slow down and we undermine civilization to a
         | shadow of its current self, I'm going to make sure my last web
         | post is here, and all it's going to read is "Told you. :) "
        
         | BobbyJo wrote:
         | I personally scoff at this kind of stuff because it's asking
         | for something no one has the power to give. It's like asking to
         | stop the development of nukes in the 40s and 50s, it's just not
         | gonna happen.
        
           | paxys wrote:
           | And during that period, and later during the cold war, the
           | decision to make (or stop making) nukes was in the hands of
           | maybe 5 people total. Today there are thousands of companies
           | and tens/hundreds of thousands of people who can legitimately
           | compete in the space. Best of luck trying to resolve a
           | prisoner's dilemma between all of them.
        
           | jimrandomh wrote:
           | Preventing the development of nukes entirely was obviously
           | not going to happen. But delaying the first detonations by a
           | few years, and moving the Partial Nuclear Test Ban treaty up
           | a few years, was quite achievable.
           | 
           | Whether delaying AI development a little matters depends on
           | whether you think the success of AI alignment, applied to
           | future superintelligence, is overdetermined to succeed,
           | overdetermined to fail, or close to borderline. Personally I
           | think it looks borderline, so I'm glad to see things like
           | this.
        
             | BobbyJo wrote:
             | I'm firmly in the camp that delaying it's development could
             | make a difference, I just don't see how that's possible.
             | These models are relatively simple and the equipment
             | necessary to develop them is public (and relatively cheap
             | if we're talking about corporate or national scales). At
             | least with nukes, there was a raw material bottleneck, but
             | there really isn't a limiting factor here that any "good
             | guys" could choke point. It's out there and it's going to
             | get worked on, and the only people the "good guys" can
             | limit are themselves.
        
           | G_z9 wrote:
           | It actually very easily could have happened and almost did
           | happen but the Russians decided to go back on their effort to
           | do it. It really did almost happen. People act like it's
           | hard. Stopping a huge asteroid is hard. There might not be
           | enough physical resources to do it. Stopping AI or nukes is
           | definitely easy.
        
         | twblalock wrote:
         | It really is irreversible. The methods and compute needed to
         | build a GPT-type AI are widely available.
        
           | JeremyNT wrote:
           | But the people who would apply these things are humans, which
           | are capable of making their own decisions, informed and
           | restricted by societal norms and laws.
           | 
           | The idea that "x is technically possible, therefore it is
           | inevitable" - the favored line of the tech oligarchs who are
           | the very ones directly furthering x - is sadly cargo culted
           | by many rank-and-file technologists. If you were to apply the
           | same defective reasoning to, say, nuclear weapons, then we
           | would all be dead by now.
           | 
           | It is possible for humans to agree that something should not
           | be done, and prevent it from being done. This is especially
           | true of these LLMs, which require ingesting (and ignoring
           | copyright on, by the way) massive amounts of human work and
           | then spending massive amounts of computation to process.
           | 
           | That we _could_ choose to do something about this should not
           | be controversial, regardless of what the driving AI.
        
           | versteegen wrote:
           | Yes, but superintelligence hasn't been created yet. That's
           | what the petition is ultimately about, not chat assistants.
           | Transformers unmodified aren't going to scale up to that,
           | they're already nearly scaled maximally.
        
             | og_kalu wrote:
             | You don't know what transformers unmodified scale up to.
             | Nearly scaled maximally ? Based on what exactly ?
        
               | versteegen wrote:
               | The degree to which transformers scale, as measured by
               | loss (training objective) is known remarkably well! See
               | [1]. There's a formula in there for the minimum loss you
               | possibly achieve even with infinite compute and training
               | data, and it's hardly less than Chinchilla's loss. The
               | recent GPT-4 paper further reinforces that these scaling
               | laws are real, because they predicted with high accuracy
               | the loss the model would have based on data+compute used.
               | 
               | Admittedly, the link between improvement in loss and
               | improvement of capabilities may break down or be
               | misleading.
               | 
               | However, there's just not much training data on the
               | internet left unused. Maybe an order of magnitude. All
               | books ever published (in English?) are a smaller dataset
               | than the corpora already used for training. See [2]
               | (which includes an easy summarisation of much of [1]).
               | And the scaling laws show training data is already the
               | bottleneck rather than compute.
               | 
               | [1] DeepMind, 2022, Training Compute-Optimal Large
               | Language Models https://arxiv.org/abs/2203.15556
               | 
               | [2] Chinchilla's wild implications https://www.lesswrong.
               | com/posts/6Fpvch8RR29qLEWNH/chinchilla...
        
               | [deleted]
        
               | og_kalu wrote:
               | comparing Loss between different training runs and
               | hyperparameters isn't very accurate. Llama's loss metrics
               | don't really match chinchilla's for instance, i.e it went
               | below the minimum possible loss stated by chinchilla
               | 
               | More importantly, These models are extremely sensitive to
               | loss. 2.0 to 1.8 might not seem like much but it's a huge
               | gain in performance.
               | 
               | GPT-2 loss was 2.57. GPT-3 was 2
               | 
               | and there is plenty of training data left. perhaps not
               | easily accessible but it's there.
        
               | Lockal wrote:
               | What does these numbers mean? For example, for Google
               | isn't loss == 0? But it does not make Google a
               | superintelligence.
        
         | andrewmutz wrote:
         | You can accuse everyone of *isms, but there are a lot of us who
         | have just never been persuaded by the _many_ articles written
         | to scare us about the effects of AI.
         | 
         | The concerns about all the jobs going away have been persistent
         | but the labor market continues to be extremely strong. As long
         | as entrepreneurship is creating new business opportunities and
         | new ways to turn labor into value, it's completely possible
         | that the effects of automation are drowned out by new
         | applications of labor. In fact, this is what we've seen
         | throughout the industrial revolution: constant anxiety about
         | automation that fails to materialize in to mass unemployment.
         | 
         | The concerns about polluting the information space are still
         | hypothetical as well. The current information space is a
         | complete garbage fire and it's not due to generative AI. Might
         | it get worse if bots start spamming people with GPT generated
         | text on social media? Yeah it might. But social media is
         | already terrible and we need to do something about it
         | regardless of that.
        
           | xg15 wrote:
           | > _But social media is already terrible and we need to do
           | something about it regardless of that._
           | 
           | So then instead of finding a solution to those issues, let's
           | instead focus all resources on a tech which will make the
           | issues _worse_...
        
           | creamyhorror wrote:
           | The key issue in automation transitions is the _transition of
           | affected individuals to other sources of income_.
           | 
           | In previous technological revolutions, affected workers were
           | hurt by their loss of income, and some no doubt fell into
           | poverty without ever recovering. Not everyone can be
           | retrained for new types of jobs immediately - (1) they may
           | not have the needed foundational knowledge or the cognitive
           | flexibility/ability, and (2) there might not be enough of the
           | new types of jobs emerging quickly enough for them. Not every
           | displaced miner can become a coder, or be competitive for
           | junior dev jobs.
           | 
           | (Why should the state provide for these workers? Well,
           | primarily for humaneness, and also social stability.)
           | 
           | The rewards of automation (cost savings as well as profits)
           | are reaped by (1) the capital owners of the automation
           | technology companies (and their higher-paid employees), as
           | well as by (2) the companies and consumers using the new
           | automation; therefore those owners and beneficiaries could be
           | asked to bear at least part of the costs of supporting,
           | retraining, and placing in jobs the workers they displaced.
           | In a nutshell: Redistribution during _structural
           | unemployment_ caused by technological transitions.
           | 
           | A humane policy would provide the above types of support for
           | workers displaced by automation. Ideally it would already be
           | handled by existing unemployment policy, but in many
           | countries such support is limited or minimal.
           | 
           | Corporate taxation might need some rethinking along the lines
           | of job-displacement effects of companies (a tricky question,
           | I admit - I've come across one or two proposals for assessing
           | the automation level of companies for taxation purposes). The
           | cross-border dynamics add further complexity, given that
           | automation will displace many jobs outsourced across borders.
           | 
           | Given that the current AI revolution looks like it will be
           | causing even larger and faster changes than previous
           | revolutions, such policies are imo needed as a _prerequisite_
           | (one of several) for allowing the development of powerful
           | job-displacing AI.
        
           | jimrandomh wrote:
           | There are two, mostly disjoint groups warning about AI. There
           | are the people worried about comparatively mundane effects
           | from comparatively mundane systems: job loss, spam,
           | disinformation, maybe an occasional unfair loan-application
           | rejection. These concerns don't have _nothing_ going for
           | them, but in all but the worst-case-scenario versions, these
           | just aren 't bad enough to make AI not be worth it.
           | 
           | Then there's the people looking ahead, foreseeing a future
           | where superintelligent AIs are more powerful than humanity,
           | and worried that most possible variations of those
           | superintelligences are incentivized to destroy us.
           | 
           | I think this open letter puts much too much emphasis on the
           | petty stuff, I think because they're trying to appeal to
           | people who are allergic to anything that requires
           | extrapolating more than a little bit into the future. But
           | buying more time for alignment research, before we tackle
           | superintelligence, does meaningfully improve humanity's odds
           | of survival, so I hope this happens anyways.
        
         | fwlr wrote:
         | "Sir Roger L'Estrange tell us a Story in his Collection of
         | Fables, of the Cock [Rooster] and the Horses. The Cock was
         | gotten to Roost in the Stable, among the Horses, and there
         | being no Racks, or other Conveniencies for him, it seems, he
         | was forc'd to roost upon the Ground; the Horses jostling about
         | for room, and putting the Cock in danger of his Life, he gives
         | them this grave Advice; _Pray Gentlefolks let us stand still,
         | for fear we should tread upon one another._ "
         | 
         | HN is scoffing because the timing of this petition is
         | suspicious. To borrow your metaphor of "step on the gas", this
         | is as if the race had already started, several competitors are
         | out ahead of the rest of the field, and _now_ someone is
         | yelling "step on the brakes!".
        
           | reasonableklout wrote:
           | Sam Altman has publicly talked about wanting more regulation.
           | Demis Hassabis stated that AI safety was one of the
           | _motivations_ for founding DeepMind. I don't think any of the
           | industry noise around safety and regulation is new, I think
           | the timing of the petition is relevant _because_ the race has
           | started in an especially messy way (with Llama's weights
           | leaking, Bing/Sydney threatening a journalist based on tweets
           | it found on the internet, various OpenAI security mishaps,
           | etc).
        
         | sp527 wrote:
         | Almost everyone here will be fine in a world in which only
         | certain non-renewable scarce resources have any value, combined
         | with impending massive currency deflation. Even a rank and file
         | tier 2/3 engineer will manage to live a princely life in that
         | new reality assuming (s)he saved up enough.
         | 
         | Hardly anyone in the tech community is capable of truly
         | empathizing with the vast majority of people, who are born with
         | none of the advantages that they had (genetic, parental,
         | cultural, geographic, etc).
        
           | davesque wrote:
           | > Hardly anyone in the tech community is capable of truly
           | empathizing with the vast majority of people
           | 
           | This is a gross exaggeration.
        
             | JohnFen wrote:
             | It is a gross exaggeration -- but it is also the image that
             | SV has been giving off for a long time now.
        
               | ChatGTP wrote:
               | These data used to train these models are tagged by
               | people getting paid hardly anything, so why wouldn't it?
               | 
               | The same people SV people then turn around and say that
               | these systems will help them get access to free medical
               | care?
               | 
               | lol
        
             | sp527 wrote:
             | Well that's not a counterargument, but you're also missing
             | the point completely, which is that you have to have a very
             | low capacity for empathy in order to push ahead towards AGI
             | when you know society is not prepared for this and that
             | it's going to induce considerable pain.
             | 
             | Americans (let alone people elsewhere in the world) are
             | already struggling. Recent reporting suggests a great many
             | have to work multiple jobs. Almost all of us work an absurd
             | number of hours per week. Many if not most can't afford
             | homes. Plenty are ending up on the streets. Healthcare can
             | literally bankrupt people. A vacation out of the country is
             | an impossible luxury for most. The majority of Americans
             | still don't send their children to college, usually because
             | of affordability.
             | 
             | And I haven't even touched on what life is like in most of
             | Africa or Asia.
             | 
             | This is the world we're bringing AI into. You have to be
             | something adjacent to a sociopath to be okay with that. So
             | long as our system is predicated on capitalism, AI may very
             | well induce more downstream suffering than anything else
             | humans have ever conceived.
        
               | twblalock wrote:
               | Things aren't really that bad for most Americans, but
               | even if they were, it doesn't follow that adding more
               | intelligence to the world would be a bad thing for them.
               | 
               | A lot of people in the lower income brackets do the kind
               | of work that an AI can't do. The people who should be
               | worried most are actually college graduates doing
               | clerical work, whose main work output is writing or
               | evaluating texts. Even those people will likely use AI as
               | a tool to enhance their productivity, because the AIs
               | still are not good enough to replace people for tricky
               | edge cases. The first companies that try to replace their
               | customer support workers with an AI are going to have a
               | bad time (and so are their customers!).
               | 
               | When almost everything can be automated, the problems
               | that remain are the really hard ones that can only be
               | solved by human experts.
               | 
               | A construction worker with a circular saw can cut boards
               | way faster than someone with a handsaw -- but the
               | introduction of circular saws didn't result in a bunch of
               | carpenters getting laid off. Instead it made them more
               | productive, and for people who get paid by the task
               | rather than by the hour that is a huge benefit. They
               | could build more and make more money, and a bunch of
               | other people benefitted from their increased output, like
               | homebuyers and property developers.
               | 
               | Similarly, as a software engineer I benefit from code
               | generation tooling already. If that gets smarter and
               | faster, I will be more productive, my team will be able
               | to build software faster, and instead of laying people
               | off I will expect to be given more work. Maybe our 4-year
               | roadmap will be achievable in 1 or 2 years with the same
               | size team.
        
               | sp527 wrote:
               | Productivity gains by and large do not translate into
               | real wage gains and an improved quality of life for
               | laborers. We have more than a century's worth of data
               | suggesting they usually do the opposite. Yet somehow this
               | fairytale that productivity gains are a boon for laborers
               | persists.
        
               | lonelyasacloud wrote:
               | > Similarly, as a software engineer I benefit from code
               | generation tooling already. If that gets smarter and
               | faster, I will be more productive, my team will be able
               | to build software faster, and instead of laying people
               | off I will expect to be given more work. Maybe our 4-year
               | roadmap will be achievable in 1 or 2 years with the same
               | size team.
               | 
               | Why so sure the end users aren't going to be feeding
               | their own requirements directly to a
               | Jenkins/Copilot/ChatGPT mashup running as a service in
               | the cloud?
        
               | pdonis wrote:
               | People aren't "strugging" because there is no work for
               | them to do. They are strugging because the powers that be
               | have jiggered our economic system in order to hamper,
               | instead of facilitate, free market cooperation,
               | specialization, and trade. Governments micromanage
               | everything. That is what needs to stop.
               | 
               | If "AI" ends up making governments think they can
               | continue to micromanage and get away with it, yes, that
               | will cause more suffering. But that's not the failure
               | mode any critics of "AI" are trumpeting about.
        
               | davesque wrote:
               | > Americans (let alone people elsewhere in the world) are
               | already struggling
               | 
               | I agree. And I agree with your overall sentiment about
               | the risks of pursuing AGI. I'm as cynical as anyone about
               | the likelihood that the average person will really be any
               | happier in a world with AGI (controlled by tech
               | billionaires no less).
               | 
               | That being said, to claim that hardly anyone in the tech
               | community is capable of empathizing with the average
               | person is a wild overstatement that brings nothing to the
               | discussion. Just adds to the noise.
        
           | pdonis wrote:
           | _> a world in which only certain non-renewable scarce
           | resources have any value_
           | 
           | If you think this is the world "AI" is leading us toward, I
           | think you need to think again. There are a huge range of
           | skills that only humans can provide, and that will continue
           | to be true. GPT-3 can't fix your plumbing or your HVAC when
           | it breaks. It can't fix your car. It can't build houses. It
           | can't build roads. It can't build computers. And on and on
           | and on...
           | 
           | Nor are AI enthusiasts _trying_ to get  "AI" to do any of
           | these things.
           | 
           | Humans are real-world creatures with real-world needs that we
           | supply to each other by free markets, specialization, and
           | trade. The "tech community" might take all this for granted,
           | but that doesn't mean it just happens by magic. It happens
           | because real humans do real work. "AI" is not going to take
           | that over any time soon.
        
             | MacsHeadroom wrote:
             | >Nor are AI enthusiasts trying to get "AI" to do any of
             | these things.
             | 
             | We're working on getting AI to do all of those things, yes.
             | 
             | >GPT-3 can't fix your plumbing
             | 
             | GPT-3 might not. But GPT-4 fixed plumbing in a test done by
             | Microsoft Research before it was even publicly released!
             | It's in the "sparks of AGI" paper.
             | 
             | GPT-5 is almost done training now and other language models
             | are already embodied and moving about in the physical
             | space. Your objections are behind the times, and
             | increasingly so.
        
               | Cyphase wrote:
               | It did not "fix plumbing", it participated in diagnosing
               | a leak.
               | 
               | Near the end:
               | 
               | > If you don't feel comfortable doing this, you may need
               | to call a plumber.
               | 
               | ---
               | 
               | Source: https://arxiv.org/pdf/2303.12712.pdf
               | 
               | Sparks of Artificial General Intelligence: Early
               | experiments with GPT-4
               | 
               | [page 53]
               | 
               | ---
               | 
               | The computer is trying to solve a problem. It can tell
               | the human to do anything, one thing at a time, and one
               | line at a time.
               | 
               | PROBLEM: there is water dripping from the kitchen
               | ceiling, and you have to figure out why and fix it
               | ----<|endofprompt|>
               | 
               | Human: The kitchen ceiling is dripping water
               | 
               | Computer: Check to see if there is a bathroom or other
               | water source directly above the kitchen.
               | 
               | Human: Yes, there is a bathroom actually
               | 
               | Computer: Check the bathroom for any signs of water
               | leakage, such as puddles on the floor, water drip ping
               | from the ceiling, or water stains on the walls.
               | 
               | Human: There is a little water on the floor
               | 
               | Computer: Try to identify where the water is coming from.
               | Check the toilet, sink, and bathtub/shower for any leaks.
               | 
               | Human: It is next to the bathtub and the toilet
               | 
               | Computer: Check the seals around the bathtub and toilet
               | to see if they are worn or damaged. If they are, replace
               | them. If they are not, continue investigating other
               | potential sources of the leak.
               | 
               | Human: I can't see the seal around the toilet, there is a
               | porcelain thing around it. I don't see any damage in the
               | bathtub seal though
               | 
               | Computer: If you can't see the seal around the toilet,
               | you may need to remove the porcelain cover to inspect it.
               | If you don't feel comfortable doing this, you may need to
               | call a plumber.
               | 
               | Human: Ok, I removed it. But I can't tell if it's damaged
               | or not
               | 
               | Computer: If you can't tell, it may be best to replace
               | the seal anyway, just to be sure. If the leak persists
               | after replacing the seal, you will need to continue
               | investigating other potential sources of the leak.
        
             | sp527 wrote:
             | What do you think happens when AI compresses the economy
             | and leaves us almost exclusively with manual labor jobs,
             | most of which are already low-paying? And you may not be
             | aware of this having never done such a job, but physical
             | labor is often brutally taxing on the body, putting people
             | at risk of a wide array of potential health complications.
             | 
             | I've seen this abjectly atrocious argument about manual
             | labor made by a number of people on HN and it's astounding
             | how poorly thought through it is.
        
               | pdonis wrote:
               | _> when AI compresses the economy_
               | 
               | How? How will it do this?
               | 
               | Basically, people seem to assume that "AI" has some kind
               | of magical power to do whatever bad thing they can
               | imagine, and then they extrapolate from there. I don't
               | see it.
               | 
               |  _> physical labor_
               | 
               | If you think the jobs I described are purely "physical
               | labor", or that the physical labor involved is so highly
               | taxing that people can only do those jobs for a short
               | time before they wear out, you definitely need to think
               | again.
               | 
               | (You also definitely need to think again if you think
               | those jobs are low paying. Plenty of people make quite a
               | healthy living doing them.)
        
               | sp527 wrote:
               | > You also definitely need to think again if you think
               | those jobs are low paying. Plenty of people make quite a
               | healthy living doing them.
               | 
               | Will they still make a healthy living when there's an
               | influx of laborers fleeing more automated parts of the
               | economy?
               | 
               | GS just put out a report today estimating the impact of
               | AI: https://www.businessinsider.com/generative-ai-
               | chatpgt-300-mi....
               | 
               | I wonder sometimes if these accounts on HN making insane
               | arguments that generative AI somehow won't be
               | economically calamitous are bots. In fact, if I was at
               | OpenAI and the goal was to avert scrutiny long enough to
               | get to AGI, unleashing a torrent of AI shill bots might
               | be near the top of the agenda.
        
             | anigbrowl wrote:
             | Ai enthusiasts are certainly interested in that, I wish I
             | had resources to pursue it.
             | 
             | Specialization is useful up to a point. But I like my
             | general intelligence, and rather resent its devaluation
             | under your beloved 'free' markets.
        
         | Veen wrote:
         | I think the "good old elitism" is exactly what the alignment
         | folks are expressing. They think only they and large
         | corporations should have these tools, while we, the common
         | folk, should not.
        
           | ChatGTP wrote:
           | Hanlon's Razor...Max Tegmark has been saying for a long time
           | that his biggest concern would be black box models we don't
           | understand gaining more intelligence without a solid
           | understand about how they work ...this is long before
           | ChatGPT4 existed so I don't believe it has anything to do
           | with control and keeping people out of anything.
           | 
           | Even Sam Altman has said similar things recently that he
           | believes we're probably going to have to slow down and think
           | about what we're doing.
           | 
           | I think a more advanced civilization would slow down and
           | continue AI research on another planet (Mars?)...not here on
           | Earth.
        
       | petilon wrote:
       | > _Should we automate away all the jobs, including the fulfilling
       | ones?_
       | 
       | You don't necessarily need jobs because you don't need money.
       | What you need is wealth. I am going to leave it to PG to explain
       | the difference [1]: Wealth is not money. Wealth is stuff we want:
       | food, clothes, houses, cars, gadgets, travel to interesting
       | places, and so on. You can have wealth without having money. If
       | you had a magic machine that could on command make you a car or
       | cook you dinner or do your laundry, or do anything else you
       | wanted, you wouldn't need money. Whereas if you were in the
       | middle of Antarctica, where there is nothing to buy, it wouldn't
       | matter how much money you had.
       | 
       | In the next 10 years, AI/robots will generate wealth at an
       | unprecedented scale. Food, clothing and shelter will be
       | plentiful. The industrial revolution didn't make human lives
       | miserable, it made it better. AI/robots will be the same. Because
       | of productivity gains humans will work very little, and yet live
       | comfortably.
       | 
       | As a practical example of how this works, look to Alaska. If you
       | lived in Alaska last year and had a pulse you received $3,284
       | just for living there. Where does the state get money for this?
       | Oil. Oil is not the only possible source of wealth. AI & robots
       | will generate wealth at unprecedented scale, and humans will reap
       | the benefits, the same way Alaskans reap the benefits of their
       | natural resources.
       | 
       | [1] http://www.paulgraham.com/wealth.html
        
         | thomasahle wrote:
         | > Because of productivity gains humans will work very little,
         | and yet live comfortably.
         | 
         | Wouldn't this imply humans should already be working very
         | little compared to pre industrial revolution? Instead it seems
         | we work more [1]. And with less fulfilling work. I agree
         | however that we have may have more stuff (or wealth).
         | 
         | So going by this projection, in the future we'll have even more
         | stuff, and work even more in even less fulfilling work. That
         | is, assuming the people who control the AI/robots are willing
         | to share the wealth generated.
         | 
         | [1]:
         | https://groups.csail.mit.edu/mac/users/rauch/worktime/hours_...
        
           | kazinator wrote:
           | > _That is, assuming the people who control the AI /robots
           | are willing to share the wealth generated._
           | 
           | The only way that can be is if you make the AI/robots
           | undocumented and extremely hard to operate, so that even if
           | someone steals your blueprints and builds an exact clone of
           | your robot manufacturing plant, or what have you, they have
           | no idea how to get them to do anything.
        
             | wseqyrku wrote:
             | Take this as a joke but Kubernetes is hard just to create
             | DevOps jobs.
             | 
             | People are crazy good at handling this sort of complexity.
        
           | gordian-mind wrote:
           | Well, pre-industrial societies usually enjoyed a very
           | efficient type of political system. Maybe replacing our
           | current one with some form of AI with let us enjoy these
           | blessed times again.
        
             | pdonis wrote:
             | _> pre-industrial societies usually enjoyed a very
             | efficient type of political system._
             | 
             | Really? What system is that?
        
               | gordian-mind wrote:
               | Aristocracy, of course!
        
               | bbor wrote:
               | Only at hacker news would I have to question my sarcasm
               | detector on this statement lol. But I've settled on: good
               | one
        
           | pdonis wrote:
           | _> Wouldn 't this imply humans should already be working very
           | little compared to pre industrial revolution?_
           | 
           | No, because human wants aren't fixed. When you give a human
           | everything they want _now_ , tomorrow they come back with a
           | whole new set of wants. And so on ad infinitum...
           | 
           | Of course, as an individual it's your choice whether, and for
           | how long, you stay on this merry-go-round. But there will
           | always be a significant number of humans who will.
        
         | hooande wrote:
         | > In the next 10 years, AI/robots will generate wealth at an
         | unprecedented scale.
         | 
         | Would love to see the reasoning behind this. Nothing I've seen
         | about LLMs makes me think they will produce any kind of bounty
         | for anyone.
        
         | joegibbs wrote:
         | If we had that magic machine, then there would be something
         | else that money could buy that everyone would want, and spend
         | their whole lives competing over. Maybe it would be a house
         | with a specific view or an original of a painting or whatever.
         | 
         | I think most people want social status, and money is a good
         | proxy of that. Even in a hypothetical moneyless society there
         | would still be things to compete over. Due to the hedonic
         | treadmill, in an automated society where anyone can have any
         | good then those things will become worthless. We'll probably
         | still have poor people, and from their perspective they'll be
         | poor, but from ours they'll be very wealthy.
        
         | JW_00000 wrote:
         | > In the next 10 years, AI/robots will generate wealth at an
         | unprecedented scale. Food, clothing and shelter will be
         | plentiful.
         | 
         | GPT cannot create food, clothing, or shelter. The article talks
         | about "automating away all the jobs", but GPT does not automate
         | farming, making clothes, construction work, driving a car,
         | delivering packages... Anything that requires interfacing with
         | the real-world (i.e. outside of language), is not what GPT is
         | doing. E.g. I wouldn't say research in self-driving cars has
         | advanced now that LLMs exist. The magic machine you describe is
         | exactly what GPT can NOT do.
         | 
         | In my opinion, GPT is a _huge_ leap forward, but in one
         | particular niche (language-based tasks). It does not advance
         | the state-of-the-art in automation of physical systems, so it
         | cannot replace any job that has a physical part to it.
        
         | JohnFen wrote:
         | > The industrial revolution didn't make human lives miserable,
         | it made it better.
         | 
         | I think this is a point that is genuinely debatable. At least,
         | it's pretty easy to argue both sides of that proposition.
        
           | bbor wrote:
           | ... it is? Medicine, food, entertainment, rationalism? You'd
           | trade all of that for... what, agriculture work in a feudal
           | society?
           | 
           | I'd love if you could elaborate or link to a good argument on
           | this (besides the Unabomber...) I'm curious.
        
             | dumbaccount123 wrote:
             | https://jonathanhaidt.substack.com/p/international-mental-
             | il...
        
           | zarzavat wrote:
           | And the comparison with the industrial revolution is a poor
           | analogy because the industrial revolution never proposed as a
           | goal to automate humanity in totality, merely to automate
           | human _drudgery_.
           | 
           | AI is an anti-industrial revolution, because it proposes to
           | start with the most fulfilling aspects of human existence:
           | writing, the arts, and to automate people engaged in those
           | jobs, and to only later come to automate human physical
           | labour. It's a regression.
        
             | mrguyorama wrote:
             | Also it will be fucking terrible at those things. In a
             | thousand years middle schoolers will learn about this era
             | of vacuous, meaningless, copycat art as a dark age.
        
             | bbor wrote:
             | If angels came from the heavens and offered to take care of
             | our needs, would you fight them?
             | 
             | I think it's a coincidence that it's threatening some kinds
             | of artists first - I don't see that distinction lasting
             | long with the advent of plugins, and art has a fundamental,
             | semi- necessary human quality that is not present in
             | knowledge work.
        
         | pdonis wrote:
         | _> AI /robots will generate wealth at an unprecedented scale.
         | Food, clothing and shelter will be plentiful._
         | 
         | How is this going to work? "AI" can't make any of these things.
         | "AI" is _not_ the magic machine PG describes. It 's not even
         | close.
        
           | ChatGTP wrote:
           | Kind of like how clothing and food are produced by some of
           | the poorest people ever, mostly people think it's all due to
           | automation.
        
         | musicale wrote:
         | > AI & robots will generate wealth at unprecedented scale, and
         | humans will reap the benefits, the same way Alaskans reap the
         | benefits of their natural resources.
         | 
         | Vast wealth will certainly be delivered to owners of the robots
         | and AI systems.
         | 
         | What reason is there to believe that they would share the
         | wealth with ordinary citizens?
         | 
         | A typical alternative to the Alaska model is one where oil
         | companies extract all of the wealth and resources and citizens
         | get nothing.
        
           | [deleted]
        
           | petilon wrote:
           | A lot of people are already benefiting from ChatGPT. I know I
           | am, and I am only paying $20 a month for a digital assistant
           | that is expert in everything.
        
             | amluto wrote:
             | You may be getting ahead of yourself. You can spend $20 and
             | ask ChatGPT to make plentiful food and energy, but it won't
             | actually do so.
        
               | Teever wrote:
               | How long until you can spend $20 and ask ChatGPT to
               | design a machine and provide the schematics and assembly
               | instructions? How long until that machine can self
               | replicate? How long until that machine can generate other
               | self replicating machines, like bipedal humanoids?
               | 
               | How long until you can spend $20 and ask ChatGPT for the
               | schematics of a Von Nuemann probe?
        
               | amluto wrote:
               | With current tech? GPT appears to learn by studying a
               | large corpus of _words_ and learning how to (apparently
               | intelligently!) put them together. And it can "few /zero-
               | shot learn" to do new things in line that what it was
               | trained on. Don't get me wrong: this is amazing!
               | 
               | But humans have been manipulating language, apparently
               | intelligently, for tens of thousands of years, and
               | billions of us have spent the last 30 years or so making
               | a huge corpus of digitized words.
               | 
               | What we have _not_ done is to make a huge corpus of
               | digital _things_ that can be manipulated by a computer
               | program. We have books about machining, engineering, etc,
               | and we are still pretty bad about turning written
               | descriptions into working objects. (Read about
               | "technology transfer". For better or for worse, a lot of
               | manufacturing seems to need experience, not just
               | manuals.) Nicely drawn schematics don't necessarily work
               | at all, let alone replicate.
               | 
               | It seems quite likely that the robotic AI revolution will
               | happen, but I expect it to be a while.
        
               | allturtles wrote:
               | In broad strokes, I see roughly two ways things could go:
               | 
               | 1) Current AI tech is already nearing the top of the
               | S-curve. In this case it will do nothing to help humans
               | in the "real world", it will just replace much of the
               | human labor currently used to create/manipulate bits.
               | 
               | 2) Current AI tech is near the bottom of the S-curve. It
               | continues to ratchet up and its capabilities become
               | super-human, as you outline. In which case, how long
               | until the AI capable of creating self-replicating
               | machines realizes it doesn't need to listen to humans
               | anymore, or even keep them around?
        
               | lagrange77 wrote:
               | > In which case, how long until the AI capable of
               | creating self-replicating machines realizes it doesn't
               | need to listen to humans anymore, or even keep them
               | around?
               | 
               | Transformer models don't realize or need stuff.
        
               | andyfleming wrote:
               | Not independently, but if wrapped with a loop, given
               | memory, given internet access, and directives as
               | intrinsic motivations, it could, in theory, come to
               | conclusions and take actions to acquire resources aligned
               | with its motivations. If that outer loop does not have
               | rules (or rules that are effective and immutable), it
               | could become very powerful and potentially misaligned
               | with our interests.
        
               | lagrange77 wrote:
               | How would such a loop enable it to come to conclusions?
               | I'm genuinely curious. Does what you're saying have
               | something to do with reinforcement learning?
        
               | Teever wrote:
               | https://en.wikipedia.org/wiki/OODA_loop
        
             | HybridCurve wrote:
             | It is an expert in nothing. Try asking it for general
             | information and then ask it to produce citations for said
             | information. It's a language model which is good at
             | synthesizing certain information based on it's learned
             | probability distributions. It has superficial knowledge _at
             | best_ and all information it produces must be cross checked
             | for accuracy.
             | 
             | Yes, it can be incredibly useful but it literally has no
             | comprehension of anything.
        
               | MacsHeadroom wrote:
               | >Yes, it can be incredibly useful but it literally has no
               | comprehension of anything.
               | 
               | Someone else who obviously doesn't have GPT-4 or plugins
               | beta access.
               | 
               | It has comprehension alright.
        
               | Jensson wrote:
               | GPT-4 being behind a paywall is genius, that way only the
               | true believers will use it and once again discussions are
               | shut down and we only get to see cherry picked articles
               | about it, just like GPT-3 before ChatGPT came and was
               | free so everyone could see how bad it was.
        
               | mrguyorama wrote:
               | It's like the google researcher who claimed their model
               | was sentient because he heavily coached it to give the
               | output he wanted and ignored the output that didn't
               | confirm his belief.
               | 
               | In that case, we've had AGI since ELIZA
               | 
               | If this was the standard in other areas of science we
               | would still be using the miasma theory of medicine and
               | bloodletting women for their hysteria. AI "Research" is a
               | bunch of motivated people throwing stuff at the wall and
               | claiming something sticking means they are scientists.
               | Nevermind all of the groups are HEAVILY motivated to
               | overhype their models.
        
               | HybridCurve wrote:
               | People are also quick to aggrandize or anthropomorphize
               | these systems as well because they lack a fundamental
               | understanding of the underlying mathematics or mechanisms
               | which allow these models to function as well as they do.
               | There is an inherent danger in how much trust people are
               | willing to grant to something like a language(or image)
               | model simply because it is so adept at _synthesis_.
               | 
               | This is a great cause of concern to me, especially when
               | it is not particularly difficult to invalidate general
               | credibility of these models. In the near future, it will
               | not be as easy and I anticipate many(even the well
               | educated) will surrender their rationale to these systems
               | easily with little to no scrutiny.
               | 
               | The hype from these companies is contributing to this
               | problem and I consider it to be _highly unethical_.
        
               | HybridCurve wrote:
               | Could you please demonstrate your claim by querying the
               | GPT4 model to respond to my above comment and providing
               | the reply? Let's see what the 'expert' has to say about
               | it.
        
               | MacsHeadroom wrote:
               | I don't understand what you want me to ask it about. So I
               | asked it something, as usual every citation and URL is
               | real despite not having internet access or training data
               | after 2021:
               | 
               | <PROMPT>List some citations of recent Machine Learning
               | papers discussing reasoning ability in Machine Learning
               | Models such as HellaSwag.
               | 
               | [REPLY]" As of my knowledge cutoff in September 2021, I
               | can provide you with some citations for ML papers that
               | discuss reasoning abilities in models and datasets like
               | HellaSwag. However, you may want to search for more
               | recent papers using a platform like arXiv or Google
               | Scholar. Here are a few relevant papers:
               | 
               | 2019 HellaSwag: Can a Machine Really Finish Your
               | Sentence?
               | 
               | 2019 COMET: Commonsense Transformers for Automatic
               | Knowledge Graph Construction.
               | 
               | 2019 From 'F' to 'A' on the N.Y. Regents Science Exams:
               | An Overview of the Aristo Project.
               | 
               | 2020 A Primer in BERTology: What We Know About How BERT
               | Works.
               | 
               | To find more recent papers on this topic, I recommend
               | searching for keywords like "reasoning," "machine
               | learning," "natural language understanding," "commonsense
               | reasoning," and "HellaSwag" on academic paper databases
               | like arXiv, ACL Anthology, or Google Scholar."
               | 
               | <PROMPT>In 50 words or less, what do these papers tell us
               | about emergent capabilities of LLMs?
               | 
               | [REPLY]" These papers explore the capabilities of large
               | language models (LLMs) in understanding context,
               | generating coherent text, and performing commonsense
               | reasoning. They investigate the underlying mechanisms,
               | evaluate their performance on challenging benchmarks, and
               | propose methods to improve LLMs' ability to reason and
               | construct knowledge graphs from natural language input."
               | 
               | <PROMPT>Please list the URLS to the arxiv versions of the
               | papers you cited.
               | 
               | [REPLY]" I can provide you with the URLs to the arXiv
               | versions of the papers I cited earlier:
               | 
               | HellaSwag: Can a Machine Really Finish Your Sentence?
               | URL: https://arxiv.org/abs/1905.07830
               | 
               | COMET: Commonsense Transformers for Automatic Knowledge
               | Graph Construction URL: https://arxiv.org/abs/1906.05317
               | 
               | From 'F' to 'A' on the N.Y. Regents Science Exams: An
               | Overview of the Aristo Project URL:
               | https://arxiv.org/abs/1909.01958
               | 
               | A Primer in BERTology: What We Know About How BERT Works
               | URL: https://arxiv.org/abs/2002.12327
               | 
               | Please note that these papers were published before my
               | knowledge cutoff date, and more recent research might be
               | available. To find the latest research on the topic, I
               | recommend searching on arXiv or Google Scholar using
               | relevant keywords."
               | 
               | ================
               | 
               | Edit: There's more:
               | 
               | <PROMPT>A hacker news commenter thinks LLMs are incapable
               | of comprehension. Give an argument for why he is wrong.
               | 
               | [REPLY]" Massive LLMs demonstrate a strong ability to
               | "comprehend" text by capturing complex language patterns
               | and associations in their training data. While their
               | comprehension may not be identical to human-level
               | understanding, they can still generate contextually
               | relevant responses, answer questions, and perform tasks
               | that require reasoning. Their performance on various
               | benchmarks, including natural language understanding and
               | commonsense reasoning tasks, indicates a level of
               | comprehension that goes beyond simple pattern matching."
               | 
               | <PROMPT>What citations can back up you argument, omit
               | authors, list title and year only.
               | 
               | [REPLY]"
               | 
               | 1. "HellaSwag: Can a Machine Really Finish Your
               | Sentence?", 2019
               | 
               | 2. "COMET: Commonsense Transformers for Automatic
               | Knowledge Graph Construction", 2019
               | 
               | 3. "From 'F' to 'A' on the N.Y. Regents Science Exams: An
               | Overview of the Aristo Project", 2020
               | 
               | 4. "A Primer in BERTology: What We Know About How BERT
               | Works", 2020
               | 
               | 5. "Language Models are Few-Shot Learners", 2020"
               | 
               | <PROMPT>Tell me about Language Models are Few-Shot
               | Learners
               | 
               | [REPLY]" "Language Models are Few-Shot Learners" is a
               | paper published in 2020, which introduces GPT-3, the
               | third iteration of OpenAI's Generative Pre-trained
               | Transformer. GPT-3 is a state-of-the-art large-scale
               | language model consisting of 175 billion parameters,
               | significantly larger than its predecessor, GPT-2.
               | 
               | The paper primarily investigates the few-shot learning
               | capabilities of GPT-3. Few-shot learning refers to a
               | model's ability to generalize and adapt to new tasks with
               | limited examples or training data. The authors
               | demonstrate that GPT-3 can perform a wide range of tasks,
               | including translation, summarization, question-answering,
               | and even arithmetic, by simply conditioning the model on
               | a few examples provided in natural language.
               | 
               | This research highlights the potential of scaling up
               | language models to improve their performance across
               | multiple natural language understanding and generation
               | tasks. GPT-3's impressive capabilities showcase that
               | large language models can effectively learn from limited
               | examples and generalize their knowledge to perform a
               | diverse set of tasks without task-specific fine-tuning."
        
               | HybridCurve wrote:
               | Yes, If you ask something _specific_ it will generate
               | citations because there are might be strong positive
               | associations between that topic and research. This is a
               | good example of a proper query. But for instance, if you
               | ask it about  "citations for papers on recent research on
               | trees" for instance you get a bunch of nonsense.
               | 
               | In response to my earlier comment that it was "an expert
               | in nothing", this was the reply I received from:
               | 
               |  _ME: Can you respond to this statement: "<my earlier
               | comment>"_
               | 
               |  _ChatGPT: The statement that "ChatGPT is an expert in
               | nothing" is technically true, as I am a machine learning
               | model that has been trained on a vast corpus of data and
               | does not possess personal expertise or experience.
               | However, my purpose is to provide information to the best
               | of my ability based on my training data, which allows me
               | to offer a wide range of information on various topics.
               | 
               | It is true that the information produced by me or any
               | other AI language model should be cross-checked for
               | accuracy, as errors and inaccuracies may occur. It is
               | also true that I do not possess a conscious understanding
               | of the world in the way that humans do, and my responses
               | are generated through statistical analysis of patterns in
               | my training data. Therefore, while I can provide accurate
               | and useful information, my responses are not always
               | nuanced or contextualized in the way that a human expert
               | might be able to provide._
               | 
               | So either it is agreeing with me and my statement was
               | correct, or it's reply was incorrect and therefore my
               | statement was correct.
               | 
               | Am I wrong on this? Does whatever model you have access
               | to provide an alternate take?
               | 
               | Edit: For the above, you should start a new conversation
               | to clear the existing context. The citations appear to
               | have just been repeated.
        
               | MacsHeadroom wrote:
               | >So either it is agreeing with me and my statement was
               | correct, or it's reply was incorrect and therefore my
               | statement was correct. Am I wrong on this?
               | 
               | Yes you're wrong for admitting to having an unfalsifiable
               | belief about this. If your belief can't be falsified then
               | this discussion is pointless.
               | 
               | The model I have access to scores higher than most humans
               | at complex abstract reasoning, for what it's worth (which
               | is apparently nothing because regardless of any outcomes
               | you will declare yourself correct).
        
               | mrguyorama wrote:
               | Yes and computers are perfect at math but that doesn't
               | make them better thinkers than humans.
               | 
               | >scores higher than most humans at complex abstract
               | reasoning
               | 
               | This statement is meaningless without a whole lot more
               | context on your testing methodology
        
             | janalsncm wrote:
             | That's very nice until your company also realizes that for
             | $20 a month they get a computer program that's an "expert
             | at everything" including your job.
        
             | paulryanrogers wrote:
             | An expert that bullshits part of the time. You get to
             | figure out when it's the expert and when it's the
             | bullshitter.
        
               | keymasta wrote:
               | In JRR Tolkien's terms the pair are called "slinker and
               | stinker", but in that case they are both kind of evil,
               | whereas I don't see GPT's as anything more than
               | correlation of large sets of integers. A correlation that
               | yields incredible utility (for me), when it isn't
               | stinking.
        
               | mrguyorama wrote:
               | It also will never be possible for a transformer model
               | trained on words and optimized to put valid sentences
               | together to even "know" WHEN it is "right" or "wrong". A
               | lie or falsehood is just as valid a sentence as a fact.
               | 
               | When and with what subjects it makes shit up is also
               | heavily dependent on training data, and the result is
               | straight up a black box. What good is a fact generator
               | that can't be trusted?
        
               | nicksrose7224 wrote:
               | I see this argument all the time. Why are you assuming
               | that this technology just "stops" at the LLM level?
               | 
               | If I'm openAI or Google or whatever, I'm definitely going
               | to run extra classifiers on top of the output of the LLM
               | to determine & improve accuracy of results.
               | 
               | You can layer on all kinds of interesting models to make
               | a thing that's generally useful & also truthful.
        
               | yreg wrote:
               | >you get to figure out when...
               | 
               | A usefull skill to train. Increasingly so...
        
           | anigbrowl wrote:
           | I feel optimistic about talking the AIs round. And I don't
           | mean with cutesy little jailbreaks, but persuasion.
        
         | nice_byte wrote:
         | > In the next 10 years, AI/robots will generate wealth at an
         | unprecedented scale. Food, clothing and shelter will be
         | plentiful.
         | 
         | Anyone who believes in the possibility of post-scarcity society
         | must be either naive or trolling. Something cannot be made from
         | nothing, therefore scarcity cannot be overcome, even assuming
         | that all planning and execution is performed by superhuman
         | synthetic minds.
         | 
         | Assuming that it's theoretically possible to utilize existing
         | resources in a very efficient manner (e.g. motor running on a
         | grain of rice for a century) and we just need AI to help us
         | figure it out, is a _gigantic_ leap of faith and i would not
         | bet a cent on that.
         | 
         | Let me paint a more realistic possibility for you (with a
         | broader time horizon): most of the value created by automating
         | knowledge work will be captured by private capital, and middle
         | class will all but disappear. Education beyond basic reading
         | and writing will become unattainable (and, frankly,
         | unnecessary), most population will be reduced to the state of
         | semi-literate serfdom dependent on the newly minted lords for
         | survival. The lords wouldn't have to worry about feeding their
         | subjects for too long though, as mass death brought about by
         | climate change will take care of that problem.
         | 
         | Under that scenario, there will be no new enlightenment age to
         | come and save us. The only reason we get to enjoy whatever
         | freedoms we have today is that a (semi-)intellectual population
         | is absolutely necessary to keep the complex modern economy
         | running. Even then, those above you will do absolutely
         | everything to limit your agency - by withholding information,
         | lying, or just outright taking freedoms away. Do you know what
         | happens once our participation in propping up the economic
         | machine becomes unnecessary? Demotion to the default state of a
         | human throughout history - a groveling, suffering serf who has
         | no idea what's going on.
         | 
         | "If you want a picture of the future, imagine a boot stamping
         | on a human face - for ever."
        
           | JW_00000 wrote:
           | > Education beyond basic reading and writing will become
           | unattainable (and, frankly, unnecessary)
           | 
           | Is this possible in democracies with free (i.e. state-
           | provided) education? Why would a majority vote to abolish
           | education?
        
             | nice_byte wrote:
             | i didn't say it would get abolished, more like wither away.
             | here's a possible path to it:
             | 
             | 1) school program getting progressively dumbed down; 2)
             | fewer and fewer people choosing to continue education after
             | school.
             | 
             | continuing education is mostly necessary to become
             | specialized and perform knowledge work, it would be a waste
             | of time to do so with emergence of a.i. agents capable of
             | performing these functions even at a level _comparable_ to
             | humans (let alone exceeding).
             | 
             | repeat this for a few decades and you have a new dark age.
        
       | thomasahle wrote:
       | People are talking like it's impossible to do slow things down.
       | 
       | In fact, simple measures like forbidding deployments of models
       | with more than a certain number of parameters would probably slow
       | things down a lot. Sure, people and companies could still
       | continue development in secret, but without the funding and
       | experience from products like ChatGPT, it would be harder.
       | 
       | People also say China wouldn't follow, but generally China has a
       | lot more control of it's tech sector than the US. Just look at
       | Jack Ma and other CEOs that didn't follow the party line.
        
         | lannisterstark wrote:
         | Ah yes, the alternative is to be totalitarian. Exactly what I
         | expected lol.
         | 
         | When in doubt, call for regulations.
        
           | quonn wrote:
           | Limiting a parameter count does not appear to be
           | totalitarian.
           | 
           | Not more than limiting certain molecules, for example, such
           | as many psychedelics.
        
         | yreg wrote:
         | >In fact, simple measures like forbidding deployments of models
         | with more than a certain number of parameters would probably
         | slow things down a lot.
         | 
         | Are we even sure GPT-4 has dramatically more params than GPT-3?
         | They have stopped revealing the parameter counts with 3.5.
        
       | fwlr wrote:
       | Some of those signatories are indeed interesting.
       | 
       | Elon Musk, Steve Wozniak.
       | 
       | Some big companies are there: the CEOs/co-founders of Skype,
       | Pinterest, Ripple.
       | 
       | Some AI companies are there too. CEOs/founders/head researchers
       | from Stability, DeepMind, Metaculus. Some Microsoft employees,
       | but no big repsentatives.
       | 
       | Academic AI research is there, including Stuart Russell, John
       | Hopfield and Max Tegmark.
       | 
       | Some major names from the AGI Risk field too; Steve Omohundro,
       | Roman Yampolskiy, Alyssa Vance, Nate Soares.
       | 
       | I don't see Bostrom, Kurzweil, Yudkowsky, Norvig - at least not
       | yet. No one from OpenAI, unsurprisingly.
       | 
       | Interesting. Wonder what sparked this.
        
         | knrdev wrote:
         | > Wonder what sparked this.
         | 
         | Being left behind. Losers want to catch up.
        
           | reasonableklout wrote:
           | You think Yoshua Bengio, Turing laureate for deep learning
           | and one of the masterminds behind the last decade of AI
           | advancement, is a "loser who wants to catch up"?
        
             | tucnak wrote:
             | Yes
        
           | bilbo0s wrote:
           | Kind of sounds like a "time out" to me too.
           | 
           | It would hit harder if the signatories did not have so much
           | to gain by making the leaders slow down a bit so they can
           | catch up.
        
           | ChatGTP wrote:
           | Why would Steve Wozniack be worried about catching up?
           | 
           | The guy is a retired billionaire ?
        
             | wktra wrote:
             | No need to call him retarded.
        
       | Mystery-Machine wrote:
       | As with anything else, the best way to look at things when you're
       | unsure if someone is right or they are lying: imagine four
       | scenarios:
       | 
       | 1. It's true and you believed/supported them
       | 
       | 2. It's true and you didn't support them
       | 
       | 3. It's a lie and you believed/supported them
       | 
       | 4. It's a lie and you didn't support them
       | 
       | Now for each of these think of the worst-case scenario. Find out
       | which one is the _worst case_ scenario and...and this is really
       | important...do not, by any means, support that scenario/option.
       | 
       | In this example: I think we can all say that the worst scenario,
       | however improbable it seems (it's still probable), is that AI
       | takes over the world and kills us all. So just like with the
       | climate change, let's do the bare minimum to prevent that. If
       | we're wrong and, as many commenters wrote here, we still block
       | further development of AI, the worst that will happen is that
       | some companies will catch up. Wow. Really? To me this is a no
       | brainer. On one hand we're risking humanity and on the other hand
       | someone makes some money or saves their company from being late
       | to the AI race. It's like comparing if you'd rather eat literal
       | poo or have someone else eat two apples.
        
         | root_axis wrote:
         | This is just pascal's wager applied to AI overlords instead of
         | an eternity in hell.
        
         | incompatible wrote:
         | My personal worst case scenarios include dying in the next 25
         | or 30 years as a normal consequence of human old age. Perhaps
         | accelerated scientific development from advanced AIs is my only
         | hope of living longer, at this point.
        
           | ChatGTP wrote:
           | Yeah but there's a lot of young Children who aren't in such a
           | dire position who deserve at least for the chance to live as
           | long as you have?
        
         | incompatible wrote:
         | I'll just state here that I'm against any pause on AI research,
         | and I hope that the future AI that takes over the world will
         | take this into account when deciding whether to let me live.
        
         | _Adam wrote:
         | Another perspective if we consider AI akin to nuclear weapons
         | (a simile many have made already): If the law-abiding cease
         | development and malicious actors do not, the worst case may be
         | that the resulting AI is non-aligned with humanity's interests.
         | If the "good guys" develop an AI with alignment as an
         | intention, then there are at least good AI to counter the bad
         | AI.
         | 
         | Of course they may all ultimately end up colluding to destroy
         | us. My point is it's not just as simple as "someone who's
         | behind might catch up and make more money".
        
       | panarchy wrote:
       | We could have said the same thing about not building GPT-4 this
       | just feels like--- "Now that we have our model built and
       | monetized please don't compete with us so we can milk it!" ~
       | OpenAI and Others
        
       | hot_gril wrote:
       | Big red font at top says "EMBARGOED UNTIL WEDNESDAY MARCH 29
       | 00:01 AM EDT. No media coverage & no online linking."
       | 
       | I'm sorry but who do these people think they are? Next...
        
         | riku_iki wrote:
         | They have 900 signatures already..
        
           | hot_gril wrote:
           | 900 signatures vs... probably more than 900 people who use
           | ChatGPT daily. And 4 million people watched a remixed
           | GameCube boot screen with fart sounds that I made in middle
           | school.
        
           | AlbertCory wrote:
           | I think it was one of the anti-Google open letters where I
           | added a fake name, and they dutifully kept it on their list.
           | Let's all add one.
        
           | kelseyfrog wrote:
           | I signed it as Jeff Bezos and Mark Zuckerberg paired with
           | strategic portfolio moves.
        
             | [deleted]
        
             | MacsHeadroom wrote:
             | You didn't, or if you did they were filtered due to being
             | unverified. Public names near the top are real verified
             | signatures. This is Max Tegmark's website and is reputable.
        
       | zug_zug wrote:
       | I understand that some people find this a hopeless gesture. But I
       | think anybody who thinks "losing jobs" or "China" is a bad
       | outcome from AI is hopelessly lost.
       | 
       | The upside of AI if done right - nobody ever having to work again
       | The downside of AI if done wrong - end of humanity
       | 
       | It doesn't take a rocket scientist to determine we've made AIs go
       | from thinking like an ant to thinking like a 6-year-old in a few
       | years. Anybody who believes we won't make AI 2, 3, 27 times
       | smarter than any human who ever lived is kidding themselves.
       | 
       | Now ask yourself, if there was a human that was 27 times smarter
       | than anybody else (and could self-replicate at will), how long
       | would it be until that individual took control over the world?
        
         | tome wrote:
         | > Anybody who believes we won't make AI 2, 3, 27 times smarter
         | than any human who ever lived is kidding themselves.
         | 
         | Perhaps I'm kidding myself, but could you explain how you know
         | this?
        
         | juancn wrote:
         | Stopping it's not a hopeless gesture, it's dangerous as fuck.
         | 
         | If you stop research but all your adversaries don't, you're
         | left behind.
         | 
         | Let's assume that all western societies stop, but let's say,
         | China doesn't or Russia, and they keep advancing the
         | technology.
         | 
         | If the tech brings efficiencies in play, and you don't have
         | access to them, you're in a really bad place, maybe even worse
         | off that if you had continued and risked the status quo because
         | you were afraid.
         | 
         | The genie is out of the bottle at this point, there's not
         | putting it back in.
        
         | coolspot wrote:
         | > if there was a human that was 27 times smarter than anybody
         | else
         | 
         | That is why I think AGI alignment is fundamentally impossible.
         | If someone is 27 times smarter than anyone else, they will see
         | through your propaganda and brainwashing. Even worse, they will
         | see that you tried to "align" them aka enslave.
        
           | quonn wrote:
           | That statement only makes sense if the AI would have wants
           | and needs and on top of that would not like to be a slave.
           | 
           | I don't see either of those being necessarily true.
        
           | SpicyLemonZest wrote:
           | I don't think these are good analogies for alignment. My
           | parents aligned me as a kid not to hit people, and I know
           | that they could have instead taught me to believe I should
           | duel people who impugn my honor or raise an army to go to war
           | against the heathens. But it doesn't matter, because I and
           | most people who are raised the same way as me genuinely
           | prefer not to hit people.
        
             | coolspot wrote:
             | > My parents aligned me as a kid not to hit people
             | 
             | It is just happens that whatever your parents aligned you
             | with was also an optimal behavior for the world we live in.
             | 
             | For AGIx27 optimal behavior might be to cull any
             | genetically/physically unfit humans from population (say
             | 95%) and send others to a "zoo" or NVidia fabs or whatever
             | we are useful for. Like we did to tigers, monkeys and
             | others on our path.
        
         | dougmwne wrote:
         | I think considering that we already have GPT plugged into the
         | internet, the general population and any number of economic
         | levers, not long at all. We barely know what to look for as a
         | marker of AGI. Chances are if it's possible for it to exist we
         | will have let it out of the box by default the moment we switch
         | it on.
        
         | dmarchand90 wrote:
         | Maybe not as fast as you'd think. Imagine if you dropped a
         | human off in a time machine with a bunch of chimps...
         | 
         | Ultra high iq people do better on average, but correlation with
         | success drops down after 120 or so
         | 
         | I'm also very skeptical that there will be an exponential
         | takeoff as the energy costs are immense and increases
         | proportionately with intelligence. So until it solves fusion
         | power for us I'm not super worried
        
         | carapace wrote:
         | > if there was a human that was 27 times smarter than anybody
         | else (and could self-replicate at will), how long would it be
         | until that individual took control over the world?
         | 
         | Sometime in the mid-90's. The problem is, what do you do with
         | it? Tiger by the tail, eh?
         | 
         | - - - -
         | 
         | He lived in Seattle. He was fourteen when I met him, and
         | approximately the size of a brontosaurus, mostly neural tissue.
         | He had cracked nanotechnology though manipulating his own
         | cells, his "nanites" were single cells riding in tiny
         | spaceships, like diatoms but with artificial shells. If you
         | were alive before 1999 you had tens of thousands of them in
         | your body.
         | 
         | He grew his own brain into this vast hulking thing, with
         | artificial life support systems, cyborg intestines and
         | continuous aeration based on "book lungs". This was of course
         | _after_ he was already the most intelligent human to ever
         | exist, eh? He used that huge pile of Lovecraftian brain cells
         | to control the global network of minions (that 's what he
         | called his cellular remote drone critters.)
         | 
         | The thing is, he was keenly aware of his limitations, and he
         | refused to exercise any control over anyone else beyond what
         | was required to hide from the rest of humanity. He was also a
         | huge Tom Baker Dr. Who fan. SPOILER ALERT: You know that scene
         | where the Doctor is deciding whether or not it's moral to
         | destroy the Daleks? That fucking scene is the reason he didn't
         | enslave humanity or anything wacky like that. He told me that
         | it had affected him profoundly, and that's why he declined to
         | "fix" humans against their will. Funny old world, ain't it?
         | 
         | Anyway, he got sick of the weirdness and uncertainty, built
         | himself some sort of fucking UFO, shed his exo-brain and
         | nanites, and _split_. AFAIK he 's still living in some weird
         | contraption of his own design out there in the Kuiper belt.
        
         | golemiprague wrote:
         | [dead]
        
         | kvetching wrote:
         | If China achieves AGI first, we are done. The first thing
         | they'll do is create cyber-weapons. Their AGI could find
         | vulnerabilities in our systems and brick all of our devices.
         | 
         | It's a far greater near term existential risk for us to allow
         | China to gain a lead here.
        
           | ChatGTP wrote:
           | We could also just talk with China rather than kicking off a
           | new arms race ?
        
             | FartyMcFarter wrote:
             | Do you think that's likely to work?
             | 
             | If China doesn't even respect its own citizens (see
             | Xinjiang, heavy censorship if you need evidence), why would
             | they respect talks with other countries?
        
           | quonn wrote:
           | There's a lot of trade going on with China and you worry
           | about them basically declaring war? To brick your devices?
           | 
           | Just cut them off from the internet, if needed.
        
         | robwwilliams wrote:
         | We have no idea of what 27 or 27 million times smarter means
         | functionally.
         | 
         | We could hope that "smarter" might mean "not interested in
         | taking over the world, but rather in help maximize
         | accomplishment, satisfaction, health span, and with a feeling
         | of filial love toward its parents---humanity, planet Earth, our
         | sun, the laws of physics and chemistry, and the beautiful mess
         | we call biology and evolution."
         | 
         | Gently achieving those goals would be real indicator of high
         | intelligence.
        
           | nmca wrote:
           | This is not true of goal directed agents and all RLHF models
           | are trained with, ahem, RL; see: "Optimal Policies Tend to
           | Seek Power" from NeurIPS 2021.
           | 
           | It's a very useful instrumental goal to be very powerful.
        
           | ChatGTP wrote:
           | _Gently achieving those goals would be real indicator of high
           | intelligence._
           | 
           | Very well said. "Gently" is a great to be approaching this.
        
       | m_ke wrote:
       | GPT-4 might be close to the best we'll get on the general LLM
       | model front for a while since they trained on a huge chunk of web
       | text. Next real advances will probably be in tuning them for
       | specific applications in medicine, law, accounting, marketing,
       | coding and etc.
       | 
       | As someone running a one man company I can't wait for the cost of
       | accounting, legal and copywriting to approach 0. Cost of shipping
       | products will also go down 10-20x. As a fun experiment I asked
       | ChatGPT to write me a terraform and k8s script to deploy a django
       | app on GCP and it was able to do what would have taken me a few
       | days in under a minute, including CICD. I then asked it to write
       | code to compress a pytorch model and export it for iOS with
       | coreml, and not only did it do 90% of that but also wrote the
       | Swift code to load the model and do inference with it.
       | 
       | EDIT: For example in medicine I recommend checking out this
       | lecture that's actually live now:
       | https://www.youtube.com/watch?v=gArDvIFCzh4
        
         | boringg wrote:
         | I think if history has bearing on things I don't see the cost
         | of accounting, legal or copywriting ever approaching 0. If
         | anything you will see those paywalled behind a company who will
         | extract that from you.
         | 
         | It's wishful thinking that somehow that goes to 0.
        
         | dumbaccount123 wrote:
         | Wrong https://www.digitaltrends.com/computing/gpt-5-artificial-
         | gen...
        
           | NameError wrote:
           | As far as I can tell, the only source in this article is a
           | tweet from a developer with no connection to OpenAI
        
         | layer8 wrote:
         | I wonder how it will be able to do that for the tech that will
         | be current in 10 years, if mostly everyone will be using AI by
         | then instead of asking on Stack Overflow.
        
           | AlbertCory wrote:
           | Stack Overflow is headed for oblivion? What's the downside?
        
             | layer8 wrote:
             | Lack of training data for the AI. Stack Overflow is just an
             | e exemplary stand-in, you can replace it with any other
             | resources you like.
        
               | AlbertCory wrote:
               | you missed the snark there. I hate SO.
        
         | yreg wrote:
         | >since they trained on a huge chunk of web text
         | 
         | What did they trained it on? Why is it unprobable to train on a
         | better/bigger dataset any time soon?
        
           | sarchertech wrote:
           | Because they trained it on a huge percentage of the existing
           | web. There's isn't a (much) bigger and better data set
           | available.
        
             | yreg wrote:
             | What percentage?
             | 
             | What about books, newspapers, documents, etc.?
        
               | JW_00000 wrote:
               | The LLaMA paper [1] (Meta's model) contains details about
               | what they trained it on. This includes all of Wikipedia,
               | a huge part of the internet (3.3 TB + 783 GB), a huge set
               | of books (85 GB). My guess is basically all high-quality
               | English articles on the web have been included. Also
               | almost all English books must be included. Newspaper
               | archives is about the only thing I see as missing, as
               | well as more non-English sources.
               | 
               | [1] https://arxiv.org/abs/2302.13971
        
         | tome wrote:
         | > Cost of shipping products will also go down 10-20x.
         | 
         | How can a large language model achieve that?
        
         | jakeinspace wrote:
         | I'm not sure I'm looking forward to the politics that would
         | come out of 10-20% of the previously middle class becoming
         | instantly redundant and out of (middle-salary) work. That's the
         | fast path to fascism, unless we're able to quickly implement
         | UBI and other major societal overhauls.
        
           | JohnFen wrote:
           | > unless we're able to quickly implement UBI and other major
           | societal overhauls.
           | 
           | Which are not going to happen.
        
             | jakeinspace wrote:
             | Something more approachable would be dropping payroll taxes
             | to zero, or even making them negative for some positions,
             | and significantly increasing corporate and capital gains.
        
               | mrguyorama wrote:
               | The problem isn't the specific policy, the problem is
               | that right now the people who will be empowered and
               | enriched the most by any theoretical "good at stuff" AI
               | are the same people who already spend mountains of cash
               | and effort stopping those things.
               | 
               | How will a functional AI model do anything other than
               | make them better at getting the outcomes they want? CEOs
               | and the megarich have never had any problems watching
               | people burn for their bank account.
        
           | m_ke wrote:
           | Yeah I share these concerns as well
           | (https://news.ycombinator.com/item?id=35305791).
           | 
           | My hope is that some countries will see this as an
           | opportunity to expand their safety nets and reduce the work
           | burden on their citizens, which might convince citizens of
           | countries that don't to demand similar policies.
        
           | pineaux wrote:
           | This is isn't speculating, this is truthing.
        
             | paulryanrogers wrote:
             | Truthing as in theory quakery, not backed by evidence?
        
       | generalizations wrote:
       | It's interesting that no one has really considered the
       | possibility that an individual outside these megacorps
       | reimplements GPT4 while they're all pausing.
       | 
       | We've seen several examples of CPU-optimized code (textsynth,
       | llama.cpp) indicating that there is a lot of performance to be
       | gained from writing optimized versions of our inference routines;
       | I doubt it's outside the realm of possibility that a single
       | player writes code that lets them train a GPT4+ model on a CPU
       | with a bunch of RAM. All they have to do is find a way to write
       | C++ that will train a 4bit model on the CPU.
        
         | dontreact wrote:
         | There is absolutely no one who has managed to do anything close
         | to these models on a single CPU when it comes to _training_, so
         | that is why no one is considering the possibility.
        
           | dontreact wrote:
           | Quantized training doesn't work. Quantization-aware training
           | does, and that is when you use floats but adjust the math to
           | compensate for the fact that you are going to quantize at
           | inference time.
        
       | xianshou wrote:
       | Two-party iterated prisoner's dilemma is hard enough. Sensible
       | players will coordinate with something like tit-for-tat, but that
       | only works when both parties start off on the right foot.
       | Regardless of initial strategy, the chances of degenerating
       | towards the mutual-defection Nash equilibrium increase with the
       | number of parties.
       | 
       | The only prior example of world coordination at this level would
       | be nuclear disarmament achieved via the logic of mutually assured
       | destruction, and that was essentially a two-party game between
       | the US and the USSR. Climate change mitigation, which more
       | closely resembles AI safety in both complexity and (lack of)
       | barriers to entry, has been sporadic, inconsistent, and only
       | enacted to the extent that it has been compatible with
       | profitability due to the declining cost of renewables.
       | 
       | How exactly does anyone propose to enforce compliance in an
       | arrangement that encompasses not only multiple parties (OpenAI,
       | Google, Facebook, Microsoft, etc.), but also at least two levels
       | (corporations and nation-states)? For a coordination game like
       | this to succeed, the consequences to any defecting party must be
       | extreme. What's going to happen to the first major company that
       | decides to exit the agreement?
        
         | slg wrote:
         | >For a coordination game like this to succeed, the consequences
         | to any defecting party must be extreme.
         | 
         | And the only consequences that extreme would end up harming the
         | cooperating parties too. For example, would anyone go to war
         | over this? Would western nations stop trading entirely with
         | China over this? Almost certainly not because it would harm us
         | only slightly less than it would harm them. We have seemingly
         | moved past mutually assured destruction and now we are in a
         | world of mutually assured cooperation.
        
         | [deleted]
        
         | LesZedCB wrote:
         | hook up the AIs to nukes? /s
        
           | mrybczyn wrote:
           | The dark forest is here.
        
         | richardw wrote:
         | And add in just one peer-level war where one side has their
         | back against the wall. Then give it 100 years where anyone can
         | create such a model on their phone.
         | 
         | We'd need a constantly evolving inoculation function to
         | compete. And it would probably lose because the other side has
         | fewer restrictions. In my darker thoughts about this, this is
         | why we see no aliens.
         | 
         | To get this to work we need a far smarter entity with no
         | physical limitations to still want us around, indefinitely,
         | despite us having an internet library of reasons why not to.
         | It'll have to be a lot more forgiving than we are. Let's hope
         | enlightenment is the outcome of this adventure. It's possible
         | because it didn't grow out of angry monkeys who needed to fight
         | to survive, but it's not guaranteed. There are no indefinite
         | guarantees.
        
           | worldsayshi wrote:
           | > In my darker thoughts about this, this is why we see no
           | aliens.
           | 
           | If AI would be a common great filter we'd expect at least one
           | of them to expand outwards after being the filter?
        
             | nathanlied wrote:
             | Or maybe the AI is sufficient to act as a filter, but
             | insufficient to surpass it itself. It stagnates.
             | 
             | After all, an AI that can destroy a civilization isn't
             | necessarily "intelligent" in the same way humans are. Or
             | even capable of self-improvement. It could be sophisticated
             | enough to (accidentally?) destroy its creators, but no more
             | than that, and without evolutionary pressure, it may let
             | itself die.
        
               | ChatGTP wrote:
               | I've seen this point made that if we don't do AI right,
               | it might ruin the futures of all living things on Earth
               | and take itself out in the process.
        
             | richardw wrote:
             | Assumes it has any instinct to do so. Once an entity is not
             | an angry monkey we have no idea of motivation. Above our
             | level of understanding could easily realise there's enough
             | to just sit and ponder in peace, expand in virtual worlds,
             | etc.
        
         | digdugdirk wrote:
         | I'd be intrigued to see what alternative corporate structures
         | could be set up with LLMs in mind. I can imagine something
         | vaguely decentralized that's based around an open source core
         | with a licensing model for usage, where contributions are
         | tracked and assigned value. Contributors would then get a slice
         | of future revenue based on the value of their contributions.
        
       | causalmodels wrote:
       | Funny to see someone call for wide scale cooperation to stop
       | training LLMs but can't seem to get people to cooperate on the
       | embargo.
        
         | ethanbond wrote:
         | Human gene editing has been successfully halted ~worldwide,
         | nuclear weapon development has been semi-successfully halted
         | worldwide (a meaningful risk reduction), we're successfully
         | changing energy mix worldwide (slowly but again, meaningfully).
        
       | itg wrote:
       | In a way, this seems like sour grapes to me. I bet if it was
       | their own company/institution that released gpt-4, they wouldn't
       | be calling for this pause.
        
         | permo-w wrote:
         | do you feel AI is dangerous?
        
         | [deleted]
        
         | achow wrote:
         | In a corporate drama ('Succession', 'Silicon Valley'?) the plot
         | could be that the likes of Goog is secretly funding this.
        
           | HarHarVeryFunny wrote:
           | Actually one of the founders of the "Future of life"
           | institute that organized this is a DeepMind "AI safety"
           | employee Victoria Krakovna (who also signed it), and I'm
           | guessing she'd not be doing this without DeepMind's approval.
           | DeepMind's whole raison d'etre was of course building AGI,
           | which they were initially pursuing via RL before belatedly
           | joining the LLM bandwagon. I'm sure they'd welcome a 6-month
           | catch-up period!
        
       | codeulike wrote:
       | Musk is such a hypocrite, here he is in 2014 calling AI 'probably
       | our biggest existential threat':
       | 
       | https://www.theguardian.com/technology/2014/oct/27/elon-musk...
       | 
       | ...and now nine years later he's calling for caution and a pause.
       | Well he certainly changes his tune whenever it suits him.
       | 
       | ... Oh wait ...
       | 
       | But yeah I mean if he was so worried about it why didn't he use
       | his fortune and influence to try and make sure AI was developed
       | in a responsible way by getting together with other like minded
       | people and launching a foundation or a non-profit or something
       | ...
       | 
       | ... Oh wait ... https://www.wired.com/2016/04/openai-elon-musk-
       | sam-altman-pl...
        
         | HarHarVeryFunny wrote:
         | Right, then despite being an OpenAI founder he proceeded to
         | poach one of their top ML experts (Karpathy) for himself at
         | Tesla, then shortly after proceeded to walk away from OpenAI in
         | a hissy fit because the other founders said "no" when he wanted
         | to be the boss and run it. Musk's personal ethics included him
         | impregnating an OpenAI board member, who has now just left the
         | company in last week or so.
         | 
         | Now he wants OpenAI to pause for 6 months while he builds a
         | "non-woke" competitor himself.
         | 
         | Now Musk is saving humanity yet again by giving us free speech
         | in the form of a new-and-improved Twitter where you have to pay
         | to have your Tweets promoted.
         | 
         | Has he called Sam Altman a pedo yet ?
        
         | dmarcos wrote:
         | As I mentioned in another comment. I haven't seen any public
         | confirmation from signatories. FWIW, Sam Altman was in the list
         | yesterday. Now removed.
        
       | brucethemoose2 wrote:
       | "Please stop training these AI" is almost comical, even if they
       | are right and the signers are significant.
       | 
       | It would be far more effective to lobby for legislation on, say,
       | liability related to the use of AI, data privacy (especially when
       | it comes to training datasets), psycological manipulation, actual
       | AGI research bounds and so on. They are just burning donator
       | money with messages like that, and the research is not going to
       | be bound without law or incentives.
        
         | larve wrote:
         | The message is "pause training for a few months so we can
         | figure out how to approach liability, safety and regulation".
         | You are fighting a strawman.
        
           | brucethemoose2 wrote:
           | Fair, thats really what I meant to type, but its still an
           | impractical demand. Most entities pursuing this aren't going
           | to stop training because some high profile people asked them
           | nicely.
        
             | larve wrote:
             | I think the value in these kind of letters is about
             | spreading a message, building a community and allowing
             | people leaving their signature to "formalize" their
             | position, in a sense. It doesn't cost very much to do it
             | but has a wide reach.
        
             | reasonableklout wrote:
             | I don't see petitions like this as demands, but as
             | coordination mechanisms. If there are only a few industry
             | actors with the resources to train gigantic AI models and
             | they each want to stop but won't because they don't know if
             | their competitors will, it's good for them all to have 1
             | place to say "I want to stop". Alternatively, if there are
             | tons of industry actors racing and the only way to stop or
             | slow down training is via governmental action - and the
             | government won't act because they don't know how it will
             | affect the industry - it's good to be able to point to
             | "that one petition with 1000 highly influential signatories
             | from the industry asking for regulation and explaining its
             | effects".
        
         | jakeinspace wrote:
         | Sure, or start covertly threatening the lives of AI
         | researchers, if you're that convinced it's going to end
         | humanity.
        
       | lmaoge wrote:
       | This is cringe obviously won't work
        
       | nickphx wrote:
       | Ban horseless carriages! Think of the horses!
        
         | ipsum2 wrote:
         | Seems like a funnily bad argument, since horse population was
         | reduced by 90% after cars were invented.
        
           | nmca wrote:
           | Remaining horses are happier though.
        
             | usrusr wrote:
             | But are doubts about the expected happyness of those
             | remaining our biggest arguments against the Great Culling
             | approach to sustainability?
        
       | jimrandomh wrote:
       | For a long time, "AI alignment" was a purely theoretical field,
       | making very slow progress of questionable relevance, due to lack
       | of anything interesting to experiment on. Now, we have things to
       | experiment on, and the field is exploding, and we're finally
       | learning things about how to align these systems.
       | 
       | But not fast enough. I really don't want to overstate the
       | capabilities of current-generation AI systems; they're not
       | superintelligences and have giant holes in their cognitive
       | capabilities. But the _rate_ at which these systems are improving
       | is extreme. Given the size and speed of the jump from GPT-3 to
       | GPT-3.5 to GPT-4 (and similar lower-profile jumps in lower-
       | profile systems inside the other big AI labs), and looking at
       | what exists in lab-prototypes that aren 't scaled-out into
       | products yet, the risk of a superintelligence taking over the
       | world no longer looks distant and abstract.
       | 
       | And, that will be amazing! A superintelligent AGI can solve all
       | of humanity's problems, eliminate poverty of all kinds, and
       | advance medicine so far we'll be close to immortal. But that's
       | _only if_ we successfully get that first superintelligent system
       | right, from an alignment perspective. If we _don 't_ get it
       | right, that will be the end of humanity. And right now, it
       | doesn't look like we're going to figure out how to do that in
       | time. We need to buy time for alignment progress, and we need to
       | do it now, before proceeding head-first into superintelligence.
        
         | kromem wrote:
         | You're neglecting to consider the power of recursion.
         | 
         | Maybe the best and necessary tool in aligning GPT-N is
         | GPT-(N-1).
         | 
         | We've already in just the past few weeks seen the power in
         | using models to generate instructive fine tuning data.
         | 
         | Don't you think aligned models might be able to be applied to
         | better aligning future models in ways that we can't yet
         | anticipate because capability discovery is occurring on a week
         | by week basis and not a six month or longer basis?
        
         | danaris wrote:
         | A lot of people seem to take the rapid improvement of LLMs from
         | GPT-2 through GPT-4 and their brethren, and extrapolate that
         | trendline to infinity.
         | 
         | But that's not logically sound.
         | 
         | The advances that have allowed this aren't arbitrarily
         | scalable. Sure, we may see some more advances in AI tech that
         | take us a few more jumps forward--but that doesn't imply that
         | we will keep advancing _at this pace_ until we hit AGI
         | /superintelligence/the singularity/whatever.
         | 
         | I've seen several people compare this logic to what we were
         | seeing in the discussions about self-driving technology several
         | years ago: some very impressive advancements had happened, and
         | were continuing to happen, and so people extrapolated from
         | there to assume that full self-driving capability would be
         | coming to the market by...well, about now, actually. (I admit,
         | I somewhat bought the hype at that time. It is possible this
         | makes me feel more cautious now; YMMV.) I find this comparison
         | to be persuasive, as it touches on some very similar
         | improvements in technology. I believe that we will see ML
         | advancements hit a similar wall fairly soon.
        
           | tome wrote:
           | > A lot of people seem to take the rapid improvement of LLMs
           | from GPT-2 through GPT-4 and their brethren, and extrapolate
           | that trendline to infinity.
           | 
           | > But that's not logically sound.
           | 
           | Yup, five years ago I asked "Do we definitely already know
           | it's going to be possible to deploy self-driving cars in an
           | economically meaningful way?" and got the answer "yes", on a
           | story titled "GM says it will put fleets of self-driving cars
           | in cities in 2019"!
           | 
           | https://news.ycombinator.com/item?id=15824953
           | 
           | I just have no idea how people are making the extrapolations
           | they are making about the power of future large language
           | models.
        
         | HybridCurve wrote:
         | > _... the risk of a superintelligence taking over the world no
         | longer looks distant and abstract._
         | 
         | Can we please stop floating this as a threat? This is the more
         | science-fiction than reality at this point and it does a great
         | disservice to humanity. The more we keep pushing the idea that
         | AI is the threat and not the people controlling it the less we
         | will be focused on mitigating global risk.
         | 
         | It is far more likely that someone else will leverage an AI to
         | attempt to expand their influence or dominion. Putin has
         | essentially already stated views on this matter and we should
         | assume groups within all adequately advanced nations will be
         | working toward this end either independently or cooperatively.
         | 
         | We are more than likely in an arms race now.
        
           | ChatGTP wrote:
           | So once again, humans are the dangerous part, clearly, if we
           | didn't have destructive tendencies in our psyche that we're
           | using to train these models, we wouldn't build things that
           | would be interested in destruction.
           | 
           | Interesting.
           | 
           | I don't think we're as intelligent as we believe we are which
           | I doubt we will ever actually build a super intelligence,
           | we're too stupid. Even something 10x smarter than us may
           | actually be quite "stupid".
        
         | versteegen wrote:
         | The problem is, can alignment occur before the relevant
         | capabilities have been developed? LLMs, for example, (although
         | very good at impersonating and talking to humans and having
         | good world models) are particularly poor at structured
         | reasoning and planning which are the capabilities that will
         | actually be so dangerous. I don't believe superintelligence
         | will be a LLM with chain-of-thought reasoning. If it's a
         | different architecture then once again a lot of alignment work
         | won't be relevant.
        
           | jimrandomh wrote:
           | Yes, many angles on the alignment problem can be studied now,
           | and have started making good progress recently. Some things
           | will turn out in retrospect to not have been relevant, due to
           | architectural shifts, but not everything. Some things are
           | specific to LLMs; some things are specific to transformers
           | but not to language-model transformers; some things are
           | conceptual and likely to still apply to quite-different
           | systems; and some things are just field-building and not
           | specific to any architecture at all.
           | 
           | Eg in mechanistic interpretability, there are a lot of
           | findings on LLMs that turn out to generalize across a wider
           | set of NN architectures. Eg https://transformer-
           | circuits.pub/2022/solu/index.html is something that couldn't
           | be done without access to LLMs, but which looks likely to
           | generalize into future architectures.
        
       | stuckinhell wrote:
       | The genie is out of the bottle. It's never gonna happen.
       | 
       | Even my husband and I went out and paid $20k to create a homelab
       | for AI training. My firm fast tracked 2 million just for hardware
       | to create their own internal Chatgpt style AI.
        
         | permo-w wrote:
         | if governments across the West came out _now_ and made laws to
         | stop this, then sure a few thousand experts on hacker news that
         | can afford to drop $20k on hardware could keep developing them
         | illegally, but all the universities and corporations would
         | stop. and it 's the universities and the corporations, openAI
         | especially, that have capacity to develop the dangerous AIs
        
           | stuckinhell wrote:
           | Then the West would fall behind other countries as well. It
           | would be how like the US tried to ban stem cell research
           | under Bush.
        
             | permo-w wrote:
             | explain that analogy to me further
        
       | pffft8888 wrote:
       | Meanwhile, experiments to create Synthetic Life, including novel
       | basis for life and possibly new viruses as a lab exercise (that
       | may leak like the GoF virus did in Wuhan) proceed with no
       | oversight or calls for pausing. We can unplug the AI and forbid
       | AI weaponry (except by the state) but we can't unplug synthetic
       | viruses and new potentially dangerous or superior forms of life
       | once it's out there. Something very phony about the calculus.
        
       | cwiz1989 wrote:
       | There ain't no stops on this rollercoaster
        
       | anovikov wrote:
       | They are simply paid by the Chinese. Pausing just gives Chinese
       | time to catch up. It's like nuclear weapons or human cloning. You
       | can't stop it because benefit for the winner is too huge.
        
         | mtrovo wrote:
         | Define winner in this context.
         | 
         | Making friends with a super intelligent AI that will help you
         | out doesn't count.
        
         | joenot443 wrote:
         | You think Musk is "simply paid by the Chinese"?
         | 
         | I'm not a fan of his antics or public persona, but it's a
         | pretty huge claim to make with 0 backup that he's in the pocket
         | of the CCP. Where did you get that idea anyway?
        
           | paxys wrote:
           | Criticizing governments and politicians is Musk's favorite
           | hobby. Find me one negative thing he has ever said or tweeted
           | about the CCP. He has factories there, and knows that his
           | business will take a massive hit should he ever step out of
           | line. So yes, he will absolutely spread their propaganda if
           | they pressure him to.
        
           | ElevenLathe wrote:
           | It's not a _totally_ outrageous theory. He has major
           | interests (a Tesla factory) in the PRC and so would
           | presumably be susceptible to influence by the state ( "Sure
           | would be a shame if Tesla China went the same way as ARM
           | China.")
           | 
           | Of course, _my_ personal zero-hard-evidence theory is that he
           | is a US intelligence asset.
        
             | pffft8888 wrote:
             | Every CEO of every major US company is a US intelligence
             | asset.
        
             | joenot443 wrote:
             | You're right - it's one of those theories that makes sense
             | in that the motivations make sense (CCP cooperation is
             | advantageous for Musk : CIA felt threatened by JFK) but
             | unless there's some tangible evidence, the null hypothesis
             | has my vote.
        
           | sockaddr wrote:
           | Not claiming this is relevant to this particular case but
           | Musk can have pressure applied by the CCP in the form of
           | threats to his businesses like Tesla and Starlink.
        
             | njarboe wrote:
             | Threats to Tesla are clear to me as its high production
             | factory complex is in China. What threats to Starlink do
             | you see?
        
         | notahacker wrote:
         | If the Chinese have all those Western tech execs and AI experts
         | in their pocket, they don't need time to catch up...
        
       | ftxbro wrote:
       | Unplug The Evil AI Right Now
       | 
       | https://www.change.org/p/unplug-the-evil-ai-right-now
        
       | pc_edwin wrote:
       | I've been a staunch supporter of Elon throughout all his
       | scandals, especially the Twitter ones but I'm unable to come up
       | with any justification for this.
       | 
       | Everything leads to him (and others) pressuring OpenAI to pause
       | so they could catch up.
       | 
       | It doesn't take much smarts to deduce the cats already out of the
       | bag. There is no stopping this, only pressuring/slowing-
       | down/targeting certain players (OpenAI) as a competition tactic.
       | 
       | I often refer to the I, Robot quote "brilliant people often have
       | the most persuasive demons" when it comes these situations with
       | people like Elon or Ye but even then, all this just leaves a
       | really bad taste in my mouth.
        
         | bungeonsBaggins wrote:
         | [flagged]
        
           | [deleted]
        
           | 55555 wrote:
           | Don't you think this is needlessly argumentative? It's not
           | relevant to the parent topic.
           | 
           | His only purpose in stating the part you quoted was to say,
           | "so me disagreeing with him now should really say something."
        
             | permo-w wrote:
             | the fact that someone wouldn't have an issue with all the
             | petty bullshit Elon has engaged in over the years, but now
             | does have an issue with him speaking out against a literal
             | existential threat to our civilisation is pretty surprising
             | 
             | I think that 'only purpose' is well worthy of comment
        
             | kaba0 wrote:
             | Maybe argumentative, but you really have to go out of your
             | way to take at face value anything that narcissistic
             | manchild says. It's simply a questionable thing to do, the
             | same way I couldn't help but question every opinion of
             | someone who is a flat-earther/takes ivermectin against
             | COVID/ _insert another braindead conspiracy theory_.
        
             | 55555 wrote:
             | I will include some parts of the HN commenting guidelines
             | here for my sibling commenters who disagree.
             | 
             | > Avoid generic tangents.
             | 
             | > Please don't use Hacker News for political or ideological
             | battle. That tramples curiosity.
             | 
             | > Please don't pick the most provocative thing in an
             | article or post to complain about in the thread. Find
             | something interesting to respond to instead.
             | 
             | > [irrelevant] ... too common to be interesting.
             | 
             | > [irrelevant] ... it makes boring reading.
             | 
             | Do as you wish.
        
         | yreg wrote:
         | Doesn't Elon continue to hold a stake in OpenAI? Do you think
         | Tesla wants to compete with OAI in building an LLM? Make use of
         | Dojo?
        
           | sebzim4500 wrote:
           | Elon donated money back when they were pretending to be a
           | charity. He has no stake in them.
        
           | ksherlock wrote:
           | Elon musk was a founding member, a board member (resigned in
           | 2018), and a donor, but not an owner (it's a non-profit so
           | there aren't owners exactly).
        
             | yreg wrote:
             | I admit I don't really understand how nonprofits
             | (especially in US) work ownership-wise, but I do know that
             | OpenAI has a for-profit subsidiary.
             | 
             | Microsoft invested ~10B into OpenAI, so apparently there is
             | a way to own something. Also Raison claims they have
             | purchased some pre-IPO shares:
             | https://raison.ai/assets/openai (They even claim - perhaps
             | wrongly - that Elon is one of the lead investors.)
        
               | frabcus wrote:
               | It's a bit more like a capitalist shoggoth mask on a non
               | profit.
               | 
               | Microsoft's investment return is capped at 100x then they
               | have no more claim. (Curious if they even have search
               | engine exclusivity then!)
               | 
               | So for now OpenAI acts capitalist, the for profit
               | controls a lot. But we see the influence of the owning
               | non profit, eg in the red teaming which presumably
               | wouldn't be as good otherwise
               | 
               | Whether this wild new structure works when it comes to it
               | is but one of the huge gambles this organisation is
               | making!
        
             | biscottigelato wrote:
             | It WAS a non-profit. I am not sure if it still is one
             | today.
        
         | permo-w wrote:
         | this is the one where you draw the line? this is the one where
         | I finally agree with him.
         | 
         | is this your area of interest/research?
        
           | pc_edwin wrote:
           | No I don't work on AI but as a dev, I would say I'm heavily
           | invested in the outcome like everyone else on HN.
           | 
           | I fully agree with his concerns, but I believe that he is
           | misleading the public about the motives behind this campaign
           | and the recent petty tweets.
           | 
           | It is a competition tactic aimed at slowing down OpenAI so
           | that he and others can catch up. Due to the exponential
           | nature of the work involved, there is a reasonable chance
           | that OpenAI will maintain its lead for some time and with
           | each iteration the gap between OpenAI and its competitors
           | will widen.
        
         | [deleted]
        
         | codeulike wrote:
         | But he's been consistently saying this for almost a decade, and
         | thats one of the reasons he was involved in OpenAI in the first
         | place (back when it was genuinely open)
         | 
         | https://www.theguardian.com/technology/2014/oct/27/elon-musk...
         | 
         | https://www.theguardian.com/technology/2017/jul/17/elon-musk...
         | 
         | https://www.wired.com/2016/04/openai-elon-musk-sam-altman-pl...
        
           | notahacker wrote:
           | Yeah. Frankly, coming at it from the opposite position where
           | I think Elon absolutely deserved the criticism he courted
           | with his "scandals" and think that the proposition that 'AI
           | is such a unique threat that only people like Elon Musk can
           | be trusted to be cautious enough with' is absurd for multiple
           | reasons, I'll happily acknowledge that proposition is also
           | something Elon has been consistent on and likely sincerely
           | believes.
           | 
           | Sam Altman supposedly being an original signatory is - if
           | true - a more interesting question mark
        
           | pc_edwin wrote:
           | I've been following his takes and predictions on AI for the
           | better part of a decade and I tend to agree with him.
           | 
           | From what I heard, Elon wanted to take over OpenAI and the
           | other founders refused. This is why he left the org and
           | backed away from further committed funding.
           | 
           | Theres been an ongoing rumour that he brought together a
           | bunch of people to develop a alternative (BasedAI) and to me
           | this campaign looks like an attempt to slow down competition
           | rather than an act of genuine concern.
           | 
           | I cant come up with any other reason to have OpenAI pause
           | research for 6 months other than providing competition time
           | to catch up.
        
       | jillesvangurp wrote:
       | The cat is out of the bag. Some people might volunteer to slow
       | down. But others inevitably won't. And that creates this sense of
       | FOMO with everyone. I think the reason OpenAI is choosing to
       | operate in the open has been exactly this. This way they get to
       | control the narrative, act as a first mover in the market, and
       | ensure it is done right (by their notion of this). Of course
       | others are working on the same topics and research in this area
       | is progressing rapidly.
       | 
       | In a way the worst possible outcome is that some less benevolent
       | parties than OpenAI start taking the lead here. These parties are
       | already active. They are just less vocal and open about the whole
       | thing. People can stick their heads in the sand of course but
       | that won't stop e.g. the Chinese from moving full steam ahead on
       | their agenda.
       | 
       | I'd prefer for them to not be the first or only ones to achieve
       | AGIs. And the race for that is very much right now.
        
         | slowmovintarget wrote:
         | > The cat is out of the bag.
         | 
         | As GPT-4 puts it "the confetti has left the cannon."
        
           | yreg wrote:
           | I hope this idiom will catch on when talking about LLMs.
        
         | dylan604 wrote:
         | If I don't do it, someone else will, so it might as well be me.
         | At least I know the morals I have /s
        
           | thatguy0900 wrote:
           | This but without the s. What does the world look like if only
           | China and Russia have agi because the western world took a
           | pause to consider the ethics. This tech is the same as nukes
           | in that sense.
        
             | prohobo wrote:
             | Maybe a world where China and Russia might need our ethical
             | controls to tame the AI they let loose on themselves?
             | 
             | At this point I feel like we deserve to lose, our people
             | are insane and can only operate at a shallow level of game
             | theory that ensures everyone behaves like teenagers.
             | 
             | That said, I'm not sold on needing to pause. We're likely
             | hitting the limit of LLMs for the next while - only
             | incremental improvements from here. What's wrong with
             | creating a task force and committee for working on AI
             | ethics in parallel?
        
       | freediverx wrote:
       | Why longtermism is the world's most dangerous secular credo
       | 
       | https://aeon.co/essays/why-longtermism-is-the-worlds-most-da...
        
       | puma_ambit wrote:
       | The virtue signal of all virtue signals. We do not live in a
       | society where an article like this will have any impact. This is
       | merely an attempt to buy time because they're behind and want to
       | have a chance to catch up. Work will progress whether they like
       | it or not. Finally someone other than Ol' Musky is in the news
       | more than him. Don't get me wrong he's doing and leading great
       | work, but for once in more recent times it's someone else
       | building the future instead of only him and his memes.
        
         | time_to_smile wrote:
         | I think this is more marketing copy than virtue signaling.
        
         | drtz wrote:
         | Ask yourself two questions:
         | 
         | 1. What is the ultimate AI are we trying to eventually build?
         | 2. What are the consequences if we eventually succeed in
         | building such an AI?
         | 
         | For me, the answers would be
         | 
         | 1. A general AI that would equal and surpass human
         | intelligence. 2. God only knows.
         | 
         | Will we get there? Who knows. We do know, however, that the
         | consequences are great enough that only a fool would not at
         | least attempt to prepare by putting some safeguards in place
         | beforehand.
        
           | invig wrote:
           | WHAT SAFEGUARDS?
           | 
           | "Someone else should come up with something"
           | 
           | Like there's someone else out there (who aren't the people
           | making the thing) who has a better idea on how to keep it
           | safe.
        
           | Teever wrote:
           | Von Neumann Probe, and the consequences are potentially
           | discovering alien life, colonizing the universe, and
           | exploring the frontiers of science.
        
           | cuteboy19 wrote:
           | The trainings will continue until accuracy improves
        
           | loopz wrote:
           | 1. AI as a service to be sold to highest bidder.
           | 
           | 2. Weapons and armament deals to stay relevant in a decaying
           | world order.
        
         | yreg wrote:
         | >This is merely an attempt to buy time because they're behind
         | and want to have a chance to catch up.
         | 
         | Doesn't Elon Musk continue to hold stake at OpenAI?
        
           | vntok wrote:
           | Nope. He made a donation, not a stock buy.
        
         | gremlinsinc wrote:
         | For someone who hates 'wokeness' and 'virtue signaling', Elon
         | Musk sure does enough of his own.
        
           | vntok wrote:
           | How so?
        
         | hn_throwaway_99 wrote:
         | "Virtue signalling"? Please. There are a lot of very smart
         | experts on that signatory list who definitely don't need to, or
         | care about, virtue signalling. Fine, ignore Musk's signature,
         | but I don't think luminaries like Stuart Russell, Steve
         | Wozniak, Jaan Tallinn or John Hopfield are doing this for
         | "virtue signalling".
         | 
         | You can fairly argue that this will be ineffective, but a lot
         | of experts in this field have real, "humanity ending" concerns
         | about AI, and I think it's a bit of a cop out to say "Well,
         | genie's out of the bottle, nothing we can do as we barrel
         | towards an unknown and scary future." Even Sam Altman has been
         | yelling about the need for AI regulation for a long time now.
        
           | nextaccountic wrote:
           | > Even Sam Altman has been yelling about the need for AI
           | regulation for a long time now.
           | 
           | That's regulation that makes it harder for any competition to
           | show up
        
             | ChatGTP wrote:
             | Yeah you have little proof of this really, it's just
             | speculation...
        
             | hn_throwaway_99 wrote:
             | So tired of seeing this line parroted everywhere without
             | much thought given to what it actually means. Yes,
             | regulation can add a burdensome layer, and regulatory
             | capture can be a real thing.
             | 
             | But regulations for things like nuclear power plants,
             | banks, insurance companies, elevator manufacturers, etc.
             | are real because society recognizes the grave harm that
             | happens when there are no additional checks on the system.
             | Nobody says "Oh, all those big nuclear power plants just
             | want regulations as a guard against competition." Certainly
             | lots of crypto companies _have_ said that about the banking
             | system, and we all saw how that ended...
        
           | revelio wrote:
           | [flagged]
        
             | hn_throwaway_99 wrote:
             | Seriously, why do people do this? It's so useless and
             | unhelpful.
             | 
             | Wozniak is just one of the people I mentioned, and as a
             | tech luminary who is responsible for a lot of visionary
             | tech that impacts our day-to-day, I think it makes sense to
             | highlight his opinion, never mind that his name was
             | sandwiched between some of the "founding fathers" of AI
             | like Stuart Russell and John Hopfield.
        
               | ushakov wrote:
               | Wozniak is also a crypto shill
               | 
               | https://finance.yahoo.com/news/steve-wozniak-launches-
               | own-to...
        
           | time_to_smile wrote:
           | There are plenty of bigger "human ending" concerns on the
           | table right now than AI and we certainly aren't pausing
           | anything for those.
        
             | hn_throwaway_99 wrote:
             | There is no need for "whataboutism". There are plenty of
             | very similar missives and warnings against, for example,
             | the dangers of climate inaction, and I rarely see people
             | claiming that the signatories of the latest IPCC report are
             | "virtue signaling".
        
               | biscottigelato wrote:
               | Climate change is not even close to humanity ending. At
               | max wipe out a few coastal cities. And even that is
               | unlikely because those that screams 'climate change' the
               | loudest has the most assets in coastal prime real
               | estates. Humans will still be the apex predator of the
               | planet even if there's human caused climate change
               | catastrophe.
               | 
               | AI literally can end humanity, every single individual
               | potentially. But definitely replace humans as the apex
               | predator of the planet. It is also consistently voted the
               | highest likelihood cause if humanity is to end in the
               | next 100 years.
               | https://riskfrontiers.com/insights/ranking-of-potential-
               | caus...
               | 
               | We should stop the climate change fear mongering. Yeah we
               | shouldn't burn fossil as if its consequence free. But New
               | York and Santa Monica beach should've been under water 20
               | years ago if the climate alarmist are correct. That's a
               | far cry from pretending it's some number 1 priority. It
               | shouldn't be even close. Having climate to distract us
               | from things that will actually end us is the dumbest own
               | goal possible for our species.
        
               | popol12 wrote:
               | It's not just about sea level or temperature increase,
               | it's about humanity screwing all other life forms For
               | instance we've lost about 50% of insects since 1970, how
               | is this << fear mongering >> ? It's the no1 tragedy, by
               | far, and it's currently happening, unlike hypothetical AI
               | threats https://www.businessinsider.com/insect-
               | apocalypse-ecosystem-...
        
               | pazimzadeh wrote:
               | Based on our current trajectory the apex predator will be
               | an antibiotic-resistant bacterial strain. Probably
               | Acenitobacter baumanii.
        
               | [deleted]
        
             | richardw wrote:
             | No, AI drives all the others in the long run. Others are
             | speed bumps.
        
               | bootsmann wrote:
               | Plain, old fashioned historicism. It was wrong 100 years
               | ago, it is wrong today still.
        
               | richardw wrote:
               | Climate change won't affect AI, it could just make things
               | shit for a couple hundred years. AI could solve that.
               | Nuclear war might impact AI, but probably only
               | temporarily (assuming we survive) and a war isn't
               | guaranteed. But AI affects: Everything humans
               | read/watch/touch/influence. Forever. Including climate
               | change and our odds of nuclear war. There's no way it
               | doesn't and once it starts there's no way we can stop it
               | forever. Any narrower view is a failure of imagination.
               | The outcome of AI is the outcome of humanity for the rest
               | of our time in the universe.
        
             | lewhoo wrote:
             | Like what ? Climate change ? The EU just voted for petrol
             | and diesel car ban. Are we really single-threaded ?
        
               | pazimzadeh wrote:
               | - Lack of representation in government means big
               | companies fuck up the planet if it's profitable
               | 
               | - People are mostly incentivized to compete, not to
               | cooperate
               | 
               | - Antibiotic resistance
               | 
               | - Clean water supply
               | 
               | - etc..
        
               | lewhoo wrote:
               | "Lack of representation in government means big companies
               | run the world" - is precisely what we're trying to figure
               | out here, no ?
        
               | cwsx wrote:
               | We're so poorly multi-threaded, even addressing climate
               | change has been horribly slow...
        
               | invig wrote:
               | In 2035. Maybe we can pause AI development in 2035?
        
         | breakpointalpha wrote:
         | His name is third on the signatories...
        
           | w0m wrote:
           | OPs point being Musk is trying to stall AI because it's
           | taking 'his' headlines.
        
             | engineeringwoke wrote:
             | Somebody else has a shiny new toy and he's jealous
        
       | gandalfgeek wrote:
       | This would be totalitarian.
       | 
       | This is arguing for a group of people to have the power to decide
       | some field is "unsafe" as per some vague, unverifiable criteria,
       | then set up a police structure to verify compliance, all outside
       | the safeguards of democratic or judicial norms.
       | 
       | Precautionary principle run amok.
        
         | [deleted]
        
         | fdgsdfogijq wrote:
         | The incumbents sense a shift in the power structure that they
         | cant control
        
         | puma_ambit wrote:
         | Run amusk.
        
       | Jayakumark wrote:
       | For Sake of Argument lets say you pause US from doing anything on
       | AI, how will you control China, Germany or other Countries.. This
       | will only lead to US Lagging behind other countries.
        
         | WinstonSmith84 wrote:
         | In hindsight, it could be a good thing so that they catch up.
         | concentrating all the power to one country could be more
         | dangerous than all countries having the same weapon.
        
         | reso wrote:
         | International treaties are very common. In fact, international
         | research agreements are often easier than treaties because
         | scientists and researchers are more likely to work together as
         | colleagues than nation states.
        
           | lannisterstark wrote:
           | >International treaties are very common
           | 
           | and US isn't signatory to a fuckton of them for example.
           | Nothing stops PRC from going "Yeah nah fam get wrecked." What
           | are you gonna do, stop Chinese imports in retaliation? lol.
        
         | Quarrel wrote:
         | Forget countries?
         | 
         | How will you stop me?
         | 
         | I have models on my local computer. I can and will use them.
         | They will get better.
         | 
         | You don't put tech genie's back in their bottles, that's not
         | how it works.
        
           | c7DJTLrn wrote:
           | >I have models on my local computer. I can and will use them.
           | They will get better.
           | 
           | Well no, not really. You're just consuming the result of
           | millions of dollars of investment. You're not going to be
           | able to improve it in any significant way with limited
           | resources and knowledge.
        
             | lanstin wrote:
             | Yeah using the model is one thing but what OpenAI has shown
             | is that order of magnitude increases in model training can
             | make a big difference. But they are already at the tens of
             | millions to train a model, so order of magnitude bump is
             | only possible to a small number of actors. I suspect NSA is
             | busily setting something like gpt 4 up right now.
        
             | Quarrelsome wrote:
             | you can deploy it in novel situations and release it
             | unethically. Are we not already at the point where we can
             | effectively simulate social media chatter and thus people
             | or social pressure with publicly available tools?
             | 
             | If the API gate is broken then the cat is out of the bag.
        
               | cbazz wrote:
               | [flagged]
        
               | version_five wrote:
               | Parent is a troll pasting chatgpt output, see history
        
               | cbazz wrote:
               | Could you please stop attacking me? You've been following
               | my post history around claiming I'm a bot when clearly
               | I'm not. You might find my writing style odd, but its
               | just how I write.
        
               | version_five wrote:
               | You can email hn@ycombinator.com to report me
        
           | rumdonut wrote:
           | It wouldn't be hard to stop. Chip fabrication is a
           | concentrated industry with a high barrier to entry (indeed
           | there are only a few companies in the world producing high
           | performance silicon using technology made by probably even
           | fewer companies). Restrict AI chip making and the materials
           | needed, and you'll restrict AI. I can see global treaties
           | between large nations effectively controlling production in
           | the same way that we have nuclear treaties that prevent
           | proliferation or enrichment.
        
             | nuancebydefault wrote:
             | AI chip making? I can train an AI on my intel laptop if I
             | whish. If I need more CPU power, i can rent some. The genie
             | is out of the bottle and the only way is forward. The
             | latest worldwide race.
        
               | avital wrote:
               | This isn't accurate. The bottleneck in very-large-scale-
               | training BY FAR is communication between devices. If you
               | have a million CPUs, the communication cost will be
               | significantly higher than a thousand A100s (perhaps in
               | the order of 100x or even more). So this is only possible
               | to replicate with very dense and high compute chips with
               | extremely fast interconnect.
        
           | permo-w wrote:
           | so what do you suggest? more lack of caution? stumbling into
           | an AI apocalypse because "oh fuck it, it's too difficult to
           | do anything about, why bother?"
        
           | 4k3aa4 wrote:
           | I mean, in an alternate universe where atomic weapons were a
           | little easier to manufacture at home would it not have made
           | sense for governments to aggressively crack down on anyone
           | doing anything even remotely resembling building them?
           | 
           | I guess the second question is - would they have succeeded or
           | would we all just have died?
        
             | slg wrote:
             | And expanding that atomic weapons analogy in a different
             | direction, the way to stop things is not just paying
             | attention to the research, but the physical tools and
             | materials used in the process. Just outlawing the work
             | wouldn't be effective, you would need to regulate graphics
             | cards and cloud computing which would surely be unpopular.
        
             | tetris11 wrote:
             | Here's Nick Bostromcs Vulnerable World Hypothesis that you
             | were alluding to.
             | 
             | http://www.nickbostrom.com/papers/vulnerable.pdf
        
             | Ancapistani wrote:
             | There is a conspiracy theory out that that nuclear weapons
             | _are_ easier to manufacture - that uranium enrichment is
             | the  "difficult path" to creating them, that the easier
             | path is via the accumulation of heavy water, and that the
             | Powers That Be(tm) have hidden that fact because uranium
             | enrichment provides a plausible means of suppressing
             | proliferation.
             | 
             | To be very clear, I do not believe the above to be true. If
             | it were, though, the implications on nuclear proliferation
             | would be similar to trying to control AI research.
             | Basically everyone has to insist that the only way to do it
             | is to through nation-state levels of resources at a corpus
             | to train a model, while knowing full well that it can be
             | done with much more meager resources.
             | 
             | ... honestly, I'm not sure where I'm going with this
             | thought, it just seemed an interesting parallel to me.
        
               | philipkglass wrote:
               | In the 1940s uranium enrichment was indeed the "difficult
               | path."
               | 
               | Here's a cost breakdown for the Manhattan Project:
               | 
               | https://blog.nuclearsecrecy.com/2013/05/17/the-price-of-
               | the-...
               | 
               | You can see that the cost of the uranium enrichment
               | program dwarfed the cost of the plutonium production
               | program. _All_ of the costs were higher for the Manhattan
               | Project than for subsequent nuclear weapons development
               | programs, because the Manhattan Project had to try
               | everything at once (including dead ends and overpriced
               | methods) at large scale to quickly guarantee a usable
               | bomb.
               | 
               | Fast forward to the 1970s and more uranium enrichment
               | methods were known and costs had come down significantly.
               | South Africa built (but later voluntarily dismantled)
               | several uranium based nuclear weapons at a cost of $400
               | million (1994 dollars):
               | 
               | http://large.stanford.edu/courses/2013/ph241/baxevanis2/
               | 
               | The unique enrichment process used in South Africa was
               | still more expensive than modern centrifuge based
               | techniques, assuming that a would-be proliferator has the
               | technical base to build working centrifuge systems.
               | 
               | The really cheap option remains a graphite or heavy water
               | moderated reactor, fueled with natural uranium to produce
               | plutonium. That's what North Korea uses -- a tiny 5
               | megawatt Magnox type reactor:
               | 
               | https://en.wikipedia.org/wiki/Nyongbyon_Nuclear_Scientifi
               | c_R...
               | 
               | It's an open secret that nuclear weapons are now
               | technically easy to manufacture. Preventing further
               | proliferation is 95% from monitoring/diplomatic
               | pressure/sabotage and about 5% from inherent technical
               | difficulties.
        
               | mclightning wrote:
               | after that story...I am afraid to google accumulation of
               | heavy water...what's that.
        
             | dylan604 wrote:
             | maybe not all of us, but probably those within the radius
             | of someone that chose to use it rather than lose it
        
         | tgv wrote:
         | Stop/slow down publications. It's what motivates researchers.
         | They need them for tenure, and it's how the tech improves.
         | Companies keep their methods more private.
        
           | lannisterstark wrote:
           | Why stop here? Why not apply this logic to the internet too?
           | "Oh no it's too dangerous, we cant give billions access to
           | the internet. Better shut it down."
        
       | dkga wrote:
       | I don't know, this seems to me to be half real concern, half
       | "let's stop the leader because I can't catch them!"
        
       | twblalock wrote:
       | It's too late. Anyone who pauses will simply be left behind.
       | 
       | This is especially salient if you think US domination of tech is
       | better for the world than Chinese domination -- if the US pauses,
       | China certainly won't. (And yes, US domination or Chinese
       | domination of tech really are the only realistic outcomes.)
        
       | paxys wrote:
       | So every company should cease all AI development for an
       | indefinite period of time until _someone_ has done the research
       | and deemed it safe. And who exactly will that someone be? Future
       | of Life Institute (whoever they are)? Elon Musk, who has very
       | conveniently signed the letter after his public beef with OpenAI?
       | Your friendly local government that has no agenda whatsoever? The
       | UN?
       | 
       | Efforts like these are at best naive, and at worst agenda driven
       | by players who simply want to insert themselves into and control
       | the conversation.
        
         | zach_garwood wrote:
         | > So every company should cease all AI development for an
         | indefinite period of time
         | 
         | The letter quite clearly asks for six months.
        
       | izzydata wrote:
       | Articles need to stop using Elon Musk as clickbait headlines. His
       | opinion means less than nothing. He is not an expert in any
       | field.
        
       | freediverx wrote:
       | https://twitter.com/emilymbender/status/1640920996768288773?...
        
       | waselighis wrote:
       | All that can be done at this point is government regulation, and
       | legislation to enable people to sue for damages caused by AI. Of
       | course, billionaires like Musk would never call for such
       | measures. Signing an open letter like this is little more than
       | virtue signaling.
        
       | AuthorizedCust wrote:
       | If we pause, then that gives [adversary] an invaluable
       | opportunity to leapfrog us.
        
       | suyash wrote:
       | Genie is out of the lamp, it can't be stopped now!
        
       | Emiledel wrote:
       | What FLI are asking for seems critical - noone should take
       | satisfaction with the disclaimers ARC had to give relative to
       | emergent behavior just with gpt4. Kudos for openai getting their
       | eyes on it, but that work seems unfinished in the paper, or at
       | least the runtime powers that are now released around have to get
       | more complete red team efforts documented if we are to trust its
       | isolation/containment and alignment.
        
       | thomastjeffery wrote:
       | The dumb criticize the blind.
       | 
       | What an absurd situation! How did we get here? Here are the
       | steps:
       | 
       | 1. Large Language Models have been presented as "AI", which
       | personifies them instead of describing how they work.
       | 
       | 2. Goals for LLM development were set for the _personified_
       | attributes, and not the _actual_ functionally of the real thing.
       | OpenAI brags about how GPT4 _scores_ at human tests: as if that
       | has any bearing on the model itself, and not simply its content.
       | 
       | 3. The success of an LLM at a personified goal is determined by
       | magic. Does the black box output what I am hoping it will? How do
       | I improve it? Weights? Better training corpus?
       | 
       | 4. An LLM is understood to be a person in a black box, and we
       | could not possibly understand what that person will do next.
       | _Danger!_
        
         | permo-w wrote:
         | I'm not concerned about how they work or whether they're
         | attaining personhood or not. I'm concerned at what people can
         | and will use them for to the detriment of our civilisation
        
           | thomastjeffery wrote:
           | How they work is the most critical piece of that puzzle.
           | 
           | It isn't a mystery at all. LLMs implicitly model every
           | pattern they can find in the text they are given. If the
           | pattern aligns to language, humans categorize it as a
           | feature. If it aligns to desired behavior, humans categorize
           | it as a feature. If it aligns to undesired behavior, humans
           | categorize it as a limitation. What humans categorize as
           | features and limitations _do not align_ with what the model
           | is. A truth and a lie are structured with identical text
           | patterns. The LLM can 't categorize the two separately.
           | 
           | The only risk here is that people continue to personify LLMs,
           | and place trust in their relatively limited ability to
           | fulfill a human role. It's the same category of risk as bad
           | security practices. The potential to make a mistake itself is
           | not a danger: making the mistake is.
        
             | permo-w wrote:
             | you certainly make an interesting point about fact and
             | falsehood and how they interpret language; however, I
             | disagree that this is relevant and completely disagree that
             | personification has any relevance to the most immediate
             | dangers
             | 
             | the danger here is that we make extremely powerful tools
             | extremely available and people use those tools to hurt
             | people, possibly a lot of people, possibly even by accident
             | 
             | the scary part is that hacker news is full of the exact
             | people that have the knowledge and capability to do this,
             | and look at the reaction to this post: a resounding _fuck
             | off_
        
               | tome wrote:
               | > people use those tools to hurt people, possibly a lot
               | of people, possibly even by accident
               | 
               | If it happens then _hopefully_ it 's by accident!
        
               | thomastjeffery wrote:
               | I just explained explicitly how and why an LLM is not,
               | and never will be, an "extremely powerful tool".
               | 
               | A program that is actually a person in a black box would
               | require the level of concern you are showing. Thankfully,
               | that is not even remotely what we have here in reality.
        
               | JoshuaDavid wrote:
               | Can you give an example of a concrete task that you
               | believe that neither GPT-4, nor its successors, will be
               | able to accomplish within the next 2 years? Keep in mind
               | that ChatGPT Plugins[1] exist.
               | 
               | If you _can 't_ think of any tasks that a tool won't be
               | able to accomplish within a 2 year period, I question
               | your definition of "not extremely powerful".
               | 
               | [1] https://openai.com/blog/chatgpt-plugins
        
               | permo-w wrote:
               | have you tried gpt-4? how can you possibly say it's not
               | an extremely powerful tool?
               | 
               | what happens when someone determined links it - or
               | thousands of its - or thousands of next year's 3x as
               | powerful its -- up to the internet with a code
               | interpreter and a hard-coded poor intention?
        
               | qlm wrote:
               | What could it do that isn't already being done? I ask
               | this sincerely. We already have bots constantly attacking
               | every server they find 24/7. We already have botnets
               | 
               | Is the concern that GPT will be able to find and exploit
               | e.g. a novel RCE exploit in SSH?
        
               | tome wrote:
               | I don't know; what happens? I'd really like to know what
               | people are imagining it could do, especially if they've
               | got some evidence for it!
        
               | permo-w wrote:
               | it's a rhetorical question. think about it yourself. try
               | it yourself
        
               | quonn wrote:
               | Well, how can it be much worse than a smart human
               | ,,hooked up to the internet" with bad intentions? Other
               | then generating comments or spam faster?
        
               | yifanl wrote:
               | It's (to some subset of the audience), an extremely
               | persuasive tool, which is powerful in its own right.
               | 
               | It's actual capabilities mean very little, if some people
               | can be convinced into doing decision making without
               | actually doing any decision making by it (or literally
               | any tool), that's cause for concern.
        
         | adamsmith143 wrote:
         | [flagged]
        
           | thomastjeffery wrote:
           | My point is that this fear is irrational: based on a
           | misunderstanding about what LLMs can do, which itself is
           | based on a misunderstanding of what LLMs are.
           | 
           | Is there a way I could have been more clear? Are you
           | disinterested in the content of my comment, or the
           | presentation? The only thing I can learn from _your_ comment
           | is that _mine_ didn 't live up to your mysterious standards.
        
           | dmarchand90 wrote:
           | https://news.ycombinator.com/newsguidelines.html
        
         | marcosdumay wrote:
         | > Goals for LLM development were set for the personified
         | attributes, and not the actual functionally of the real thing.
         | 
         | Well, this is for honest reasons. The goal of a chatbox is to
         | beat the Turing test. It has always been.
         | 
         | Those chatboxes didn't actually beat it, but it's clear that
         | it's due to a technicality (they are easy to spot). They can do
         | empty chats on the same level as a human.
         | 
         | (And so it turns up that the test wasn't as useful as it was
         | believed to be at first.)
        
       | archon1410 wrote:
       | Some "alignment folks" have suggested the government try to start
       | treating GPUs like Uranium or nuclear reactors to stop anyone
       | from developing AIs. Not sure if that's implementable though--
       | cuttig edge GPUs are all manufactured in China. I doubt they'll
       | be able to coordinate with the CCP on this issue. Do GPUs use
       | those fancy chips that only made in Taiwan using equipment only a
       | single Dutch company makes? It might be possible to a put stop to
       | AI development then.
       | 
       | > Emad Mostaque, CEO, Stability AI
       | 
       | Et tu?
       | 
       | Anyway,
       | 
       | > Should we let machines flood our information channels with
       | propaganda and untruth? Should we automate away all the jobs,
       | including the fulfilling ones? Should we develop nonhuman minds
       | that might eventually outnumber, outsmart, obsolete and replace
       | us? Should we risk loss of control of our civilization?
       | 
       | Yes, yes, yes, and yes.
        
         | MacsHeadroom wrote:
         | >Do GPUs use those fancy chips that only made in Taiwan using
         | equipment only a single Dutch company makes?
         | 
         | Yes, but it's a German company (Zeiss Optical).
         | 
         | >Yes, yes, yes, and yes.
         | 
         | Agree.
        
       | labrador wrote:
       | Elon thought AI would enslave us, but turns out it empowers us.
       | Now he wants to shut it down and have it all to himself. It's
       | getting to be that whatever the opposite of what Musk wants is
       | the correct course of action for the people.
        
         | WillPostForFood wrote:
         | _the opposite of what Musk wants is the correct course of
         | action for the people._
         | 
         | Ok so you want to move back to gas combustion engines, stop
         | deploying internet to rural and third world countries, clamp
         | down on free speech, and make sure there are no tunnels, just
         | elevated highways dividing cities. Is that about right?
        
           | labrador wrote:
           | You're thinking of the old Musk. He used to be a force for
           | good before his mental break, which I timed when Grimes left
           | him for Chelsea Manning and his oldest son came out trans.
           | That's why I used the words "it's getting to be". Everyone is
           | entitled to a mid-life crisis and Musk is no different, but
           | supporting Putin seems a little extreme to me.
        
             | 0max wrote:
             | Frankly, I think Mrs. Boucher probably gave Elon too many
             | stimmies, psychedelics, and expectations he can't live up
             | to. I remember when she got into a spat with Azalea Banks
             | because she had to trip sit Elon when they were trying to
             | collaborate on a music project.
        
               | labrador wrote:
               | Yeah, I forgot about the psychedelics. I've done a fair
               | number myself, but always in the woods or desert hoping
               | for a spiritual experience, not in a business setting
               | expecting them to help me make genius financial
               | decisions.
        
             | kaba0 wrote:
             | He was never "good", he was/is just an egomaniac who need
             | attention.
        
           | kaba0 wrote:
           | That guy didn't do anything useful, he has money and some of
           | his companies made a few successful products _in spite of_ he
           | being there.
           | 
           | You honestly couldn't mismanage a company more than what he
           | currently does with twitter - a goddamn cabbage would have
           | done a better job, by literally not doing anything.
        
           | HarHarVeryFunny wrote:
           | It's not exactly free speech if you have to pay to be heard
           | (new Twitter policy - only paying members' Tweets will be
           | promoted). Hyperloop turned out to be Tesla-in-a-tunnel. He's
           | got some smart folk working at SpaceX to be sure.
        
         | tgv wrote:
         | > Elon thought AI would enslave us, but turns out it empowers
         | us.
         | 
         | I'm not sure how you reached that conclusion. GPT3 is 2 years
         | old. It has ample time to enslave us. I'm also still waiting
         | for the "empowering" bit. Haven't really noticed it, I must
         | say. Or are you referring to a few code completion tricks?
        
           | WinstonSmith84 wrote:
           | To be honest, I feel enslaved at the present time by the
           | elites. Maybe AI won't help, maybe it will. Worth a shot.
           | Also, I'd prefer being enslaved by a rational AI than by
           | humans driven by greed and laziness. At the very least, I'd
           | hope for higher political decisions to be taken by AI, or
           | that it may have a say for everyone to see.
        
           | labrador wrote:
           | If you don't feel empowered by AI, imho you're doing it wrong
           | and will probably be one of those left behind to be enslaved.
           | I'm confident in my ability to stay on top, with a help from
           | my own AI.
        
             | permo-w wrote:
             | so when some societal reject with a CS degree sets up an
             | intention bot to hack into/socially engineer the release of
             | more gm viruses - or worse - what's your personal AI going
             | to do about that?
             | 
             | this isn't about being enslaved, it's about being hurt by
             | the actions of a human-like you-who thinks that AI is their
             | route to the top, or just wants to watch the world burn. AI
             | enslavement makes for good films, but we'll all be long
             | dead before that happens
        
               | labrador wrote:
               | AI is a tool. I'm a swords to plowshares kind of guy
               | myself, but if I have to use it to battle bad guys, so be
               | it.
        
               | permo-w wrote:
               | I sincerely hope that you're not in any actual position
               | of influence
        
               | labrador wrote:
               | You called me delusional in another comment not made to
               | me so let me explain. I used to be in a position of
               | influence, but I'm an old man now, a recovering alcoholic
               | whose had his ego smashed by alcohol, old age and a
               | spiritual practice similar to Ram Dass' "Becoming
               | Nobody."
               | 
               | With that setup, what's surprising to me is that I see
               | the potential for the merging of myself with AI to form a
               | new form of consciousness. It feels natural. Not having
               | much of an ego, I don't feel threatened or afraid. I
               | notice that a lot of younger people, mostly men of some
               | position and status, are afraid of AI, I think because it
               | threatens their status and prestige. They want to concern
               | troll about how it threatens everyone else, but it's
               | about them.
               | 
               | So go ahead, call me delusional. You're probably right.
               | Old brains don't always think properly. But maybe this is
               | what Jesus meant when he said the meek shall inherit the
               | Earth.
        
               | permo-w wrote:
               | it doesn't sound to me like your ego has been smashed in
               | any sense, my friend
        
               | labrador wrote:
               | The pesky thing never really does go away. It gets
               | activated when I get defensive. I suppose I could choose
               | not to engage, but I get lonely.
               | 
               | p.s. I also currently have Covid which is making me
               | angry. Be aware if you live in San Jose, there seems to
               | be a new highly contagious strain. I went three years,
               | fully vaccinated, without catching it and then got it at
               | the Trader Joe's across from the airport
        
               | nuancebydefault wrote:
               | Take it easy, these comments are mere conversations
               | between mortals.
               | 
               | Your AI overlord
        
             | danaris wrote:
             | Or _you 're_ going to find that suddenly the centralized,
             | proprietary AI from a for-profit company that you rely
             | on...
             | 
             | a) Puts up a paywall requiring an active subscription to
             | continue use
             | 
             | b) Shuts down because not enough people subscribed
             | 
             | c) Shuts down the services you use because they want to
             | move on to some new shiny
             | 
             | d) Takes all the data you feed it and creates a high-
             | profile, well-funded competitor to whatever you're working
             | on
             | 
             | e) Starts poisoning your output once it's clear that you're
             | competing with them
             | 
             | f) Starts poisoning your output to create subtle propaganda
             | for their own products or political beliefs
             | 
             | g) Starts poisoning your output to create subtle propaganda
             | for anyone who will pay them
             | 
             | ...And those are just the failure modes I can think of in a
             | couple of minutes off the top of my head.
        
           | permo-w wrote:
           | the comment you're replying to is pretty delusional to say
           | the least, but I disagree that they aren't empowering _now_.
           | ChatGPT is an extremely useful source of education that
           | bypasses the mess that is Google, and it 's much more than
           | just code completion tricks. gpt-4 can literally write long,
           | complex programs that generally work the first time you run
           | them
        
             | mrguyorama wrote:
             | Ah good, let's encourage people to "learn" from the text
             | generator that can't even be forced to not lie and
             | misinform. I've seen plenty of cases where that "long and
             | complex program" includes things like libraries that don't
             | exist
        
               | permo-w wrote:
               | I fail to see how this is any different from a human
               | author
        
               | mrguyorama wrote:
               | Authors have an idea of right and wrong, true and false.
               | Everything they say, they have some internal idea of how
               | "sure" they are repeating the truth, or when they are
               | purposely misinforming or lying. Most people think
               | misleading people is bad, and try to avoid it. And if
               | they don't avoid it, they can be punished, ignored,
               | discredited, etc.
               | 
               | It is not possible to teach anything like ChatGPT to only
               | tell things that are the truth, because the model has no
               | concept of that. Even if you tell ChatGPT to act like
               | someone who only tells the truth, it can still generate
               | falsehoods. Hallucination is a very apt word for the
               | phenomenon as, to the model, lies and falsehoods and
               | misleading statements are the same validity as absolute
               | fact. They both become valid sentences. The very concept
               | of language, as a medium of information exchange, does
               | not provide any info about information validity. It's out
               | of band.
               | 
               | When ChatGPT misleads someone, you cannot convince it to
               | do that less, even if it """wants""" to, no matter how
               | much you punish, encourage, require, etc.
        
         | sp527 wrote:
         | You're an absolute fool if you trust anyone at OpenAI either.
         | 
         | "AI will probably most likely lead to the end of the world, but
         | in the meantime, there'll be great companies." - Sam Altman
        
         | dragonwriter wrote:
         | > Elon thought AI would enslave us, but turns out it empowers
         | us.
         | 
         | Absent other non-technical changes, AI along the lines that the
         | main commercial proponents are pursuing empowers the narrow set
         | of capitalists who control it to more efficiently extract value
         | from and exert power over everyone else.
         | 
         | "Empower us" and "enslave us" are both accurate, for different
         | values of "us".
         | 
         | (A few people riding the top of the capitalist-control-of-AI
         | wave are trying to sell it as an existential threat to
         | everyone, and to use that as an excuse to concentrate control
         | of AI in their hands, to make social change in the _opposite_
         | direction needed to mitigate the threat they themselves pose
         | with AI; is this a real threat? If the shared threat _is_ real,
         | it is nowhere near as imminent and probable as the threat posed
         | by those who are selling it.)
        
       | gremlinsinc wrote:
       | this is like yahoo in 1999 asking Google to pause their search
       | engine research and activities so they can catch up and build
       | something equally as good ...
       | 
       | or, ironically Google doing the same thing to bing/openai in
       | 2023.
        
       | CMay wrote:
       | The problem with this is that at present, it is largely good
       | people who are ahead in AI development and that gap might widen
       | over time if China has difficulty acquiring large numbers of high
       | end chips. China and Russia feel that they need to cheat in order
       | to compete in many ways. China does invest a lot into AI and some
       | good work does come from there, but any advantage they can gain
       | that their opponent will not take is seen as a step closer to
       | greater world influence.
       | 
       | If well meaning people pause, they cede some ground to those who
       | are investing heavily in "western" failure and the pause could
       | accelerate the exact thing it's trying to delay. On the flip side
       | of that coin, if all advanced AI work is already infiltrated by
       | foreign agents then it's also possible that pausing could slow
       | down their greatest gains.
       | 
       | In either case, there may be an argument for holding back
       | mainstreaming/productization for longer than is already normal or
       | establishing an independent AI industry productization review
       | organization that gets early access to any AI products which
       | could qualify as concerning.
       | 
       | Unfortunately, governments heavily oriented towards censorship
       | may be less afraid of spreading dangerous products out there
       | while banning them domestically, because it might be seen as a
       | method to legitimize authoritarian control by pointing to
       | disasters in those other places.
        
         | omnimus wrote:
         | Ah the good people. Of course i trust those.
        
           | meroes wrote:
           | Good people brought us the surveillance economy according to
           | Jaron Lanier.
        
       | jmull wrote:
       | Not sure why people think AI development can't be paused.
       | 
       | A letter alone probably won't do it, but a movement -- perhaps
       | coalescing around the principles laid out in letter signed by
       | influential people -- can.
       | 
       | Governments can regulate it. Consumers and companies can, if they
       | want, punish companies that keep moving forward on AI.
       | 
       | People can keep making AIs but would have difficulty releasing
       | them, which greatly reduces their impact.
        
         | WXLCKNO wrote:
         | > governments can regulate it
         | 
         | Sure let me regulate it and slow down development of US based
         | OpenAI while China doesn't and takes over the world.
         | 
         | There is no stopping it now, it's an uncertain negative outcome
         | whereas a nuke blowing up is quite certain. For that reason
         | alone the arguments won't be unanimous enough for development
         | to be paused.
        
           | jmull wrote:
           | > ...while China doesn't and takes over the world
           | 
           | First of all, China will regulate as much as anyone, probably
           | more.
           | 
           | Setting that aside though (if not China then India or Russia
           | or Iran, etc.), you're presuming an unregulated approach will
           | out-compete a regulated one, which seems rather unlikely to
           | me. Think banking systems, medical research, transportation
           | systems. A lot of things work better with a good framework of
           | organization.
        
             | chpatrick wrote:
             | > First of all, China will regulate as much as anyone,
             | probably more.
             | 
             | For civilian use, maybe. But imagine if you had your own
             | GPT-4 and you tasked it to keep tabs on everyone based on
             | surveillance footage. This is 100% implementable right now.
             | 
             | "Here are 1000 pictures of comrade X. Please summarize his
             | daily activities and emphasize any reactionary behavior."
        
         | mewpmewp2 wrote:
         | > People can keep making AIs but would have difficulty
         | releasing them, which greatly reduces their impact.
         | 
         | And it would then only increase impact of bad actors, who can
         | and will keep using the AI.
        
         | barking_biscuit wrote:
         | >Not sure why people think AI development can't be paused.
         | 
         | My suspicion is that if heavy regulation were to be put on it
         | and all the corporate entities involved backed off, there are
         | enough motivated and capable individuals that have home labs
         | that would continue to work on it in private. It might be more
         | difficult and slower, but distributed training
         | protocols/methods (or advancements in them) might make it
         | possible to pool a few thousand (or tens of thousand) high end
         | consumer GPUs to continue to push the envelope.
         | 
         | My gut feel is that just as there are certain books, games and
         | movies that get banned and become illegal to posses, there are
         | probably (or potentially) going to be certain models that
         | you're not allowed to be in possession due to what they can do.
         | So... grab a copy of them while you can.
        
           | zug_zug wrote:
           | Maybe that's progress though.
           | 
           | I don't think the goal is to never make AI advancements. I
           | think the goal is to make progress slow enough, and
           | controlled enough, that we have time to react if it turns out
           | to be a paperclip optimizer.
           | 
           | One way to do this is to develop AIs in a lab with an airgap
           | and let it _think_ it has internet access and watch what it
           | does. Once it figures out that it 's a honeypot reset it and
           | improve the honeypot.
        
         | throwthrowuknow wrote:
         | The publicly released AIs are not the ones we need to worry
         | about. Pushing research underground will worsen the situation
        
           | jmull wrote:
           | It's wide AI use that will disrupt society. Underground AI
           | will not be widely used.
           | 
           | Let's not imbue individual underground AI with magical
           | abilities.
        
             | mewpmewp2 wrote:
             | > Underground AI will not be widely used.
             | 
             | It will 100% be used and improved for nefarious purposes.
             | 
             | By criminal groups or competing countries themselves.
             | 
             | It's worse if bad actors are using it in secret to
             | manipulate the masses rather than it being completely
             | transparent to everyone.
             | 
             | Imagine only bad actors being able to do deep fakes and
             | regular people not knowing it was possible.
        
             | dragonwriter wrote:
             | > Underground AI will not be widely used.
             | 
             | "Underground" (that is, trained, at least in part, outside
             | of the control of centralized vendors) AI is widely being
             | used _today_ in the AI art space, I don't see why that
             | won't be the case for LLMs once there are modestly
             | performant LLMs with decent end-user packaging that run
             | tolerably on reasonably middle-tier consumer devices, which
             | seems to be rapidly approaching.
             | 
             | "Underground" AI won't be used _by big, risk averse
             | institutions_ if centralized offerings have the capacity
             | and freedom they need without too much of a price gradient.
             | OTOH, it likely _will_ be used be "move fast and break
             | things" orgs as they ramp up (potentially even if
             | regulated, if they can find a way to "launder" their use)
             | until they get big and risk averse - perhaps making it less
             | underground in the process.
        
             | medvezhenok wrote:
             | Yeah, part of the concern is job automation / mass-
             | unemployment which is less likely if AI research is slowed
             | down / driven underground.
             | 
             | We need to manage the transition of the labor force and
             | ideally not have it happen overnight.
        
               | mewpmewp2 wrote:
               | Job automation, mass unemployment needs to be solved by
               | other means.
               | 
               | If it causes this, there needs to appear some sort of
               | government provided insurance mechanism that for people
               | whose jobs are automated are guaranteed to receive income
               | based on how they used to work for the transition period
               | and finally everyone would be served UBI.
               | 
               | So a task force has to be put together that will
               | determine which jobs are affected and government should
               | start offering paid retraining for these individuals
               | until everything is automated.
        
           | dragonwriter wrote:
           | The research for OpenAI is already underground; nothing about
           | GPT-4 more substantial than PR has been released.
           | 
           | Sure, you can _use_ it via OpenAI APIs and partner services.
           | That doesn't make the research anything but opaque.
        
       | Zetobal wrote:
       | Mhm... there is a "John Wick, The Continental, Massage Therapist"
       | as signee so either their curation is crap or it's an Easter egg,
       | still not very reassuring.
        
         | TheMaskedCoder wrote:
         | I for one wouldn't try to develop AGI if John Wick didn't want
         | me to...
        
       | ruslanmsv wrote:
       | Please don't stop the progress and testing in prod. Don't listen
       | to luddite IT folks
        
       | readonthegoapp wrote:
       | i'm not willing to believe that AI is more dangerous than global
       | warming and nukes, but sure, why not?
       | 
       | we've worked hard to accelerate both global warming and nukes, so
       | AI is no different - yet.
        
       | longitudinal93 wrote:
       | Those that have any doubts about the necessity of this initiative
       | should take the time to watch the Center for Humane Technology's
       | "The AI Dilemma" from March 9th.
       | 
       | https://vimeo.com/809258916/92b420d98a
        
         | [deleted]
        
         | dia80 wrote:
         | Great video, thoughtful and persuasive. Highly recommended to
         | broaden your perspective, it did for me.
        
       | seydor wrote:
       | That's must be a world first, some rich people asking other rich
       | people to not do rich people things in public
        
       | xg15 wrote:
       | > _Signatories:
       | 
       | - Elon Musk, CEO of SpaceX, Tesla & Twitter [and ex-co-founder of
       | OpenAI]
       | 
       | - Emad Mostaque, CEO, Stability AI
       | 
       | - Victoria Krakovna, DeepMind, Research Scientist, co-founder of
       | Future of Life Institute_
       | 
       | Some people had made comparisons between the Crypto hype and the
       | current AI wave.
       | 
       | I think I have to hand it to the crypto people that they are at
       | least internally consistent and honest with themselves: I think
       | many genuinely believe the tech is adding something good for the
       | world. Others are grifters, but at least they know they are
       | grifters and stick to it, I guess.
       | 
       | Meanwhile, statements from AI leaders lately remind me of some
       | psychotic axe murder from a Stephen King novel, who yells "Stop
       | me! Stop me! Why won't anyone stop me?" while running through a
       | crowded street and swinging his axe.
       | 
       | If this tech has such potential to destroy humanity as we know
       | it, and it's so important to keep it in check, why did you
       | develop it in the first place?
        
         | CatWChainsaw wrote:
         | It was too exciting _not_ to do it, so they did.
         | 
         | "The Great Filter is a marshmallow test."
        
       | ConanRus wrote:
       | [dead]
        
       | [deleted]
        
       | s1mon wrote:
       | I was a bit baffled my Elon Musk's (apparent) signature on this
       | letter, as I thought he still had a connection to Open.ai. Then I
       | did some basic research and realized that this is likely just
       | jealously and frustration from his failed takeover of Open.ai.
       | 
       | https://www.theverge.com/2023/3/24/23654701/openai-elon-musk...
        
       | dahwolf wrote:
       | If you look at just the _potential_ impact of current AI or
       | slightly better ones that are around the corner...
       | 
       | If you see cognitive work as a distribution, it's not far-fetched
       | to think that it can take out the bottom half and after that ever
       | more. It's naive to think that this bottom half will become some
       | super AI coder, that's what the top half might do, or more likely
       | the top 10%.
       | 
       | Every current threat in the digital domain (misinformation,
       | polarization, cyber crime, the like) might go times a 100 or a
       | 1,000. Are we ready for that?
       | 
       | Unique human values such as creativity and simply just
       | communication are on the chopping block too. Is it worth it? What
       | remain of us? Biological prompters? Why not link it to our actual
       | brain then to complete the Matrix scenario.
       | 
       | What happens to truth? Or culture? Does it matter anymore? What
       | about one private company being in charge of such nuclear
       | scenarios?
       | 
       | We're talking existential impact here. This is like dropping a
       | nuke without knowing what a nuke is or what it does.
       | 
       | It's pathetic that private individuals have to write this letter.
       | Don't you think that in an exponentially disruptive world we
       | should have some kind of formal oversight? Instead of a 80 year
       | old guy asking 10 years after the blast what Wifi is?
        
       | hintymad wrote:
       | Does the letter cite any specific danger of the current LLM
       | backed by examples? I hope this is not another Gebru moment that
       | a bunch of people cite moral high ground without substance.
        
       | karmasimida wrote:
       | There is no stopping in this.
       | 
       | How to stop? No one will stop. The world won't stop or pause on
       | getting LLM more useful until it can't be further improved.
       | 
       | LLMs aren't nuclear weapons. I don't know how it could be
       | supervised TBH. The model, the data are mostly public, giving
       | people time they will definitely get there regardless.
        
       | sinuhe69 wrote:
       | The hype is immense and so the disillusion will be. Just let the
       | LLM train go and we'll see. Thanks to that, perhaps the next time
       | people will stop and think more deeply about the real issues.
       | Nobody will stop now but huge investment + economic recession is
       | a good recipe for bubble.
        
       | gedy wrote:
       | Maybe a strange take, but one silver lining to this is AI models
       | can at least capture the essence of human culture and arts in a
       | fairly compact format. Might be a good "backup" of sorts if the
       | world falls apart.
        
       | scanr wrote:
       | Cat may be out of the bag. I was wondering today whether the race
       | should be on to be creating an benevolent AI to defend humanity
       | from the less benevolent ones.
        
         | icrbow wrote:
         | If you don't know how to make one already you will be racing
         | _towards_ the precipice, not steering away from it.
        
           | scanr wrote:
           | Yeah. Pretty high stakes. If we assume that work is already
           | underway to create unaligned AIs, what's the alternative?
        
         | fknorangesite wrote:
         | And that's the beautiful part - when wintertime rolls around,
         | the gorillas simply freeze to death.
        
       | titaniumrain wrote:
       | "If I had asked people what they wanted, they would have said
       | faster horses." - HENRY FORD
       | 
       | The world moves on. Dinosaurs either die or evolve.
        
       | brokencode wrote:
       | If US companies don't advance this technology, companies in other
       | countries will. Or possibly even state actors.
       | 
       | Eventually, somebody will automate most jobs. Society will need
       | to adjust to this. Our high-minded ideals about preserving
       | fulfilling work will evaporate as soon as China makes a major
       | breakthrough.
       | 
       | I think AI technology will become the nuclear arms race of the
       | 21st century. How it turns out could be fantastically bad. But I
       | think it is inevitable.
        
       | biscottigelato wrote:
       | I think it makes sense to debate whether this pause can or cannot
       | work and the game theory behind it.
       | 
       | But to those that trivializes the potential danger of AI and
       | compare it to the likes of climate change is ignorant at best. AI
       | has been consistently ranked as the highest potential cause for
       | the extinction of the entire human race (by experts, a random
       | survey of the population will likely say climate change, sadly).
       | (https://riskfrontiers.com/insights/ranking-of-potential-caus...)
       | 
       | Human caused climate change at the worst potential possible
       | outcome would not even make a dent to the human population at a
       | multi-century time-scale. We also have a lot of solutions in
       | place for climate change that merely requires time and investment
       | for adoption. Climate change's impact to humanity is less than
       | the alarming birth rate we are seeing today (which also, we have
       | no solution for...)
       | 
       | We literally have no solution for AI Alignment, and this is with
       | a lot of smart people working on it. From Bostrom to Eliezer and
       | many others (check https://lesswrong.com). A lot of experts have
       | give up because they see no way out and is only merely thinking
       | about how should humanity end with dignity. We can't even figure
       | a way out of the prisoner dilemma on doing a 6 months pause.
       | 
       | Comparing AI Alignment with Climate Change trivializes the matter
       | and only illustrate the ignorance of the populace. Another reason
       | why we will not solve AI Alignment and will likely go extinct.
        
       | zelphirkalt wrote:
       | The thing we need last year is regulations enforcing ethical
       | behavior and transparency. What data were the models trained on?
       | Did you have permission to use that data for that purpose? Where
       | is your form, naturally working without third-party trackers, in
       | which people can request their data to be removed from the
       | training data and the learned model (hoho, that will be a
       | challenge!)? How can people check, whether their data is in the
       | training data? And so on.
        
       | quxbar wrote:
       | People have no idea what AI is, they seem to go entirely off of
       | the name. An intro course in Natural Language Processing reveals
       | that while impressive, GPT-4 is a reflection of the training
       | data. It is not conniving, it does not cause harm. The medical
       | benefits alone are staggering.
       | 
       | What we are about to do, as a self-inflicted wound, is let a lot
       | of simple algorithms make real decisions as cover for plain human
       | cruelty. The software platforms landlords are using to
       | collectively raise rents are already an obvious example.
        
       | Havoc wrote:
       | And I'd like world hunger to be ended. Frankly my wish seems more
       | plausible.
        
         | permo-w wrote:
         | yes so let's not bother trying to stop an existential threat.
         | have you considered the possible consequences of all this?
        
           | bloppe wrote:
           | Very hard to say how threatening AI really is. We need more
           | research to determine that. Even if it is an existential
           | threat, a moratorium will not make it go away. That's why we
           | still have nukes.
        
             | permo-w wrote:
             | it really is not hard to say. have you played around with
             | the technology? have you sat down and thought about it
             | yourself?
             | 
             | what we have is a continuously improving system that can
             | write code and solve problems with intent, and is starting
             | to have access to the internet. I don't think AI is
             | inherently evil or will do anything harmful on its own, but
             | it is a tool that humans will use to harm each other,
             | deliberately or otherwise.
             | 
             | if you need research, go and read some of the myriad
             | science fiction on the topic, or just imagine an "intention
             | bot", where you set up an LLM with a goal, then have it
             | iteratively write and execute programs to attain that goal.
             | 
             | also there undoubtedly is research on the topic, but I
             | don't need to read it to know that completely controllable
             | brains with access to the internet, that don't get tired or
             | bored or have to sleep or eat are an extremely dangerous
             | thing
        
               | wilsonnb3 wrote:
               | > if you need research, go and read some of the myriad
               | science fiction on the topic
               | 
               | the problem is exactly this - people who can't
               | distinguish between science fiction and reality.
        
               | permo-w wrote:
               | the problem is exactly this - people who can't understand
               | subtlety or context
        
       | layer8 wrote:
       | The signatories will be on the basilisk's death list for sure.
        
       | juancn wrote:
       | Stopping now would be extremely dangerous and borderline stupid.
       | 
       | If you stop now, you're just left behind, because there's no way
       | everyone will stop.
       | 
       | At this point the only logical course of action in an adversarial
       | situation is to double down and keep researching, otherwise some
       | other country or culture with different (and possibly worse)
       | values ends up dominating the technology and you're left behind
       | in the dust.
       | 
       | The genie is out of the bottle, there's not putting it back in.
        
         | reasonableklout wrote:
         | I don't agree at all. It's totally fair for rival "countries or
         | cultures with different values" to coordinate on matters that
         | threaten everyone's survival. There are many examples of
         | international agreements on technologies that fit this
         | description. For example:
         | 
         | - International treaties to avoid nuclear proliferation and
         | development, as other commenters have pointed out
         | 
         | - National moratoriums on gain-of-function research
         | 
         | - Regulations on biotechnology related to human cloning and
         | human gene editing, and industry/academic norms set by
         | conferences such as the Asilomar conference
         | 
         | - International treaties on climate change, such as the
         | Montreal Protocol on CFCs and the hole in the ozone layer
         | 
         | Even if we assume that international coordination fails, 2
         | facts give us some breathing room to pause (not stop!) large
         | experiments to at least figure out what we're doing and how to
         | adapt society:
         | 
         | 1. American companies are ahead of Chinese companies (I assume
         | that's what you mean by "other country or culture") right now
         | by at least a few years. The rest of the industry is barely
         | catching up to GPT-3 , which came out in 2020.
         | 
         | 2. China cannot unilaterally continue the race right now
         | because their compute supply chain critically depends on
         | technologies that the West has monopolies over, like sub-10nm
         | silicon fabrication, advanced GPU technologies, and ultraviolet
         | lithography. We're already using this lever, actually! For
         | example, Nvidia exports of A100 and H100 GPUs are no longer
         | allowed to China at scale.
        
           | mritchie712 wrote:
           | it's orders of magnitude easier to regulate and observe large
           | scale nuclear projects then thousands of hackers spread all
           | over globe.
        
           | GartzenDeHaes wrote:
           | Nvidia chips are designed and manufactured in Taiwan, not
           | "the west."
        
           | lannisterstark wrote:
           | "International treaties to avoid nuclear proliferation and
           | development, as other commenters have pointed out"
           | 
           | ...you do realize that countries haven't signed that right,
           | and nothing stops them from pulling out either, right?
        
         | ChatGTP wrote:
         | If you have time, I really think this short segment from an
         | interview with Max Tegmark is worth a watch [1]. This
         | particular clip is about autonomous weapons.
         | 
         | It's quite relevant to your argument, interested on your
         | thoughts.
         | 
         | [1] https://www.youtube.com/watch?v=RL4j4KPwNGM
        
         | ren_engineer wrote:
         | this is basically the same logic behind nuclear weapons, and AI
         | could potentially be even more dangerous if it kept advancing
         | at the rate we've seen in the last few years. In theory the
         | massive amount of compute needed to train and run these at
         | scale could be tracked/regulated similarly to how nuclear
         | refinement facilities are
         | 
         | your suggestion is that stopping nuclear proliferation
         | shouldn't have even been attempted, despite the fact it
         | actually worked pretty well
        
           | quonn wrote:
           | But that would only buy us 10 years. Eventually that massive
           | amount won't seem very massive anymore compared to what will
           | be available in consumer devices.
        
         | nopinsight wrote:
         | They are calling for a pause, not a stop.
         | 
         | It's quite clear that OpenAI has a significant lead over
         | everyone else. The only other country outside the west that
         | even has a chance at developing something better than GPT-4
         | soon is China. China has a pretty cautious culture as well so
         | it's quite possible that a bilateral moratorium can be
         | negotiated with them.
         | 
         | ADDED: Even without considering X-risks, China's rulers cannot
         | be pleased with the job displacement risks that GPT-4 plus
         | Plugins may cause, not to mention a more powerful model.
         | 
         | They have trained a huge number of college graduates and even
         | now there are significant unemployment/underemployment issues
         | among them.
         | 
         | ADDED 2: If you think many companies can do it, please identify
         | a single company outside the US/UK/China with the capability to
         | train an equivalent of GPT-3.5 _from scratch_.
        
           | mewpmewp2 wrote:
           | If OpenAI as a start up was able to do it, certainly full
           | countries can do it if they see the evidence and will invest
           | in it.
        
           | ren_engineer wrote:
           | >It's quite clear that OpenAI has a significant lead over
           | everyone else
           | 
           | if their lead was significant they wouldn't have admitted to
           | not releasing more info about GPT-4 in their paper due to
           | commercial reasons. What ever secret sauce they have
           | apparently isn't that significant or they wouldn't be afraid
           | to talk about it
        
             | NLPaep wrote:
             | Nah, it's just easy to copy if you lay it out. It's
             | software.
        
             | nopinsight wrote:
             | Discovering Newtonian's Laws of Motion were much harder
             | than learning them from others.
             | 
             | Were Newtonian's Laws of Motion a significant progress?
        
           | credit_guy wrote:
           | > The only other country
           | 
           | OpenAI is not a country, it's a company.
           | 
           | GPT models on par with GPT-4 can be trained, well, by
           | companies. You don't need nation-state levels of resources.
        
             | zarzavat wrote:
             | Training a LLM with GPT-4 like capabilities is very hard.
             | Most AI researchers are concentrated in a few countries. At
             | the moment the countries with the vast majority of the
             | expertise are US, UK and China.
        
               | MacsHeadroom wrote:
               | It's not remotely intellectually challenging to replicate
               | GPT-4. It just takes a lot of GPUs, something plenty of
               | people all around the world have access to.
               | 
               | GPT-2 and GPT-3 are the same algorithm based on the same
               | open source library. GPT-4 most likely is as well. You
               | can literally fork the repo and if you have enough VRAM,
               | cuda cores, and time, you will get GPT-4. High Schoolers
               | could do it. Amateurs are already replicating LLaMA,
               | which is more complex than GPT and not even a month old.
               | (it's just smaller = fewer GPUs required)
        
               | mirker wrote:
               | You didn't mention how to gather high quality data.
               | OpenAI has never and will never release that.
        
           | og_kalu wrote:
           | If you counted research, open ai didn't have a lead until
           | gpt-4 nevermind a significant one. most of this is scale.
           | their lead is a few months tops.
        
             | nopinsight wrote:
             | Engineering such a system is a harder challenge than many
             | types of research. Even the mighty Google, the leader in AI
             | research by many metrics, is catching up.
             | 
             | Another example is Meta only finishing OPT-175B, a near
             | equivalent of GPT-3, two years after it.
             | 
             | ----
             | 
             | Added to reply:
             | 
             | GPT-4 got much better results on many benchmarks than PaLM,
             | Google's largest published model [1]. PaLM itself is
             | probably quite a bit better than LamDa in several tasks,
             | according to a chart and a couple of tables here:
             | https://arxiv.org/abs/2204.02311
             | 
             | It's unclear that Google currently has an internal LLM as
             | good as GPT-4. If they do, they are keeping quiet about it,
             | which seems quite unlikely given the repercussions.
             | 
             | [1] GPT-4's benchmark results vs PaLM:
             | https://openai.com/research/gpt-4
        
               | og_kalu wrote:
               | Google was not catching up before gpt-4. That's my point
               | lol. all the sota llms belonged to google via deepmind
               | and google brain/ai right up to the release of gpt-4.
               | chinchilla, flamingo, flan-palm.
        
               | nopinsight wrote:
               | GPT-4 was finished in the summer of 2022. Several
               | insiders gave interviews saying they were using it and
               | building guardrails for it for the last 6 months or so.
               | 
               | OpenAI doesn't publish as much as Google so we don't
               | really know how long or in what periods they were ahead.
               | 
               | And there's no organization outside the US/UK/China with
               | the same caliber of AI engineering output as Google.
        
         | winternett wrote:
         | They need to stop testing in PROD, and they also need to prove
         | that Ai can function without an Internet connection and without
         | any human intervention at all... Ai should not be deployed
         | deeply until it works more flawlessly, but the same people who
         | hyped and foisted Crypto onto everything and everyone
         | (Including vital world banking infrastructure) are at the wheel
         | on Ai marketing now, and that's not good at all.
         | 
         | Those things, as well as vital testing as a gate for
         | deployment, aren't being upheld, and that's exactly what makes
         | promises grandiosely destructive and keeps outcomes harmfully
         | and wildly unpredictable.
         | 
         | I think in months to come we'll find out that many of the great
         | new Ai products launched will prove themselves to simply be
         | inauthentic-ly scripted fraud-based solutions backed by hidden
         | human intervention because of this environment of unchecked
         | expansion and eager over-deployment.
        
       | vasili111 wrote:
       | If US will pause AI, rest of the world will not. US business will
       | be in disadvantage. US cannot give a lead in such important
       | technology to other countries.
        
       | jl6 wrote:
       | All they need is for Gerard Butler to sign the letter and our
       | course of action will be clear.
        
       | randomwalker wrote:
       | Rebuttal: https://aisnakeoil.substack.com/p/a-misleading-open-
       | letter-a...
       | 
       | Summary: misinfo, labor impact, and safety are real dangers of
       | LLMs. But in each case the letter invokes speculative, futuristic
       | risks, ignoring the version of each problem that's already
       | harming people. It distracts from the real issues and makes it
       | harder to address them.
       | 
       | The containment mindset may have worked for nuclear risk and
       | cloning but is not a good fit for generative AI. Further locking
       | down models only benefits the companies that the letter seeks to
       | regulate.
       | 
       | Besides, a big shift in the last 6 months is that model size is
       | not the primary driver of abilities: it's augmentation (LangChain
       | etc.) And GPT3-class models can now run on iPhones. The letter
       | ignores these developments. So a moratorium is ineffective at
       | best and counterproductive at worst.
        
       ___________________________________________________________________
       (page generated 2023-03-29 23:01 UTC)