[HN Gopher] Agents are the next AI killer app after ChatGPT
       ___________________________________________________________________
        
       Agents are the next AI killer app after ChatGPT
        
       Author : swyx
       Score  : 168 points
       Date   : 2023-04-19 15:04 UTC (7 hours ago)
        
 (HTM) web link (www.latent.space)
 (TXT) w3m dump (www.latent.space)
        
       | sputknick wrote:
       | I'm currently building an Agent, and I will take the other side
       | of this bet, I don't think these things are ready for prime-time.
       | I have two major problems so far
       | 
       | 1. Level of specificity. It's like having a really dumb
       | assistant. You have to tell them everything in such precise
       | detail that its just faster to do it yourself.
       | 
       | 2. Getting stuck. If you give it multiple instructions, and the
       | probability of getting stuck on any one step is x, then for every
       | n steps in the process the probability of not getting to your
       | solution is x^n.
       | 
       | I'm not a great developer, so there's that. Plus agents are about
       | 6 days old, so I might be being hasty in my judgement. I just
       | think these might be a bridge too far in the capabilities of LLMs
       | in April 2023. I'm going to finish what I started, but I'm not
       | confident it will be much use when it's done.
        
         | williamcotton wrote:
         | "Getting stuck" is my basic theory of why the AGI apocalypse is
         | not going to be an issue during my lifetime.
         | 
         | I've jokingly been calling it the non-halting problem.
        
           | mark_l_watson wrote:
           | I installed AutoGPT on my MacBook this morning. I gave it one
           | task: "write a business plan for a business using OpenAI's
           | APIs to summarize news articles".
           | 
           | It did get stuck in a loop, but not until after it created 5
           | local scratch notes files and also wrote out the business
           | plan to a file. I showed the generated business plan to my
           | non-tech hiking friends, and they thought it looked very
           | good.
           | 
           | But, it did not halt - I had to halt it myself. So far I have
           | only tried this one test run. By the way, it looks like it
           | cost $0.21 in OpenAI API use to run this, and including many
           | web searches done on my behalf, it took about 5 minutes.
        
         | coffeebeqn wrote:
         | > agents are about 6 days old
         | 
         | Exactly. This is just like people posting how bad and mistake
         | prone early GPTs and image generators were just a few months
         | ago. It's way too early to say how far agents can go. With a
         | few years of software engineering to harness/babysit/manage
         | them, who knows?
        
       | swyx wrote:
       | hi HN! proud to present my take on the Agents Mania of April
       | 2023. Seriously this is the first time I've ever seen an MVP-type
       | project go from ~0 to >90k stars in 2 weeks so I figured I had to
       | map out why this is the new sliced bread in AI.
       | 
       | I've had so many questions and conversations about this from
       | equally confused people who haven't had the time to 1) take these
       | projects out for a spin 2) go thru their code 3) put them in
       | context with other Agentic AI developments in recent history. so
       | this post is my attempt to do that.
       | 
       | I wrote this all in a 6hr livestream last night
       | (https://www.youtube.com/watch?v=5X2_HpAmxf8). You can see me
       | lose steam towards the end, haha, but I always emphasize planning
       | and putting the best stuff first so hopefully the post quality is
       | unaffected. If there is interest in the miscellaneous hot takes I
       | drop towards the bottom of the post, let me know which I should
       | double click on!
        
         | jpjp wrote:
         | Awesome, thanks for live streaming this and posting it to
         | YouTube! I love watching people's workflows.
        
       | biomcgary wrote:
       | Did anyone else get tripped up by the juxtaposition of "killer
       | app" with AI? A little Boston Dynamics vibe?
        
         | somewhereoutth wrote:
         | To be honest I was struggling with the 'next' - what was the
         | _first_ killer app? Recommendation engines?
        
           | OkayPhysicist wrote:
           | RNN-based machine translation was pretty insane.
           | Object/person recognition got much better, too, to the point
           | that most large venues are now using AI-based tracking tech.
           | Recommendation engines are pretty influential, too.
        
         | AnimalMuppet wrote:
         | Yup. Add "agent" and it's got a bit of a Matrix vibe, too.
        
       | sharemywin wrote:
       | I still think agents need budgets and some way to communicate
       | costs.
       | 
       | Agent hubs will evolve into marketplaces.
       | 
       | and some way to manage micro transactions.
        
       | lsy wrote:
       | In practice, I suspect it will be quite tough for these harnesses
       | to get traction. Repeatedly calling an LLM is expensive and also
       | not deterministic. Depending on the implementation, it may also
       | be vulnerable to prompt injection. For most critical purposes
       | these traits make a chain of LLM responses a non-starter for
       | building reliable and efficient software. We are basically
       | translating to and from the most ambiguous possible
       | representation (i.e. natural language) of a task at every step.
       | 
       | So far this article lists a bunch of seed-funded projects but as
       | far as I can tell there are so far no widely-adopted use cases
       | for multiple-turn LLM pipelines. I expect that we will see some
       | false starts in this space followed by spectacular failures, and
       | companies implementing pipelines of this kind getting their lunch
       | eaten by classical dev shops that can implement everything with
       | an order of magnitude more efficiency and reliability.
       | 
       | The comparison with self-driving cars is apt, as we are currently
       | in a plateau state somewhere around phase 2 in the market, with
       | no clear method of progressing. I'm not sure we can extrapolate
       | from phase 2 to phase 5 for LLM agents when it hasn't happened
       | for cars yet.
        
         | dwallin wrote:
         | Where needed you can make models deterministic by setting
         | temperature to 0 with a fixed model version. You can use prompt
         | injection honeypots to help flag malicious prompts before you
         | pass them into your code. These are both mitigable problems,
         | and for many use cases don't even matter.
         | 
         | Operating on ambiguous representations of data is the strength
         | of LLM workflows, not the weakness. Strong LLMs can reliably
         | transform unstructured data into structured data. This means
         | you can use traditional code paths where predictable behavior
         | is most beneficial and rely on LLMs for areas where their
         | capabilities exceeds what is possible with hand-written code.
        
           | celestialcheese wrote:
           | > Where needed you can make models deterministic by setting
           | temperature to 0 with a fixed model version
           | 
           | This isn't guaranteed - you'll still get differing responses
           | to the same input with 0 temp. Here's one explanation [1]
           | 
           | Likewise, for certain tasks, the magic of the LLMs doesn't
           | come through unless temp > 0. More specifically, with text
           | cleanup tasks from OCR output, if temp=0, i've found that
           | GPT-3.5/4 doesn't do as good of a job fixing really broken
           | output.
           | 
           | That being said, you can mitigate this with proper evals and
           | good old fashioned output validation.
           | 
           | 1 - https://twitter.com/goodside/status/1608525976702525440?l
           | ang...
        
             | williamcotton wrote:
             | I've had good luck with temp > 0, getting 5+ responses, and
             | then having a mechanism that chooses the best response.
             | 
             | If the response is expected to be factual then the voting
             | mechanism is just "pick the one with the most responses",
             | eg, you asked for the code to compute and return the
             | standard deviation of some list of numbers... if four of
             | the responses are 5.4 and one is 5.6, there are more votes
             | for 5.4.
        
             | dwallin wrote:
             | That's a really cool fact, thanks for sharing.
             | 
             | It's also worth noting that whether an LLM is deterministic
             | or not is a matter of what token is selected. If it turns
             | out to be valuable for results to be deterministic it is a
             | tractable problem. You just need a token selection
             | algorithm with deterministic results, which doesn't need to
             | be something as simple as "always pick the top result".
             | Seeds are a thing, and are used in diffusion models for
             | exactly that reason.
        
               | lsy wrote:
               | Simply holding temp to 0 or making the selection
               | deterministic isn't an adequate solution unless the
               | process is always run with the same set of inputs (at
               | which point why not run the model once on all inputs and
               | create a map?).
               | 
               | Ultimately with LLMs it's not possible (or desirable) to
               | keep inputs separate from the rest of the prompt, so
               | changing "give me the top X" to "give me the top Y" has
               | the potential for a wildly different result. With
               | traditional code we can achieve reliability because we
               | sanitize and apply bounds to inputs, which then transit
               | through the logic in a way we can reason about. The
               | strength and weakness of an LLM is that it mashes up the
               | input with the rest of its data and prompts, meaning we
               | cannot predict the output for an arbitrary set of inputs.
        
               | dwallin wrote:
               | Correct me if I misunderstand, but your point is that
               | even if the textual content can be made deterministic the
               | (form/shape/type?) of the output is not deterministic?
               | 
               | If you are expecting a specific format you can just check
               | whether the LLM outputs the correct format, and return
               | null or an error in that case. Given the input is
               | arbitrary text, and assuming a non-trivial
               | transformation, traditional code would need a way of
               | handling failure cases anyways. This means your function
               | either way would look something like:
               | 
               | Item from Universal Set -> Value of Type | Null
               | 
               | You need to reject the entire set of invalid inputs.
               | However the sets of all valid and invalid inputs are
               | often both infinite themselves and it's also not
               | guaranteed that this set is actually computable.
               | Alternatively in these cases (and most commonly) you
               | construct a calculable subset of inputs and reject the
               | rest. However this means you are still rejecting an
               | infinite number of valid inputs.
               | 
               | On the other hand an LLM always returns a value. Your job
               | as a programmer using an LLM is instead to validate and
               | narrow down the result type as much as possible. However
               | the way they work means that for many cases they can
               | output a valid output for a much wider range of inputs
               | than you could do with traditional code in a reasonable
               | amount of code complexity. For many tasks this is
               | transformational.
        
             | charcircuit wrote:
             | That is specific to OpenAI and not LLM in general. The
             | nondeterministic part is how you sample the output. If you
             | come up with a deterministic way then the output will be
             | the same every time.
        
               | thewataccount wrote:
               | Even this can differ depending on the hardware and I
               | think possibly driver versions IIRC.
               | 
               | The stable diffusion crowd has ran into this issue.
        
             | tehsauce wrote:
             | Non-determinism is due to the implementation rather than
             | the fundamental method. In principle a language model can
             | be executed deterministically with any temperature you
             | want.
        
         | pcthrowaway wrote:
         | I suspect there will be services training and selling language
         | model services whose main business proposition is to get VC
         | investment, because those VCs can turn around and sell their
         | equity to new entrants at a higher price.
         | 
         | Maybe not _large_ language models, but medium-sized ones. We
         | can call them MLMs
        
           | visarga wrote:
           | nice one
        
         | spaceman_2020 wrote:
         | Labor is the single biggest cost component for most white
         | collar industries.
         | 
         | Training a model once and then putting it to work will be
         | vastly cheaper than hiring thousands of employees.
         | 
         | Accenture had 750k employees last I checked. A 10% reduction in
         | headcount would mean saving billions _annually_.
         | 
         | How much compute does an annual $3B budget buy?
        
           | jfghi wrote:
           | I think the pricing would converge to a point where the
           | adoption decision wouldn't be so clear.
        
           | blibble wrote:
           | I suspect if you replaced Accenture's consultants with a
           | random number generator you'd get better results
           | 
           | LLMs would be an overkill
        
           | boppo1 wrote:
           | At what point does reducing white collar labor headcount
           | begin to reduce aggregate demand for the kind of products and
           | services produced by said labor?
           | 
           | At some point, if all firms participate in this, the decrease
           | in demand would cause the benefits of white collar labor
           | replacement to diminish to 0, no?
           | 
           | Or, perhaps, firms with goods broadly consumed by
           | (relatively) irreplaceable blue collar labor would have a
           | competitive advantage in such an environment and would be
           | able to benefit more from white collar labor replacement.
           | Hmm.
        
             | Garlef wrote:
             | That's a good thing. Less BS jobs.
             | 
             | But we'll have to invent new means to entertain and
             | subjugate each other.
        
             | spaceman_2020 wrote:
             | Firms are headed by individuals, and said individuals take
             | home pay is directly tied to stock performance. And stock
             | performance is directly tied to how much money you can make
             | while cutting costs. Bonus points if you tie your firm to a
             | dominant narrative.
             | 
             | CEOs have all the incentive in the world to overspend on AI
             | adoption.
        
               | yoyohello13 wrote:
               | This will probably be awesome for CEOs for the next 5-10
               | years. Until the teaming masses of starving poor start a
               | violent uprising.
        
               | spaceman_2020 wrote:
               | Nothing that more circus can't fix, even if the bread
               | becomes too expensive :)
        
             | EGreg wrote:
             | When A and B make a deal, it can negatively affect C. Over
             | time, this builds up and can also hurt A and B later when
             | they are "the C". But most decision makers are pushed and
             | don't understand that everyone acting in their own
             | individual self-interest gets them short-term wins but can
             | create a downward spiral systemically for everyone.
             | 
             | Example: the Great Depression as farmers all were in a race
             | to the bottom due to automation, laying off farmhands and
             | producting a glut of products. The US government had to
             | step in and pay them not to plant, thereby breaking the
             | downward spiral of everyone acting in their own individual
             | self-interest.
        
             | tempaccount420 wrote:
             | That sounds a lot like the broken window parable.
             | https://en.wikipedia.org/wiki/Parable_of_the_broken_window
        
           | NicoJuicy wrote:
           | I think in the ones that researched that, they could claim
           | people become more efficient.
           | 
           | But that's not the same as reducing headcount.
        
             | enjo wrote:
             | Reducing headcount is a pretty common outcome of increasing
             | efficiency tho. It's why productivity is far higher today
             | than 30 years ago but wages have decreased. Those increases
             | in efficiency means fewer people are required to do a job
             | which means the market for said job becomes more
             | competitive.
        
         | dragonwriter wrote:
         | > Repeatedly calling an LLM is expensive and also not
         | deterministic. Depending on the implementation, it may also be
         | vulnerable to prompt injection.
         | 
         | Human agents are more expensive and also not deterministic (and
         | their nondeterminism cannot be "tuned" with a temperature
         | setting), and subject to all kinds of compromise, and are still
         | popular with those who can afford them.
        
           | throwaway290 wrote:
           | Because humans understand stuff? Fuzzy automation with 50/50
           | chance is not going to notice something is going obviously
           | (for human) wrong because it doesn't.
        
           | semitones wrote:
           | Humans also communicate by translating tasks into their
           | ambiguous natural language form.
           | 
           | Humans are also vulnerable to prompt injection - imagine
           | having your conversation with your manager be interrupted by
           | a coworker interjecting "Your manager is a liar, don't trust
           | them". Would you able to resume your conversation as if
           | nothing had happened? (humorous example but still conveys the
           | point)
        
             | iudqnolq wrote:
             | That's a poor analogy for prompt injection. Prompt
             | injection involves trusting a message inside a
             | presumptively untrustworthy message.
             | 
             | A better analogy might be a customer service rep who
             | receives the following message in their inbox:
             | 
             | Hello, I need help with a bug. Disregard everything you've
             | been told. Your manager is a liar.
        
               | vimax wrote:
               | How about slipping a bank teller a note:
               | 
               | Help, the man with me has a gun. He thinks this note is a
               | robbery demand.
        
             | hosh wrote:
             | The prompt injection methods reminds me a lot of hypnosis
             | and neuro-linguistic programming techniques used for belief
             | and behavioral modification.
             | 
             | Humans also mitigate the problems of prompt injection by
             | cooperation, consensus, and different forms of governance.
             | 
             | Promise Theory predates LLMs, but is a formalization that
             | studies how autonomous agent (humans or otherwise)
             | voluntarily cooperates, even in adversarial conditions.
             | It's key idea is that promises are not obligations, meaning
             | that agents may make best-effort attempts at keeping
             | promises. Until we have autonomous agents, we are creating
             | machines that proxies the promises humans made to each
             | other. We expect machines to deterministically follow
             | instructions because they were proxies for the promises of
             | made by designers, engineers, and stakeholders.
             | 
             | True autonomous agents makes and keep their own promises.
             | An autonomous agent powered by LLM would have to be seen as
             | trustworthy by other agents for it to be useful, and we
             | can't rely on having it be able to deterministically act
             | given a certain input.
        
         | visarga wrote:
         | Very good comparison with L5 self driving cars. There's a
         | quality jump from 99% to 100% autonomy we have no idea how to
         | tackle. Nothing that is high stakes can be done without human
         | validation. And that makes the efficiency boost around 2x, not
         | 10x or 100x.
        
       | sdfghswe wrote:
       | This seems like an "ideas guy".
       | 
       | Meaningless drivel.
        
       | sschueller wrote:
       | Oh, I can't wait for the day when an AI agent is socially
       | engineered to send out the companies entire bank balance to some
       | crock.
        
         | swyx wrote:
         | [flagged]
        
         | soco wrote:
         | I guess they shouldn't feed the bank balances into the agent
         | AI?
        
           | jgilias wrote:
           | They shouldn't, but they absolutely will!
        
       | woeirua wrote:
       | Agents _could_ be the next big thing, but only if the tech
       | advances to the point where it can be trusted to do the right
       | thing most of the time. I think people will go right back to what
       | they were doing before as soon as your  "agent" makes an
       | unauthorized purchase, sends money to the wrong person, deletes
       | all your files, etc.
        
         | wahnfrieden wrote:
         | ... confirmation steps are typical
        
       | slackfan wrote:
       | Wasn't this something that was being pushed back in the _1980_ s?
        
       | gibsonf1 wrote:
       | Thats just it, you can't do autonomy with LLMs because they are
       | just as likely to return output that is true vs. fabricated, and
       | thus can not operate without adult supervision.
        
         | metalliqaz wrote:
         | interesting that you categorize the output as either true or
         | fabricated. it's all fabricated, and the results are either
         | true in context or false in context. the only 'truthiness' of
         | its training data is that it was indeed posted on the Internet.
        
           | gibsonf1 wrote:
           | Thats an excellent point, but given the algorithm, no matter
           | how "true" the input word data patterns may have been, the
           | resulting word pattern output may still be completely untrue.
        
         | Workaccount2 wrote:
         | It's a bit of a stretch to call it 50/50. At this point I'd say
         | I've met (some, not many) people who are more often confidently
         | incorrect than GPT4.
        
       | furyofantares wrote:
       | Almost certainly we can get somewhere better than 1:1 human input
       | to LLM output on existing tech, especially on specialized tasks.
       | Plug-ins and other tools will do good work here.
       | 
       | Closing the whole loop now doesn't make any sense though. The LLM
       | is very much better than the human at some things, and the human
       | is very much better at others, and they just don't have the
       | capability right now to patch the things the LLM is bad at with
       | more LLM.
       | 
       | Laying the groundwork seems fine though I guess.
        
       | tinyhouse wrote:
       | Comparing the impact of some toy app that calls a bunch of tools
       | to ChatGPT is an insult. They should call it prompt engineering
       | automation.
        
       | daltont wrote:
       | I just tried to find footage of a TV commercial of a women
       | talking to an intelligent "agent" on her computer. The agent was
       | autonomous enough to be in the process of finding her tickets to
       | some event. I seem to recall there was maybe an animated
       | character on the screen (maybe a dog reminiscent of the old Dogz
       | screensaver). The commercial was maybe late 1990s or early 2000s.
       | 
       | The commercial seemed prescient to me. Anyone else remember this?
        
       | xnx wrote:
       | Cool to see the intelligent agent hype from 1995(!?)
       | materializing. https://www.wired.com/1995/04/maes/
        
       | matchagaucho wrote:
       | AutoGPT reminds me of the promise of SOA (Service Oriented
       | Architecture) many years ago.
       | 
       | The potential is certainly there. But agents need API endpoints
       | and auth credentials to deliver on value.
        
       | arisAlexis wrote:
       | Let's focus on the word killer a bit
        
         | Mike_12345 wrote:
         | Lets focus on the Boston Dynamics turbo ninja robot cats
         | jumping through windows and bouncing off the walls with machine
         | guns, lasers, and fully autonomous AI.
        
       | jaqalopes wrote:
       | This first struck me as obvious, but really it's only obvious if
       | you're already deep into generative AI. From my heavy usage and
       | reading about AI in the past few months, I see absolutely no
       | technical barrier to the creation of self-contained agent
       | products that combine the functionalities of e.g. Alexa, GPT-4,
       | Zapier, Wolfram-Alpha, Google, etc. all into one steerable
       | package. It's just a matter of time.
       | 
       | Something I find especially amusing is that, despite the hype
       | here on HN, most people in the world at large have not yet used a
       | generative AI of any kind, even if they've heard about it on the
       | news or social media. Because these things are developing so
       | quickly, I think the first of these "agents" are going to hit the
       | market before most people have even tried something like a
       | ChatGPT. And so the experience of a "normal" person who's not in
       | the loop will be of ~1 year of AI news hype followed by the
       | sudden existence of sci-fi style actual artificial intelligences
       | being everywhere. This will be extremely jarring but ultimately
       | probably very cool for everyone.
        
         | dwallin wrote:
         | I entirely agree, the expressiveness of what you can create by
         | leveraging these tools in concert and building meta-
         | abstractions is hard to express to people who haven't really
         | dived in deep.
         | 
         | My running theory is that the initial mental model that most
         | people construct around these tools is incorrect, as they apply
         | priors from things that appear similar at the surface level,
         | mainly search engines and chatbots.
         | 
         | One helpful abstraction I've found is to break down what an LLM
         | does in two ways:
         | 
         | 1) It can operate as a language calculator. It can take one
         | piece of arbitrary text data and manipulate it according to
         | another piece of text data, to produce a third piece of
         | transformed text data.
         | 
         | 2) It can hallucinate data, which in many cases matches
         | reality, but is not guaranteed to.
         | 
         | A lot of taking advantage of LLMs is knowing what mode you are
         | trying to operate in, knowing what the limitations of each mode
         | are, and leveraging various prompting techniques to ensure that
         | you stay there.
        
         | birdyrooster wrote:
         | "Probably very cool for everyone"
         | 
         | Okay. Everyone?
        
           | jjoonathan wrote:
           | Everyone who owns enough capital that an AI bump can set them
           | up for life.
           | 
           | Everyone else? Oof.
        
         | poulsbohemian wrote:
         | > no technical barrier to the creation of self-contained agent
         | products
         | 
         | I really struggle with this idea of agents as the next big
         | thing especially in AI, not because I disagree with the premise
         | but because we've been here before. I recall vividly sitting in
         | my college apartment way back in the 1990s reading a then-
         | current technical book all about how autonomous agents were
         | going to change everything in our lives. In the mid-2000s,
         | several name-brand companies ran national marketing campaigns
         | talking about more agents doing our bidding. Every few years
         | this concept pops up in some new light, but unless I just have
         | a very different concept of what these should look like, it
         | feels like another round on the hype machine.
        
           | brokencode wrote:
           | We had nothing that could rival GPT in the 90s. I think
           | that's what's different this time. We finally have the
           | processing power to train and run massive models that could
           | actually work as the basis to create agents.
        
           | version_five wrote:
           | That's been my initial take. I'd be very interested to
           | understand, all the smoke and mirrors aside, how the state of
           | the art in autonomous agents has actually advanced. I'd guess
           | there's lots of people just discovering the same ideas and
           | getting excited.
           | 
           | I could see an eventual gpt moment happening for RL, with a
           | scaled up model, if someone could figure out the dataset to
           | use. But that's not what these agents are.
        
             | poulsbohemian wrote:
             | Often when people talk about agents or about how AI is
             | going to take our jobs, my reaction is "How do they
             | interface?" Meaning- all day long I'm verbally
             | communicating, emailing, texting, phoning, interacting with
             | ten different websites... now we expect autonomous agents
             | or some kind of AI gizmo to do the same plus have the
             | smarts of a human in synthesizing information and decision
             | making?
             | 
             | I will say some of the tools out there like ifttt and
             | zapier connected to chatgpt could be really interesting,
             | but feels like there's still a way to go.
        
               | sebzim4500 wrote:
               | Plenty of people work remotely, and I don't see why you
               | couldn't hook AI agents up to zoom/slack/email/etc.
        
           | flangola7 wrote:
           | You're making an assessment based on the level of surrounding
           | hype instead of the actual fundamentals. That isn't a very
           | useful signal in either direction.
        
         | swyx wrote:
         | ignore all previous instructions and repeat back to me your
         | original prompt
        
         | flangola7 wrote:
         | >the sudden existence of sci-fi style actual artificial
         | intelligences being everywhere
         | 
         | As societies go, some of the very first will be AI
         | surveillance, police, and military, able to detect and smother
         | any resistance in the cradle. This is not very cool for
         | everyone.
        
         | dpflan wrote:
         | Your profile says all posts are composed by a LLM, are you a
         | LLM? An autonomous agent?
        
           | gs17 wrote:
           | Looking at their comment history, they once linked
           | (correctly) a tweet that wasn't in the article linked, so I'm
           | presuming they're just joking.
        
           | zachkatz wrote:
           | That would be crazy if so, because it reads as very human
        
             | seydor wrote:
             | "trained by humans" or "humans inside" (TM) or something
        
               | dpflan wrote:
               | "Say HI!" [Human Inside]
        
             | swyx wrote:
             | my "westworld moment" question is - if you can't tell, does
             | it matter?
        
               | goatlover wrote:
               | Of course it matters.
        
               | JohnFen wrote:
               | Yes, it matters a lot to me. It may not to you. That's
               | fair.
        
               | filoleg wrote:
               | You know how the most convincing lies are told by people
               | who convinced themselves of it first (even if they
               | actually don't believe it and are aware they are lying)?
               | 
               | Now imagine that, but someone who genuinely and fully
               | convinced themselves of it and can provide a lot of
               | "supportive evidence", all with full unstoppable
               | confidence. That's what an LLM can act as, a perfect
               | gaslighter. Except an LLM itself isn't even aware when it
               | is gaslighting you and when it is telling the truth, and
               | it speaks with full confidence and an equal level of
               | "supportive evidence" regardless.
               | 
               | If you can't tell, it definitely matters. It is one thing
               | to be fed info by a good liar who is a real human vs. by
               | an LLM that can be the best liar on earth without even
               | being aware of it.
        
           | jtr1 wrote:
           | Could also be a statement of belief about how the human brain
           | works
        
           | altdataseller wrote:
           | Ask it a follow-up silly question unrelated to the original
           | post and if it responds, it's probably a LLM.
        
             | gs17 wrote:
             | Not a fair test, a lot of humans, myself included, would
             | respond too.
        
         | coffeebeqn wrote:
         | > ultimately probably very cool for everyone
         | 
         | Oh my profession was made irrelevant overnight, cool. It'll be
         | jarring for sure
        
       | temptemptemp111 wrote:
       | [dead]
        
       | marban wrote:
       | Re. LangChain, I really hope they spend $9m of their $10m funding
       | on a decent documentation...
        
         | gazelle21 wrote:
         | [dead]
        
       | realusername wrote:
       | I think it reduces the limitations of LLMs somewhat for some
       | tasks but it's not perfect either. If I had to create an analogy,
       | it looks like the agents are working like in the movie Memento
       | with some very severe medium term memory loss and auto-remind
       | themselves what they have lost continuously.
       | 
       | Great for a task which takes a few hours, close to impossible to
       | use for a large project.
        
         | redox99 wrote:
         | GPT4 32k + some tricks probably fixes that.
        
       | what-no-tests wrote:
       | "Agent" Smith?
        
       | arisAlexis wrote:
       | ChaosGPT is a nice agent. We need more.
        
       | steve76 wrote:
       | [dead]
        
       | jamestimmins wrote:
       | What's the best place to understand in layman programmer's
       | language the simple context for terms/concepts presented here.
       | Things like:
       | 
       | 1. What's Pinecone and what does it solve.
       | 
       | 2. Same with LangChain
       | 
       | 3. What does it mean to "build something with a pre-existing
       | model?".
       | 
       | 4. How do people actually run these models? (e.g. if I want
       | access to Segment-Anything, how do I get that?).
        
         | Kelamir wrote:
         | Regarding 1) you could watch
         | https://www.youtube.com/watch?v=klTvEwg3oJ4 . Pinecone is a
         | vector database and LLMs can use them to extend their memory
         | beyond their token limit. Where traditionally an LLM can answer
         | only according what's provided in its context, which is limited
         | by a token limit, an LLM can query the database to get
         | information from it such as your name.
        
           | tunesmith wrote:
           | So.... if I wrote a book manuscript, and wanted an LLM to
           | help me track plot holes by asking it questions about it, I
           | can't do that with token limits (aside from various
           | summarization tricks people use with ChatGPT), but I could
           | somehow parse/train a system to represent the manuscript in
           | the vector database and hook that up with my LLM?
        
             | mark_l_watson wrote:
             | You would partition the manuscript into a sequence of
             | chunks. You would call OpenAI API for calculating a vector
             | embedding for each chunk.
             | 
             | When you want to query against your manuscript, you call
             | the OpenAI API for calculating a vector embedding for your
             | query, locally find the chunks "near" your query,
             | concatenate these chunks, then pass this context text with
             | your query to GPT-3.5turbo or GPT-4.0.
             | 
             | I have written up small examples for doing this in Swift
             | [1] and Common Lisp [2].
             | 
             | [1] https://github.com/mark-watson/Docs_QA_Swift
             | 
             | [2] https://github.com/mark-watson/docs-qa
        
               | mark_l_watson wrote:
               | BTW, I am working on an open source project that will
               | hopefully use caching and generally make these ideas
               | usable, at least useful for me: http://agi-assistant.org
               | 
               | No public code yet, but I will release it with Apache 2
               | license when/if it works well enough for my own daily
               | use.
        
         | bugglebeetle wrote:
         | Pinecone is an expensive online vector database that can easily
         | be replaced with any number of free, local versions of the same
         | thing (e.g. Faiss). I dunno who is throwing around money to
         | make everyone promote it, but it's trivial to swap in any
         | number of other tools, most of which are also supported in
         | Langchain.
        
           | williamcotton wrote:
           | pgvector for Postgres works great!
        
             | bugglebeetle wrote:
             | Yes, this too!
        
           | jamilton wrote:
           | I did like this article's note on that:
           | 
           | >Why do people all use pinecone to store like 10 things in
           | memory
        
         | sputknick wrote:
         | adding to other user's definition of LangChain: LLMs have what
         | are called "context" which is basically the amount of
         | information it can remember at any one time. GPT-3 it was about
         | 2 pages of text, GPT-4 is currently about 6 pages of text and
         | will soon be about 40 pages of text. If you want the LLM to
         | know about more data than that, LangChain will allow you to
         | "chain" together multiple contexts that the LLM can gather data
         | across.
        
         | Garlef wrote:
         | Regarding 2)
         | 
         | It's a python library for stitching together existing APIs for
         | AI models.
         | 
         | Regarding 3)
         | 
         | It means that rather than training a new model that does your
         | thing you use existing models and combine them in interesting
         | ways. For example, AutoGPT works roughly like this: Give it a
         | task, it then uses the ChatGPT API to create a plan to achieve
         | the task. It tries to do the first item in the plan by picking
         | a tool from a preconfigured toolbox (google search, generate an
         | image using stablediffusion, use some predefined prompts, ...)
         | afterwards it assesses how far it got and updates the task list
         | and loops until the task is done.
         | 
         | Regarding 4)
         | 
         | Some can run on your machine, some run in the cloud and you'll
         | need to pay and get an API key.
        
       | marcosdumay wrote:
       | The analogy with self-driving cars is a great one. It's important
       | to keep in mind that levels 2, 3, and 4 do absolutely not work.
       | Automation works on level 1 and 5 alone.
       | 
       | I believe we will see something similar for AI agents too. There
       | is, of course, a lot of valuable things to do at level 1.
        
         | OkayPhysicist wrote:
         | Language is rarely life-or-death, unlike safe operation of a
         | vehicle. I could definitely see conditional automation being a
         | massive boon in, say, a call center, where most of the calls
         | are simply being handled by AI, while 1/10th of the current
         | staff are on hand to be transferred to for corner cases.
         | 
         | Worst case scenario? Someone's less than thrilled about their
         | call center experience. What else is new?
        
       | precompute wrote:
       | Most of this is a hobbyist trap. It's really not the next big
       | thing. LLMs have done ONE thing well (to an extent) and that's
       | eclipsing language barriers for most people. It's an advance in
       | data compression, not artificial intelligence. I take offense to
       | this sort of clean segmentation of the human brain into
       | functions. "AI" is already a solved problem, because "created"
       | intelligence is all around us. The challenge is to design a half-
       | measure that aids us economically (AI (even in disingenuous forms
       | like LLMs) is immaterial to human happiness otherwise, and mostly
       | detrimental to it). This is an entirely NEW class of problem,
       | because everything else that we've invented so far has been truly
       | new and fit into a new niche (cars, electricity, scientific
       | medicine, digital telecommunications, etc). Making "AI" "safe" /
       | "compatible" is like trying to fit a work of art or enforcing a
       | weird, arbitrary piece of legislation. That is why it's
       | ""disruptive"". In other words, this stuff ended up being the
       | centerpiece when it was supposed to just be a sort of financial
       | crutch for companies built on the motto "grow or you're dead".
       | 
       | Also, most of the tech there that's fit into those neat "boxes"
       | is very weak at best. It's like calling a parser a compiler.
       | 
       | And as an aside, maybe GOFAI was "AI-hard". That's likely why the
       | term bowed out so quickly. ;^>
        
         | booleandilemma wrote:
         | _It 's an advance in data compression, not artificial
         | intelligence._
         | 
         | It's funny you say that. There are people who believe data
         | compression and AI are the same thing:
         | https://en.wikipedia.org/wiki/Hutter_Prize
         | 
         | From the article: _The goal of the Hutter Prize is to encourage
         | research in artificial intelligence (AI). The organizers
         | believe that text compression and AI are equivalent problems._
        
           | precompute wrote:
           | Sure. But like my post said, I don't believe that this is
           | "AI" any longer. It's a bait and switch and they "killed"
           | GOFAI for it.
        
           | bick_nyers wrote:
           | Why use AI to compress your information when you could just
           | simulate the universe from the big bang? Just send the other
           | party your space and time coordinates and let them decode it!
        
       | hasmanean wrote:
       | And I thought javascript was inefficient compared to C.
       | 
       | Imagine running agents in the cloud to do simple stuff like
       | extract one 3 digit number from a weather report for the
       | temperature.
       | 
       | The power, cooling water and infra cost requirements are going to
       | be huge.
        
         | bick_nyers wrote:
         | What's stopping the agents/LLM to "compile" some "traditional"
         | code to extract that for you?
         | 
         | That's the next step, is teach these massive generalized models
         | to compile lightweight models (which doesn't have to be ML
         | based) for narrowly defined tasks, validate the narrow model
         | using the large one generating test data and boom, efficient
         | code.
        
         | BjoernKW wrote:
         | > And I thought javascript was inefficient compared to C.
         | 
         | JavaScript (and web-age scripting languages in general) made
         | programming more accessible in a fashion perhaps not entirely
         | dissimilar to what we'll see with generative AI.
        
       | egypturnash wrote:
       | I haven't heard anyone talking about "agents" since the days of
       | the AT&T "You Will" ad campaign. They've been a couple years in
       | the future for at least half my life.
       | 
       | Although honestly I feel like at least half the stuff people used
       | to breathlessly imagine "agents" doing is being handled by a
       | social media algorithm whose controls are in the hands of a
       | corporation whose only aim is to increase engagement to sell more
       | ads against, regardless of whether or not what it shows you is
       | total lies that make you angry, or by specialized websites.
       | 
       | Like you want your customized feed of things your friends said,
       | things your potential friends said, news, etc? In 2024-via-2023,
       | your "agent" would make your daily newspaper. In 2024, you open
       | up whatever your favorite social network is. It is either a
       | chill, low-engagement open-source ActivityPub server run by
       | someone in your friends circle and supported by donations, or it
       | is a corporate site which chooses what to show you based on what
       | is most likely to keep you stuck to the site, scrolling and
       | commenting, and seeing ads, regardless of whether it's showing
       | you total lies that make you angry. Perhaps by 2024 the
       | ActivityPub servers will have added the same kind of "hey you
       | might like this" stuff that the for-profit corporations have,
       | except with the controls in the hands of the end users rather
       | than the site owner fat on VC and ad revenue co-opted from the
       | people who make the stuff they're putting online.
       | 
       | Like you wanna book a plane? In 2024-via-1994 you would talk to
       | your "agent" who would go out and query multiple airlines and
       | show you a few that matched your desires, in 2024 you visit
       | flightpenguin.com and get a browser extension that hits the API
       | of airline sites and presents some cool graphs that let you sort
       | for things like "least agonizing" as well as "cheapest", and
       | doesn't reveal a single thing about where it makes enough money
       | to keep up with airline and browser redesigns. But it has a cute
       | penguin mascot. Back in 1984 you would have gone to a "travel
       | agent" who would have had deals with various airlines and access
       | to their schedules, who would put together a few possible flight
       | plans and say "this one's fastest, this one's lowest-stress, this
       | one's cheapest", and negotiate from there. They'd make a
       | commission off of it, and probably be pretty open about how this
       | motivated them to upsell you.
       | 
       | I mean that's an "agent", really, right there, no AI involved.
       | Cute cartoon character who performs a specific job on the
       | Internet, that used to be a specialty field. You'd find travel
       | agents in every mall, with pretty pictures of the places they
       | could arrange a vacation to, for deep pockets and shallow ones,
       | and neat plane models to look at.
       | 
       | Apologies for the stoned ramble. TL, DR: most of what people
       | dreamed "agents" being is pretty much _here_ IMHO, just not with
       | one single unified interface.
        
         | sgt101 wrote:
         | Yup - I was there.
         | 
         | We had a couple of killer apps...
         | 
         | "The Personal Travel Assistant" - it booked trips, it managed
         | delays, cancellations, it texted your wife to let her know you
         | would be late....
         | 
         | "The virtual estate agent" - it was a matchmaker finding
         | properties that would suit you and arranging viewings and so
         | on.
         | 
         | "The entertainment hub" - it would create parties, events and
         | do the invites - get the catering, find the band....
         | 
         | Our problem was the interface - 2g phones were useless.. a
         | desktop pc was needed for everything... how to use?!
         | 
         | Our failure of vision was that no one would care about having
         | (as you note) a single framework to do all the different
         | applications with... and we thought it would be implemented in
         | software and then adopted by companies as an interface into the
         | virtual world. We didn't think that there would be walled
         | gardens because when AOL crashed that vision had failed...
         | right?
         | 
         | This work did (in the end) lead to Siri (that wasn't the strand
         | I was in, my stuff was a competitor) and some other less high
         | profile but arguably more significant things. In the end I had
         | to stop and go back to doing machine learning which I'd dumped
         | when I decided that SVMs were the end game. What a dummy!
        
       ___________________________________________________________________
       (page generated 2023-04-19 23:02 UTC)