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

171–180 of 268 posts

Re: The short leash AI coding method for beating Fable

#171

Post by sn0n »

solenoid0937 wrote: post #111
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…

Posts like this are meaningless without more context - the model you're using, the harness, the initial prompt and context. Fable is better than most staff engineers at my FAANG.

Maybe I’m missing something, but he talks about charm and tasks (repos on his GitHub). Charm being his harness, and tasks being one of his skills. Idk, maybe I’m mistaken from reading the article…

https://github.com/taoeffect

Re: The short leash AI coding method for beating Fable

#172

Post by NitpickLawyer »

sn0n wrote: post #169
youdont wrote: post #153

Earlier quoted context omitted.

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.

Isn’t that part of what the think blocks are for? Yea, don’t inject them back into the context, but do log them for review of that train of thought… no?

You don't get access to the thinking traces. Might work with local models tho, but the current meta isn't particularly suited for this either, as it's a big blob of rambling surfaced by RL, with the "only" objective being that the thinking blob somehow leads to a better final answer. Something more detailed, using templates akin to oAI's harmony could work, provided there's also a step that teaches the models to reflect on the various thinking channels, and maybe surface bits and pieces to include in "skills" or "learnings".

Re: The short leash AI coding method for beating Fable

#173

Post by Jensson »

youdont wrote: post #153
Shitty-kitty wrote: post #152

Earlier quoted context omitted.

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.

Humans can accurately retell what their consciousness was doing, but they have no clue why their unconsciousness responded as it did.

LLM is just that unconsciousness part that humans have to post hoc explain like that, and lacks the conscious part that we humans actually can inspect in ourselves.

If the AI had some introspection part where it actually tracks its reasoning maybe it would be closer to conscious humans. Its too expensive to do that everywhere ofc, not even us humans tracks everything like that, just a tiny bit, but tracking that tiny bit is enough for so much error correction to happen.

Re: The short leash AI coding method for beating Fable

#174

Post by esperent »

chewbacha wrote: post #94

I did this for two weeks on a side project and still ended up in a situation where I did not have a mental model of the codebase. There’s no way build that model without building it yourself. I’m more convinced then ever of this.

If you were working as a manager on a large project, how would you build a model? Something where your position requires you to have an overview of the project but not necessarily to actually write or review much code.

Re: The short leash AI coding method for beating Fable

#175

Post by matheusmoreira »

rexarex wrote: post #64
matheusmoreira wrote: post #47

Earlier quoted context omitted.

It's impossible for someone to doubt their own sentience. The literal act of doubting is enough to dissipate all doubt. Solipsism is essentially the one certainty that every mind out there has. Doubting the sentience of machines and even other humans is perfectly fine though. Only empathy allows people to make the leap and assume other humans have souls.

So you posit that humans are solipsistic by default, but some (most?) develop more and realize they’re not the only conscious being out there?

"Realize" is too strong a word. You're the only one who can verify that you're the soul who's staring out at the world through your eyes. For all you know, everyone else could be just biological automatons, golems.

Any leap beyond that is based on empathy. You have a soul, and you are human, therefore other humans could have souls too. It's a spiritual belief. Answers to questions that cannot be answered.

Re: The short leash AI coding method for beating Fable

#176

Post by marmarama »

rexarex wrote: post #64
matheusmoreira wrote: post #47

Earlier quoted context omitted.

It's impossible for someone to doubt their own sentience. The literal act of doubting is enough to dissipate all doubt. Solipsism is essentially the one certainty that every mind out there has. Doubting the sentience of machines and even other humans is perfectly fine though. Only empathy allows people to make the leap and assume other humans have souls.

So you posit that humans are solipsistic by default, but some (most?) develop more and realize they’re not the only conscious being out there?

That's the standard Piagetian understanding of child development, yes. Humans do not start out with theory of mind, and are thus inherently solipsistic, but in most cases an understanding that there are other conscious beings with their own thoughts, goals and feelings develops between the ages of 2 and 7.

Developing theory of mind is one of the key milestones in child development.

Re: The short leash AI coding method for beating Fable

#178

Post by andai »

I call this method semiauto. The main benefit is keeping your mental model synchronized.

The process becomes real-time instead of asynchronous, and active instead of passive.

And you don't have to spend extra time catching up on the code later.

You can also use much smaller faster cheaper models, because the scope always stays bite sized.

Re: The short leash AI coding method for beating Fable

#179

Post by andai »

chewbacha wrote: post #94

I did this for two weeks on a side project and still ended up in a situation where I did not have a mental model of the codebase. There’s no way build that model without building it yourself. I’m more convinced then ever of this.

Unfortunately I ran into the same issue even before AI.

The forgetting curve means that my mental model lasts not much longer than the initial building period.

As for how to rebuild it, I haven't figured that part out yet.

Re: The short leash AI coding method for beating Fable

#180

Post by andai »

esperent wrote: post #174
chewbacha wrote: post #94

I did this for two weeks on a side project and still ended up in a situation where I did not have a mental model of the codebase. There’s no way build that model without building it yourself. I’m more convinced then ever of this.

If you were working as a manager on a large project, how would you build a model? Something where your position requires you to have an overview of the project but not necessarily to actually write or review much code.

I've been experimenting with the Feynman technique on codebases. However the issue I run into is that, you need hard feedback to verify your hypotheses.

I was satisfied with my own explanation of how something worked but it turned out to be wrong.

LLMs help here (the transformer is good at seeing the big picture, at least on smallish codebases), but the best thing I found so far is just modding.

Actually making a change to the code is the best way to get hard feedback about your model.

Post reply on HN