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

181–190 of 268 posts

Re: The short leash AI coding method for beating Fable

#181

Post by andai »

sebmellen wrote: post #17
gambiting wrote: post #13

Earlier quoted context omitted.

>>You never use “YOLO” mode (aka “dangerously skip permissions”) Do you mean this? I'm curious how are people using Claude in any way other than bypass-permissions. I've tried for so long to maintain a curated list of things Claude can use, but inevitably I would always come back only to find it stuck because it decided to pipe an output of one tool into another and that's not explicitly allowed so it stopped even th…

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.

I got halfway thru learning about containers before I realized, I just don't want it to blow up my files. That was a very solved problem in the 1970s! So I just made a Linux user called agent.

Re: The short leash AI coding method for beating Fable

#182

Post by andai »

fny wrote: post #46

AI is a junior to mid-level engineer. If you treat it as such, you get the best of both vibe coding and rigorous engineering without all this paranoia. Since the very beginning I've ran Claude from an isolated VM on yolo mode. This is just like giving an engineer their own laptop. Claude works on a feature up to a PR worthy point. I review the diff, just like I would with another engineer, and massage it to get it in…

And if you give Claude an actual laptop, he can fix the Linux bluetooth audio issues ;)

Re: The short leash AI coding method for beating Fable

#184

Post by ACCount37 »

dncornholio wrote: post #163
ACCount37 wrote: post #39

Earlier quoted context omitted.

"Next token prediction" is an interface, not an algorithm. A process that "predicts next tokens" can be arbitrarily complex or simple, and arbitrarily capable or incapable of performing a given task. Saying that an LLM can or can't do something because it's a "token predictor" is a category error. The interface isn't a hard limit.

The word "prediction" still holds a lot of weight. LLM's only can predict what has been written. This is a hard limit.

For something like "a hard limit" to hold, LLMs must be restricted to only reproducing existing text. This is utterly false even for base models - their basin seems to be "permutations loosely inspired by existing text".

And that's before all the post-training comes in.

What's the "limit" there?

Re: The short leash AI coding method for beating Fable

#186

Post by seunosewa »

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.

You can just ask the model to explain the code to you.

Re: The short leash AI coding method for beating Fable

#187

Post by stefanfisk »

Jensson wrote: post #173
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.

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…

"Humans can accurately retell what their consciousness was doing" is often not true, because of complex mechanisms. The feeling of shame alone can make it very hard for someone to accurately describe how the arrived at the wrong conclusion.

Re: The short leash AI coding method for beating Fable

#188

Post by thehours »

sleples wrote: post #89
alexsmirnov wrote: post #85

Earlier quoted context omitted.

> This happens but far less often than it used to, and the case for full autonomous agents is getting stronger, not weaker. This is that I do not see. My journey, just couple weeks ago, Claude Code + Opus 4.8. The task was not too complicated, 4 new API endpoint plus events streamed from client by websocket. 1. Multiply iterations on API definitions, refine request/response models, database schema, whole flow. A lot…

Same thing I'm seeing, all the "AI practitioners" at my company with their advanced workflows are just shipping mountains of slop, and end up either putting the actual work on the reviewers, or the poor soul that's on call when an incident occurs. I feel like people that have built crazy AI workflows have developed a false sense of confidence that their guardrails are helping them ship clean/correct code with little…

> The first that will be replaced are going to be those that are using AI mindlessly, because at that point, what are you besides a very expensive human LLM interface?

I think this archetype has a good chance of surviving. Not because of merit, but because they will be the only ones able and willing to work on projects taken over by AI slop.

I'm very much aligned with everything else you said.

Re: The short leash AI coding method for beating Fable

#189

Post by arcanemachiner »

seunosewa wrote: post #186
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.

You can just ask the model to explain the code to you.

Yes, and you will still not understand as well as if you had built it.

Re: The short leash AI coding method for beating Fable

#190

Post by Jensson »

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 also have a deep nuanced discussion with a rubber duck as long as you don't ask any questions it needs to respond to.
Post reply on HN