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

261–268 of 268 posts

Re: The short leash AI coding method for beating Fable

#261

Post by sothatsit »

zquzra wrote: post #107
sothatsit wrote: post #23

This “short leash” seems like more of a crutch to me, and a sign of not giving the AI enough detail on the problem to begin with, or not reviewing and iterating on its output. Hand-holding great models like Fable through implementation is a waste of time, and a waste of Fable. You can have increasingly nuanced discussions with stronger models, and they write a lot better code than they used to. The process of discuss…

Do you have a background in CS or optimization? MILP is a pretty standard concept in algorithms/optimization. So this example doesn't really convince me that the AI reached some unusually superior conclusion. It sounds more like it suggested a well-known technique that you personally hadn't encountered. Useful, yes, but that seems more about background knowledge gaps than about the merits of letting the tool run unco…

There are always concepts that some people think are a basic, that others haven't heard of. The entire benefit here is that AI can point out what we miss. There are certainly techniques you don't know about, or just didn't think to apply to a problem, that others would find to be pretty standard.

Re: The short leash AI coding method for beating Fable

#262

Post by cpursley »

weakfish wrote: post #252
cpursley wrote: post #233

Earlier quoted context omitted.

[flagged]

I’d prefer kindness and good faith when talking to strangers, but maybe my expectations are too high. Do you think you’ll change someone’s mind by being an asshole? Rarely works.

You’re in agreement with me, call these toxic language police jerks out as soon they have keyboard spasms.

Re: The short leash AI coding method for beating Fable

#263

Post by avereveard »

artisin wrote: post #45
avereveard wrote: post #7

Seems hella inefficient. Better method start to realizing that everything that every program do is data transformations and or movement Then you ask llm to subdivide data in a tree along the domain model, classifing streaming vs storing nodes Then for each node you discuss with the ai for the best data structure Then you ask for an interface that fully encapsulate the structure and every mutation only allows to go fr…

Efficient != effective, and the author outlines as much. Regardless, while you're technically correct, it's kinda like saying the Fantasy Land Specification[1] (aka the "Algebraic JavaScript Specification") is pure. The problem is that purely functional fantasy lands rarely exist outside of fairytales. In other words, life is a lot like JavaScript and never that simple. [1] - https://github.com/fantasyland/fantasy-la…

never said purely functional, but there are only 4 data channels in each method (input, return, calling another method, setting a state) - and if you constrain your class design to pick only 2 for each method, your life is just a tad easier.

and doesn't matter how bad the rest of the world is, rest of the world is some other maintainer's problem, you just encapsulate it.

Re: The short leash AI coding method for beating Fable

#264

Post by entropyneur »

mirror_neuron wrote: post #231
entropyneur wrote: post #137

This reminds me of the workflow I had a year ago. Miss Aider so much. Are there any good open source agents right now? Might be a good time to try one soon as Fable switches to token-based billing, which Code is designed to maximize.

I still work like this, using Aider. What do you mean when you say you “miss” it? (Why not just keep using it?)

Around last fall it started chronically lagging in SOTA models support. Honestly, not sure why a code update is even needed for that. Eventually it'd get patched but it just wasn't quick enough for me. Other development seems to have ceased completely. At one point I tried to investigate what's going on and it looked like the community had moved on. There was a fork that promised a liberal approach to accepting changes and it looked broken beyond repair because of that.

Re: The short leash AI coding method for beating Fable

#266

Post by HappMacDonald »

FeepingCreature wrote: post #248
Dilettante_ wrote: post #222

Earlier quoted context omitted.

> Consciousness tries to make things up, it learns that people notice this, it then begins trying to construct justifications that won't be predictably called out as false. There's a logical "skip" between that and > Eventually it learns how its unconscious operates, and how to interrogate it, and its post-hoc justifications, at least in the common cases, become reliable. The brain constructs a narrative that won't b…

Yep. It converges on truth unless there's a strong reward for lies because truth is easy. It's a neural network. It just reads off/probes the internal state because that's the cheapest way to model the unconscious. The justification won't necessarily be true, mind, in terms of the labels it puts, but it should mostly be true structurally - behaviorally predictive in the ordinary domain. (Even if you are incentivized…

Your explanation still presupposes that a "true signal" even exists in the first place to be able to internally interrogate, though.

Re: The short leash AI coding method for beating Fable

#267

Post by lukasco »

mholm wrote: post #73
codazoda wrote: post #63

Earlier quoted context omitted.

I find it still asks too many questions. Unless I'm not triggering it as often as I think I am.

What questions? When I go into auto mode, it doesn't come back until it accidentally/intentionally tries to slip the guardrails, or completes the task. My prompt will generally include information on what it's allowed to do to accomplish the task, where to test, etc. Simple, but effective.

Same here. Before auto, couldn’t handle the constant stopping because of backslashes no matter how many things I permitted.

Re: The short leash AI coding method for beating Fable

#268

Post by FeepingCreature »

HappMacDonald wrote: post #266
FeepingCreature wrote: post #248

Earlier quoted context omitted.

Yep. It converges on truth unless there's a strong reward for lies because truth is easy. It's a neural network. It just reads off/probes the internal state because that's the cheapest way to model the unconscious. The justification won't necessarily be true, mind, in terms of the labels it puts, but it should mostly be true structurally - behaviorally predictive in the ordinary domain. (Even if you are incentivized…

Your explanation still presupposes that a "true signal" even exists in the first place to be able to internally interrogate, though.

I mean, I do believe that an explanation of the unconscious is a model about firing patterns in the brain that can be true or false, sure. That does not seem to me controversial?
Post reply on HN