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

Two things LLM coding agents are still bad at

kix.dev

Post reply on HN
Print view View original

91–100 of 382 posts

Re: Two things LLM coding agents are still bad at

#91

Post by sebtron »

ivape wrote: post #65
grey-area wrote: post #59

Earlier quoted context omitted.

Or just not bother. It sounds pretty useless if it flunks on basic tasks like this. Perhaps you’ve been sold a lie?

Well, you see it hallucinates on long precise strings, but if we ignore that, and focus on what it’s powerful at, we can do something powerful. In this case, by the time it gets to outputting the url, it already determined the correct intent or next action (print out a url). You use this intent to do a tool call to generate a url. Small aside, it’s ability to figure what and why is pure magic, for those still peddlin…

> Well, you see it hallucinates on long precise strings

But all code is "long precise strings".

Re: Two things LLM coding agents are still bad at

#92

Post by NitpickLawyer »

freetonik wrote: post #86
NitpickLawyer wrote: post #52

Earlier quoted context omitted.

> almost always the first group presents examples of simple CRUD apps How about a full programming language written by cc "in a loop" in ~3 months? With a compiler and stuff? https://cursed-lang.org/ It might be a meme project, but it's still impressive as hell we're here. I learned about this from a yt content creator that took that repo, asked cc to "make it so that variables can be emojis", and cc did that 5$ late…

Ok, not trivial for sure, but not novel? IIUC, the language does not have really new concepts, apart from the keywords (which is trivial). Impressive nonetheless.

Novel as in never done before? Of course not.

Novel as in "an LLM can maintain coherence on a 100k+ LoC project written in zig"? Yeah, that's absolutely novel in this space. This wasn't possible 1 year ago. And this was fantasy 2.5 years ago when chatgpt launched.

Also impressive in that cc "drove" this from a simple prompt. Also impressive that cc can do stuff in this 1M+ (lots of js in the extensions folders?) repo. Lots of people claim LLMs are useless in high LoC repos. The fact that cc could navigate a "new" language and make "variables as emojis" work is again novel (i.e. couldn't be done 1 year ago) and impressive.

Re: Two things LLM coding agents are still bad at

#93

Post by exe34 »

rossant wrote: post #79
coldtea wrote: post #76

Earlier quoted context omitted.

> A few days later, just before deployment to production, I wanted to double check all 40 links. This was allowed to go to master without "git diff" after Codex was done?

It was a fairly big refactoring basically converting a working static HTML landing page into a Hugo website, splitting the HTML into multiple Hugo templates. I admit I was quite in a hurry and had to take shortcuts. I didn't have time to write automated tests and had to rely on manual tests for this single webpage. The diff was fairly big. It just didn't occur to me that the URLs would go through the LLMs and could b…

this is why I'm terrified of large LLM slop changesets that I can't check side by side - but then that means I end up doing many small changes that are harder to describe in words than to just outright do.

Re: Two things LLM coding agents are still bad at

#94

Post by exe34 »

worldsayshi wrote: post #69
rossant wrote: post #37

Recently, I asked Codex CLI to refactor some HTML files. It didn't literally copy and pasted snippets here and there as I would have done myself, it rewrote them from memory, removing comments in the process. There was a section with 40 successive links with complex URLs. A few days later, just before deployment to production, I wanted to double check all 40 links. First one worked. Second one worked. Third one worke…

This is of course bad but: humans also makes (different) mistakes all the time. We could account for the risk of mistakes being introduced and make more tools that validate things for us. In a way LLM:s encourage us to do this by adding other vectors of chaos into our work. Like, why not have tools built into our environment that checks that links are not broken? With the right architecture we could have validations…

> that checks that links are not broken?

Can you spot the next problem introduced by this?

Re: Two things LLM coding agents are still bad at

#95

Post by BenGosub »

The issue is partly that some expect a fully fledged app or a full problem solution, while others want incremental changes. To some extent this can be controlled by setting the rules in the beginning of the conversation. To some extent, because the limitations noted in the blog still apply.

Re: Two things LLM coding agents are still bad at

#96

Post by exe34 »

ivape wrote: post #90
hansmayer wrote: post #89

Earlier quoted context omitted.

Yeah so, the reason people use various tools and machines in the first place is to simplify the work or everydays tasks by : 1) Making the tasks execute faster 2) Getting more reliable outputs then doing this by yourself 3) Making it repeatable . The LLMs obviously dont check any of these boxes so why don´t we stop pretending that we as users are stupid and don´t know how to use them and start taking them for what th…

[flagged]

I take it you have bought stocks? What do you recommend?

Re: Two things LLM coding agents are still bad at

#97

Post by _ink_ »

> LLMs are terrible at asking questions. They just make a bunch of assumptions and brute-force something based on those guesses.

I don't agree with that. When I am telling Claude Code to plan something I also mention that it should ask questions when informations are missing. The questions it comes up with a really good, sometimes about cases I simply didn't see. To me the planning discussion doesn't feel much different than in a GitLab thread, only at a much higher iteration speed.

Re: Two things LLM coding agents are still bad at

#99

Post by AllegedAlec »

jeswin wrote: post #68
AllegedAlec wrote: post #13

On a more important level, I found that they still do really badly at even a minorly complex task without extreme babysitting. I wanted it to refactor a parser in a small project (2.5K lines total) because it'd gotten a bit too interconnected. It made a plan, which looked reasonable, so I told it to do this in stages, with checkpoints. It said it'd done so. I asked it "so is the old architecture also removed?" "No, i…

> I wanted it to refactor a parser in a small project This expression tree parser (typescript to sql query builder - https://tinqerjs.org/ ) has zero lines of hand-written code. It was made with Codex + Claude over two weeks (part-time on the side). Having worked on ORMs previously, it would have taken me 4x-10x the time to get to the same state (which also has 100s of tests, with some repetitions). That's a massive…

I have tried several. Overall I've now set on strict TDD (which it still seems to not do unless I explicitly tell it to even though I have it as a hard requirement in claude.md).
Post reply on HN