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

31–40 of 382 posts

Re: Two things LLM coding agents are still bad at

#31

Post by ziotom78 »

I fully resonate with point #2. A few days ago, I was stuck trying to implement some feature in a C++ library, so I used ChatGPT for brainstorming.

ChatGPT proposed a few ideas, all apparently reasonable, and then it advocated for one that was presented unambiguously as the "best". After a few iterations, I realized that its solution would have required a class hierarchy where the base class contained a templated virtual function, which is not allowed in C++. I pointed this out to ChatGPT and asked it to rethink the solution; it then immediately advocated for the other approach it had initially suggested.

Re: Two things LLM coding agents are still bad at

#32

Post by athrowaway3z »

sxp wrote: post #30

Another place where LLMs have a problem is when you ask them to do something that can't be done via duct taping a bunch of Stack Overflow posts together. E.g, I've been vibe coding in Typescript on Deno recently. For various reasons, I didn't want to use the standard Express + Node stack which is what most LLMs seem to prefer for web apps. So I ran into issues with Replit and Gemini failing to handle the subtle diffe…

>But Three.js does support GL_TRIANGLE_STRIP rendering for architectural reasons.

Typo or trolling the next LLM to index HN comments?

Re: Two things LLM coding agents are still bad at

#33

Post by pimeys »

Vipsy wrote: post #21

Coding agents tend to assume that the development environment is static and predictable, but real codebases are full of subtle, moving parts - tooling versions, custom scripts, CI quirks, and non-standard file layouts. Many agents break down not because the code is too complex, but because invisible, “boring” infrastructure details trip them up. Human developers subconsciously navigate these pitfalls using tribal mem…

Yep. One of the things I've found agents always having a lot of trouble with is anything related to OpenTelemetry. There's a thing you call that uses some global somewhere, there's a docker container or two and there's the timing issues. It takes multiple tries to get anything right. Of course this is hard for a human too if you haven't used otel before...

Re: Two things LLM coding agents are still bad at

#34

Post by freetonik »

I see a pattern in these discussions all the time: some people say how very, very good LLMs are, and others say how LLMs fail miserably; almost always the first group presents examples of simple CRUD apps, frontend "represent data using some JS-framework" kind of tasks, while the second group presents examples of non-trivial refactoring, stuff like parsers (in this thread), algorithms that can't be found in leetcode, etc.

Tech twitter keeps showing "one-shotting full-stack apps" or "games", and it's always something extremely banal. It's impressive that a computer can do it on its own, don't get me wrong, but it was trivial to programmers, and now it is commoditized.

Re: Two things LLM coding agents are still bad at

#36

Post by sidgtm »

As a UX designer I see they lack the ability of being opinionated about a design piece and go with the standard mental model. I got fed up with this and made a simple java script code to run a simple canvas on the localhost to pass on more subjective feedback using highlights and notes feature. I tried using playwright first but a. its token heavy b. it's still for finding what's working or breaking instead of thinking deeply about the design.

Re: Two things LLM coding agents are still bad at

#37

Post by rossant »

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 worked. Fourth one worked. So far so good. Then I tried the last four. Perfect.

Just to be sure, I proceeded with the fifth one. 404. Huh. Weird. The domain was correct though and the URL seemed reasonable.

I tried the other 31 links. ALL of them 404ed. I was totally confused. The domain was always correct. It seemed highly suspicious that all websites would have had moved internal URLs at the same time. I didn't even remember that this part of the code had gone through an LLM.

Fortunately, I could retrieve the old URLs on old git commits. I checked the URLs carefully. The LLM had HALLUCINATED most of the path part of the URLs! Replacing things like domain.com/this-article-is-about-foobar-123456/ by domain.com/foobar-is-so-great-162543/...

These kinds of very subtle and silently introduced mistakes are quite dangerous. Be careful out there!

Re: Two things LLM coding agents are still bad at

#38

Post by juped »

It's apparently lese-Copilot to suggest this these days, but you can find very good hypothesizing and problem solving if you talk conversationally to Claude or probably any of its friends that isn't the terminally personality-collapsed SlopGPT (with or without showing it code, or diagrams); it's actually what they're best at, and often they're even less likely than human interlocutors to just parrot some set phrase at you.

It's only when you take the tech out of the area it's good at and start trying to get it to "write code" or even worse "be an agent" that it starts cracking up and emitting garbage; this is only done because companies want to forcememe some kind of product besides "chatbot", whether or not it makes sense. It's a shame because it'll happily and effectively write the docs that don't exist but you wish did for more or less anything. (Writing code examples for docs is not a weak point at all.)

Re: Two things LLM coding agents are still bad at

#39

Post by throw-10-8 »

nxpnsv wrote: post #35
throw-10-8 wrote: post #23

3. Saying no LLMs will gladly go along with bad ideas that any reasonable dev would shoot down.

Agree, this is really bad.

It's a fundamental failing of trying to use a statistical approximation of human language to generate code.

You can't fix it.

Re: Two things LLM coding agents are still bad at

#40

Post by pimeys »

throw-10-8 wrote: post #23

3. Saying no LLMs will gladly go along with bad ideas that any reasonable dev would shoot down.

I've found codex to be better here than Claude. It has stopped many times and said hey you might be wrong. Of course this changes with a larger context.

Claude is just chirping away "You're absolutely right" and making me to turn on caps lock when I talk to it and it's not even noon yet.

Post reply on HN