Two things LLM coding agents are still bad at • Hacker News Board

Re: Two things LLM coding agents are still bad at

#191

Post by tom_ » Thu, Oct 09, 2025, 1:46 PM UTC

jeswin wrote: post #113

pprotas wrote: post #109

Earlier quoted context omitted.

I guess the interesting question is whether @jeswin could have created this project at all if AI tools were not involved. And if yes, would the quality even be better?

Very true. However, to claim that the "API looks completely different for Postgre and SQLite" is disingenuous. What was he looking at?

There are two examples on the landing page, and they both look quite different. Surely if the API is the same for both, there'd be just one example that covers both cases, or two examples would be deliberately made as identical as possible? (Like, just a different new somewhere, or different import directive at the top, and everything else exactly the same?) I think that's the point.

Perhaps experienced users of relevant technologies will just be able to automatically figure this stuff out, but this is a general discussion - people not terribly familiar with any of them, but curious about what a big pile of AI code might actually look like, could get the wrong impression.

Re: Two things LLM coding agents are still bad at

#192

Post by ravila4 » Thu, Oct 09, 2025, 1:48 PM UTC

Regarding copy-paste, I’ve been thinking the LLM could control a headless Neovim instance instead. It might take some specialized reinforcement learning to get a model that actually uses Vim correctly, but then it could issue precise commands for moving, replacing, or deleting text, instead of rewriting everything.

Even something as simple as renaming a variable is often safer and easier when done through the editor’s language server integration.

Re: Two things LLM coding agents are still bad at

#193

Post by NitpickLawyer » Thu, Oct 09, 2025, 1:48 PM UTC

Gazoche wrote: post #188

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…

> written by cc "in a loop" in ~3 months? What does that mean exactly? I assume the LLM was not left alone with its task for 3 months without human supervision.

From the FAQ:

> the following prompt was issued into a coding agent:

> Hey, can you make me a programming language like Golang but all the lexical keywords are swapped so they're Gen Z slang?

> and then the coding agent was left running AFK for months in a bash loop

Re: Two things LLM coding agents are still bad at

#194

Post by knes » Thu, Oct 09, 2025, 1:50 PM UTC

Leynos wrote: post #108

tjansen wrote: post #18

Agreed with the points in that article, but IMHO the no 1 issue is that agents only see a fraction of the code repository. They don't know whether there is a helper function they could use, so they re-implement it. When contributing to UIs, they can't check the whole UI to identify common design patterns, so they re-invent it. The most important task for the human using the agent is to provide the right context. "Loo…

I wonder if a large context model could be employed here via tool call. One of the great things Gemini chat can do is ingest a whole GitHub repo. Perhaps "before implementing a new utility or helper function, ask the not-invented-here tool if it's been done already in the codebase" Of course, now I have to check if someone has done this already.

This is what we do at Augmentcode.com.

We started with building the best code retrieval and build an agent around it.

Re: Two things LLM coding agents are still bad at

#195

Post by mehdibl » Thu, Oct 09, 2025, 1:52 PM UTC

You can do copy and paste if you offer it a tool/MCP that do that. It's not complicated using either function extraction with AST as target or line numbers.

Also if you want it to pause asking questions, you need to offer that thru tools (example Manus do that) and I have an MCP that do that and surprisingly I got a lot of questions and if you prompt, it will do. But the push currently is for full automation and that's why it's not there. We are far better in supervised step by step mode. There is elicitation already in MCP, but having a tool asking questions require you have a UI that will allow to set the input back.

Re: Two things LLM coding agents are still bad at

#196

Post by mehdibl » Thu, Oct 09, 2025, 1:54 PM UTC

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…

Errors are normal and happen ofter. You need to focus on providing it ability to test the changes and fix errors.

If you expect one shot you will get a lot of bad surprises.

Re: Two things LLM coding agents are still bad at

#197

Post by segmondy » Thu, Oct 09, 2025, 2:00 PM UTC

Someone has definitely fallen behind and has massive skill issues. Instead of learning you are wasting time writing bad takes on LLM. I hope most of you don't fall down this hole, you will be left behind.

Re: Two things LLM coding agents are still bad at

#198

Post by linsomniac » Thu, Oct 09, 2025, 2:00 PM UTC

>Sure, you can overengineer your prompt to try get them to ask more questions

That's not overengineering, that's engineering. "Ask clarifying questions before you start working", in my experience, has led to some fantastic questions, and is a useful tool even if you were to not have the AI tooling write any code. As a good programmer, you should know when you are handing the tool a complete spec to build the code and when the spec likely needs some clarification, so you can guide the tool to ask when necessary.

Re: Two things LLM coding agents are still bad at

#199

Post by ColonelPhantom » Thu, Oct 09, 2025, 2:00 PM UTC

hwillis wrote: post #148

tjansen wrote: post #18

Agreed with the points in that article, but IMHO the no 1 issue is that agents only see a fraction of the code repository. They don't know whether there is a helper function they could use, so they re-implement it. When contributing to UIs, they can't check the whole UI to identify common design patterns, so they re-invent it. The most important task for the human using the agent is to provide the right context. "Loo…

That's what claude.md etc are for. If you want it to follow your norms then you have to document them.

Well, sure, but from what I know, humans are way better at following 'implicit' instructions than LLMs. A human programmer can 'infer' most of the important basic rules from looking at the existing code, whereas all this agents.md/claude.md/whatever stuff seems necessary to even get basic performance in this regard.

Also, the agents.md website seems to mostly list README.md-style 'how do I run this instructions' in its example, not stylistic guidelines.

Furthermore, it would be nice if these agents add it themselves. With a human, you tell them "this is wrong, do it that way" and they would remember it. (Although this functionality seems to be worked on?)

Re: Two things LLM coding agents are still bad at

#200

Post by jamesjyu » Thu, Oct 09, 2025, 2:03 PM UTC

For #2, if you're working on a big feature, start with a markdown planning file that you and the LLM work on until you are satisfied with the approach. Doesn't need to be rocket science: even if it's just a couple paragraphs it's much better than doing it one shot.