Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The short leash AI coding method for beating Fable

blog.okturtles.org

Post reply on HN
Print view View original

151–160 of 268 posts

Re: The short leash AI coding method for beating Fable

#151

Post by iainmerrick »

tuvix wrote: post #52
semiquaver wrote: post #38

Earlier quoted context omitted.

Do you not say your words one-at-a-time like everyone else? Otherwise I can’t see how my comment is “wrong”

Even if you could understand human cognition to the level required to say, confidently, that it’s done one word at a time, it’s likely not! Natural language is not a prerequisite for human intelligence, as evidenced by the fact that we went from primates to commenting on HN. Natural language is, however, a prerequisite for the existence of LLMs. It’s more similar to methods for storing and retrieving information, lik…

Even if you could understand human cognition to the level required to say, confidently, that it’s done one word at a time, it’s likely not!

I think they’re not talking about cognition, but about output: regardless of what may be happening inside your brain, ultimately one word at a time comes out of your mouth, right? And you can’t then unsay it.

When you put it in those terms, LLMs are in exactly the same boat.

Re: The short leash AI coding method for beating Fable

#152

Post by Shitty-kitty »

doctoboggan wrote: post #122
sixtram wrote: post #106

Earlier quoted context omitted.

You say you can have increasingly nuanced discussions with stronger models. What I say is, when I asked Claude why he applied a certain change I didn't understand, and boy, it was a small change, he said he "reasoned from first principles" based on the code paths. But it didn't work, and when I asked, "Okay, describe the steps of your reasoning from first principles," it literally answered that it had just made it up…

You can never ask why a model did a certain thing, or what it was "thinking" when it said something - just like you can't ask a human which neurons were firing when they had a certain thought. The information just isn't available at that level. You absolutely can have deep nuanced discussions with LLMs however, you just need to better understand their strengths and weaknesses.

A human won't respond with "Neuron 10-100 of the frontal cortex" (jokes aside) with deceptively convincing confidence.

Re: The short leash AI coding method for beating Fable

#153

Post by youdont »

Shitty-kitty wrote: post #152
doctoboggan wrote: post #122

Earlier quoted context omitted.

You can never ask why a model did a certain thing, or what it was "thinking" when it said something - just like you can't ask a human which neurons were firing when they had a certain thought. The information just isn't available at that level. You absolutely can have deep nuanced discussions with LLMs however, you just need to better understand their strengths and weaknesses.

A human won't respond with "Neuron 10-100 of the frontal cortex" (jokes aside) with deceptively convincing confidence.

The human will quite convincingly be able to construct a post-hoc reasoning on an action that may or may not be related at all to what was actually going through their head or the actual instinctual reasons that led to a decision.

Re: The short leash AI coding method for beating Fable

#154

Post by sixtram »

doctoboggan wrote: post #122
sixtram wrote: post #106

Earlier quoted context omitted.

You say you can have increasingly nuanced discussions with stronger models. What I say is, when I asked Claude why he applied a certain change I didn't understand, and boy, it was a small change, he said he "reasoned from first principles" based on the code paths. But it didn't work, and when I asked, "Okay, describe the steps of your reasoning from first principles," it literally answered that it had just made it up…

You can never ask why a model did a certain thing, or what it was "thinking" when it said something - just like you can't ask a human which neurons were firing when they had a certain thought. The information just isn't available at that level. You absolutely can have deep nuanced discussions with LLMs however, you just need to better understand their strengths and weaknesses.

So you're saying I can absolutely have a deep, nuanced discussion with an LLM, as long as I don't ask how he arrived at his conclusions?

Re: The short leash AI coding method for beating Fable

#155

Post by wrxd »

data-ottawa wrote: post #99
sebmellen wrote: post #17

Earlier quoted context omitted.

I’ve found unexpected success in using ephemeral NixOS VMs for local development… once you authenticate your agent you can let it run wild without worrying about permissions.

Dies the agent have access to is own nix config (and therefore install permissions), or do you have to provide it all the tools externally?

It doesn’t even need access to nix config. It could use nix shell to grab the tools it needs.

Re: The short leash AI coding method for beating Fable

#156

Post by root_axis »

infinite_spin wrote: post #91
root_axis wrote: post #79

Earlier quoted context omitted.

The post I responded to stated that the commenter was just a next-word-sayer, but that's wrong. The similarities you draw aren't really relevant to my reply.

no disrespect intended, however I think my response is relevant, because the broader topic here is whether LLMs and the human mind share similar functions. They both do in fact have a lot of overlapping features, and a fundamental one is predicting next-thing , be that a word, image, or otherwise.

It's not relevant. However, if you want to talk about a broader point, that's ok.

> LLMs appear to learn distributions of representations, they both develop a hierarchy of those representations, both have early layers that process simple features, with later ones processing more abstract concepts, both predict missing information.

This type of superficial comparison isn't very meaningful, it's trivial to liken anything to a human biology in this manner.

A plane and a bird both use wings to produce lift, it doesn't then follow that a bird and a plane are meaningfully similar.

Re: The short leash AI coding method for beating Fable

#157

Post by sothatsit »

sixtram wrote: post #154
doctoboggan wrote: post #122

Earlier quoted context omitted.

You can never ask why a model did a certain thing, or what it was "thinking" when it said something - just like you can't ask a human which neurons were firing when they had a certain thought. The information just isn't available at that level. You absolutely can have deep nuanced discussions with LLMs however, you just need to better understand their strengths and weaknesses.

So you're saying I can absolutely have a deep, nuanced discussion with an LLM, as long as I don't ask how he arrived at his conclusions?

You can have a nuanced discussion with an LLM. But LLMs also have failure modes where they start making up justifications. The two are not mutually exclusive.

Re: The short leash AI coding method for beating Fable

#158

Post by infinite_spin »

root_axis wrote: post #156
infinite_spin wrote: post #91

Earlier quoted context omitted.

no disrespect intended, however I think my response is relevant, because the broader topic here is whether LLMs and the human mind share similar functions. They both do in fact have a lot of overlapping features, and a fundamental one is predicting next-thing , be that a word, image, or otherwise.

It's not relevant. However, if you want to talk about a broader point, that's ok. > LLMs appear to learn distributions of representations, they both develop a hierarchy of those representations, both have early layers that process simple features, with later ones processing more abstract concepts, both predict missing information. This type of superficial comparison isn't very meaningful, it's trivial to liken anythi…

> A plane and a bird both use wings to produce lift, it doesn't then follow that a bird and a plane are meaningfully similar.

The use of Bernoulli's principle to achieve lift is a fundamental and meaningfully similar function of both airplane and bird wings. That functional similarity is well known.

> This type of superficial comparison isn't very meaningful

The comparisons I provided are fundamental to both the human mind and LLMs.. that's pretty darn relevant.. and whether you find that trivial or not is a matter of opinion.

Re: The short leash AI coding method for beating Fable

#159

Post by user3939382 »

ramon156 wrote: post #148

One problem I have with "how to do X with AI" is that every situation is different. For example, I'm bumping Symfony projects from 3.1 to 8.1. There's a clear path here - Follow the written up migration guides PER major version - test all routes, authorised, etc. You can even hand-curate these tests. some might return 200, some might return 302 - Maybe optionally start with writing a safety net so you do not need to…

Have you tried rector?

Re: The short leash AI coding method for beating Fable

#160

Post by infinite_spin »

esailija wrote: post #150
infinite_spin wrote: post #35

Earlier quoted context omitted.

> it doesn't mean it's intelligent I'm not sure how you're defining "intelligent", but I'd like to know how it is able to exclude a language model, while still including humans, without simply defining it with an axiom that predefines LLMs as lacking intelligence.

Intelligence is the complete opposite of an LLM. Usually the more you needed to memorize to do something the less intelligent you were considered. It was also not considered to be a different route to the same thing, but more like fraud. Also conceptually I could just write the weights on paper and do the billion multiplications on paper without any computer, does that mean I am the paper or the numbers or what??

> Intelligence is the complete opposite of an LLM

Like I said, "without simply defining it with an axiom that predefines LLMs as lacking intelligence"

Post reply on HN