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

51–60 of 268 posts

Re: The short leash AI coding method for beating Fable

#51

Post by lowbloodsugar »

gambiting wrote: post #13
jonplackett wrote: post #6

I thought this was how everyone who can actually code uses AI for anything that’s actually important. Am I wrong? Are you guys just YOLOing everything these days?

>>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…

Build your own MCP of allowed tools. Cargo. Ripgrep. File read and write, including directory listing and find. some git commands. Then block everything else.

Re: The short leash AI coding method for beating Fable

#52

Post by tuvix »

semiquaver wrote: post #38
root_axis wrote: post #33

Earlier quoted context omitted.

This is wrong. Human thinking and speech isn't autoregressive like LLM inference.

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, like the printing press or a database, than it is to a sentient being.

That’s not to say that LLMs can’t do crazy things, because they already have. Our language can encode a whole lot of information, and it’s incredible that we’ve found a way to distill that so effectively.

Re: The short leash AI coding method for beating Fable

#53

Post by artisin »

semiquaver wrote: post #38
root_axis wrote: post #33

Earlier quoted context omitted.

This is wrong. Human thinking and speech isn't autoregressive like LLM inference.

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

Only one word at a time!?! It's time you embrace the way of the diffusion model and hazily refine your entire thought until it's coherent.

Re: The short leash AI coding method for beating Fable

#54

Post by infinite_spin »

Cycl0ps wrote: post #42
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.

An LLM has a fixed number of ways it can express itself. we can give it an array of 14 billion options but it still has to chose one to output. Humans have no such limitation. An LLM does not persist in consciousness from one token to the next. Each generation, happening hundreds of times a second, will be initialized, generate an output, and terminate. Humans are not stateless like an LLM.

You're conflating a singular model with a much larger system, but I want to address some of your points anyway.

> An LLM has a fixed number of ways it can express itself

While deterministic, there is not a fixed number of ways it can express itself, given that we can use settings like temperature to inject randomness into the output.

> An LLM does not persist in consciousness from one token to the next

While a model alone does not update itself to persist some form of history, there are a number of ways to overcome this, e.g. episodic memory, fine-tuning, and other self-improvement systems exist, which can indeed carry forward what you've called "consciousness".

> Humans are not stateless like an LLM.

A single LLM might be stateless, but an agentic system that relies on LLMs is very often not.

Re: The short leash AI coding method for beating Fable

#55

Post by YuechenLi »

I mean, the key is to stop trying to one-shot everything: The main problem I found with LLM code is more that they always try to take the shortest path to the solution possible, so a lot of time Codex would write code that meets the requirements of the prompt but misses something that cause it to not work in the non-ideal scenario.

The solution for that is pretty easy too, it's just iteration: you describe the exact problem you have with the code and why it is not running correctly and ask them to provide a narrow fix that addresses the bug. It's not that complicated.

Re: The short leash AI coding method for beating Fable

#56

Post by giancarlostoro »

Here I thought this was about Fable the video game, then I remembered Anthropics model got named Fable. It's going to be painful to google one of my favorite game series, just like googling "Rust server" does not give you Rust programming results, but Rust the video game results. I wish google would have fixed this problem long ago, it seems like something trivial for them to fix.

Re: The short leash AI coding method for beating Fable

#57

Post by basilikum »

giancarlostoro wrote: post #56

Here I thought this was about Fable the video game, then I remembered Anthropics model got named Fable. It's going to be painful to google one of my favorite game series, just like googling "Rust server" does not give you Rust programming results, but Rust the video game results. I wish google would have fixed this problem long ago, it seems like something trivial for them to fix.

Fable -AI

Re: The short leash AI coding method for beating Fable

#58

Post by lukasco »

gambiting wrote: post #13
jonplackett wrote: post #6

I thought this was how everyone who can actually code uses AI for anything that’s actually important. Am I wrong? Are you guys just YOLOing everything these days?

>>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…

It's not YOLO, but auto mode in Claude Code does reduce the amount you have to approve significantly. And frankly, without it, progress is constantly interrupted by permission requests. It's all I use. Don't even really switch into Plan mode manually anymore.

Re: The short leash AI coding method for beating Fable

#59

Post by MoltenMan »

moezd wrote: post #18

LLMs are still next token predictors, just because you can give it more vague instructions and it still finds the right steps to follow, it doesn't mean it's intelligent. It means you're speaking the same language as the harness they trained your model on. And that has a limit. If you are stuck at PoC level or simple apps, you have no idea how limited the current models still are. There you really need to break tasks…

Calling LLMs 'next token predictors' is completely reductive and disingenuous; it's true that technically that is what they're doing, but so are you! What people generally mean by this though is that they're just 'predicting the next token of their training [i.e. the internet]'. If you were talking about the raw models, this would actually be true; but the models are post trained, so even this description isn't true at all anymore! Saying they aren't 'intelligent' is both not useful and (imo) wrong. Who cares if it matches your definition of 'intelligent'; it still gets impressive stuff done, much more impressive stuff than you seem to be implying.

Re: The short leash AI coding method for beating Fable

#60

Post by nqzero »

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…

what VM/provisioning are you using ?
Post reply on HN