[HN Gopher] How to write stuff no one else can
___________________________________________________________________
How to write stuff no one else can
Author : EthanDBrooks
Score : 81 points
Date : 2024-02-09 19:52 UTC (1 days ago)
(HTM) web link (thewritetoroam.com)
(TXT) w3m dump (thewritetoroam.com)
| yamrzou wrote:
| This sentence caught my attention:
|
| > You can't just Google these kinds of things. That's why they're
| so interesting.
|
| So what Google did is dilute the information advantage. The more
| interconnected we are, the harder it becomes to maintain that
| advantage.
| hawski wrote:
| That's also something I often encounter with ChatGPT. It often
| is very wrong about things I ask, because I often wonder and
| try things off the beaten path. That's our advantage against
| LLMs.
| from-nibly wrote:
| No the advantage is that you have context. That context is
| HUGE. That's why you can't and won't be able to have chat gpt
| actually do your job for you. You still need to ask it
| questions. And to even know what questions you need to ask
| you need to have context.
| Jensson wrote:
| You don't just need a context, you need to finetune a model
| around that context since working memory isn't enough. That
| is what human workers do, they spend the first months
| finetuning their model around the company context before
| they can start to provide valuable code.
|
| Once you can pay to get your own fine tuned version of the
| big LLMs maybe we can start to do real work with these.
| adtac wrote:
| Purely probabilistically, trying things off the beaten path
| is just a matter of higher LLM temperature. Turning up
| GPT-4's temperature is basically an expensive /dev/urandom
| pipe today, but I don't see any fundamental reason why LLMs
| can't catch up. Maybe all it takes is tinkering with how
| temperature is calculated.
| cjohnson318 wrote:
| The fact is that we're not that interconnected though. Finding
| people that have useful, actionable information, and want to
| share it with you, is extremely difficult.
| Jensson wrote:
| That is a search issue not an interconnectivity issue.
| ssivark wrote:
| Google, ChatGPT, Gemini, Perplexity, etc are all retrieval
| services (with some rudimentary remixing capabilities thrown
| in, for the latter few). Some human has to actually have
| interesting insights and write them. Retrieval services help
| with distribution & discovery. The less we're connected, the
| harder it is to find the right audience who value your (niche)
| insights.
|
| Of course attribution and linking is important.
| wordpad25 wrote:
| AI so much much more than retrieval since it knows how to
| correctly apply exist concepts to previously unexplored
| areas.
|
| You can ask ChatGPT how one might implement and enforce laws
| in a world where magic exists. Or time travel. Or whatever.
| Because it knows laws and it knows common fiction tropes and
| can reason well enough to surmise how to apply them together.
| wordpad25 wrote:
| Wanted to give it a try. I didn't even consider many of
| these and doubt I would've come up with such a good list
| even if I had a lot of time. Much less than 1 second it
| took to generate the response.
|
| In a world where magic exists, laws and the legislative
| system would likely undergo significant adaptations to
| address the unique capabilities and risks presented by
| magic. Here are several ways in which these systems might
| be different, based on various assumptions about the nature
| and scope of magic:
|
| 1. *Regulation of Magical Practices*: Just as with
| professions and practices in our world, there would be
| regulations governing who can practice magic, how it can be
| learned, and where it can be used. Licenses or permits
| might be required for practicing certain types of magic,
| similar to medical licenses or driving licenses.
|
| 2. *Magic-Related Offenses*: New categories of crimes would
| exist, such as unauthorized enchantments, illegal curses,
| magical fraud (using illusions or mind control for deceit),
| and unlicensed necromancy. Laws would specify what
| constitutes a magical assault versus a non-magical one,
| with potentially different penalties.
|
| 3. *Enforcement and Jurisdiction*: Special law enforcement
| units trained in counter-magic or magical defense would be
| necessary to handle crimes involving magic. The
| jurisdiction might depend on the nature of the magic used;
| for example, cross-dimensional or time-altering magic could
| involve a higher authority or international magical
| council.
|
| 4. *Evidence and Investigation*: The collection of evidence
| might include magical means, such as truth spells, scrying
| (viewing distant or future events), or reviewing memories
| directly. However, there would also need to be laws
| protecting individuals against invasive magical
| investigations.
|
| 5. *Rights and Protections*: There would be laws to protect
| non-magical beings from discrimination or harm by magical
| individuals or entities. Similarly, sentient magical
| creatures or beings might have their own rights, leading to
| more complex legal considerations regarding interspecies
| interactions.
|
| 6. *Ethical Use of Magic*: Legislation would likely address
| the ethical implications of spellcasting, summoning, and
| other magical practices, including the use of magic on
| unwilling subjects or creating sentient beings. Regulations
| might prevent or restrict the use of magic that can alter
| someone's will, memories, or identity.
|
| 7. *Magical Contracts and Agreements*: The legal system
| would need to address the binding nature of magical
| contracts, which could have irrevocable consequences. Laws
| might specify how such contracts can be fairly negotiated
| and what remedies exist for breaking a magical contract.
|
| 8. *Intellectual Property*: In a world where spells,
| potions, and magical items are created, there would be
| intellectual property laws protecting the creators of
| magical inventions. This could include patents on spell
| formulas, copyright on magical texts, or trademarks on
| magical item designs.
|
| 9. *International Relations and Security*: On a larger
| scale, there might be international laws governing the use
| of magic, especially in conflicts or espionage. Treaties
| could limit the use of particularly destructive spells or
| ban the creation of magical weapons of mass destruction.
|
| 10. *Education and Public Safety*: Laws would govern the
| education and training of individuals with magical
| abilities, possibly requiring mandatory schooling to ensure
| that magic is used safely and responsibly. Public safety
| regulations would address the storage of magical materials
| and the construction of magically protected buildings.
|
| In this magical world, the legal and legislative system
| would need to be flexible and innovative, capable of
| addressing the ever-evolving nature of magic and its impact
| on society. It would be a blend of traditional legal
| principles and new rules designed to manage the unique
| challenges posed by the existence of magic.
| bena wrote:
| All of these are basically "what we have now, but with
| magic".
|
| I'm sorry but how magic and the legal system interact
| _is_ a subject explored in fiction. Hell, even Harry
| Potter touched on the subject. And that 's not going to
| even touch authors like Jim Butcher and Piers Anthony who
| have entire series about "this, but with magic".
| pcc wrote:
| Fun little exercise: while reading above, see what
| happens when mentally substituting "magic" with "AI",
| words like "enchantments" with "algorithms" and so on.
| oldandtired wrote:
| You make the following comment regarding artificial
| stupidity systems (AI)
|
| > since it knows how to correctly apply exist concepts to
| previously unexplored areas
|
| and yet these systems know nothing at all. Far too many
| people (including the developers of such systems) have
| failed to understand that none of these systems can go
| beyond the programming that humans have incorporated into
| them. Yes, they appear to exhibit certain [abilities] but
| no more than any other essentially mechanical device and
| the limited capabilities that we have been able to design
| in them.
|
| You can certainly pose questions and these systems (within
| the constraints of the programming involved in them) can
| retrieve and correlate data that is accessible. Bus the
| insights drawn will require human involvement.
|
| Over decades, I have built tools to help in the analysis of
| all sorts of data sets and it has taken a human asking the
| [right] questions to get appropriate outcomes.
|
| We do not understand our own intelligence let alone being
| able to build any artificial intelligent system that can
| operate on its own.
|
| What does amaze me though is that we create natural
| intelligence systems all the time and they are called
| children. I have been avidly watching the development of my
| youngest grandchild and she makes an absolute mockery of
| any artificial system we have built anywhere.
|
| In a very real sense, every artificial stupidity system
| (AI) that we have built is as complicated as a hammer or a
| knife.
|
| It is what we (human beings) do with these simple tools
| that determine the outcomes.
| philipswood wrote:
| > and yet these systems know nothing at all. Far too many
| people (including the developers of such systems) have
| failed to understand that none of these systems can go
| beyond the programming that humans have incorporated into
| them.
|
| I think the point of machine learning is that programming
| isn't "incorporated into them".
| QuantumGood wrote:
| The longer I think about something, the dumber AI gets.
|
| I have given our internal knowledgebase documents to ChatGPT
| and asked for summaries, and it adds in things from the
| general internet that are wrong to very wrong contradicting
| our KB (we are very far off the beaten path of conventional
| audio studio design testing).
| mattfrommars wrote:
| I read the article, what mind opening tactic did the author
| explain to the public?
|
| Appears to be blogspam.
| tmountain wrote:
| Going down a layer below Tim Ferriss to his staff... /s
| vrc wrote:
| I think the extent to which writers have to get creative in
| finding sources for novel pieces is taken for granted. I did
| not realize how tactical and painstaking the process is to
| create the content that I casually skim and enjoy. So I
| strengthened my appreciation of the process
| irrational wrote:
| I wonder if Stephen Hanselman is being inundated with email right
| now and doesn't know why?
| thenerdhead wrote:
| What was the answer?
|
| Find a human who can bypass robots.txt/limitations of ChatGPT and
| find less traveled sources given the internet fails to archive
| itself and important information can be wiped any minute? Isn't
| that just called good journalism?
___________________________________________________________________
(page generated 2024-02-10 23:00 UTC)