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

Issue: Claude Code is unusable for complex engineering tasks with Feb updates

github.com

Post reply on HN
Print view View original

631–640 of 829 posts

Re: Issue: Claude Code is unusable for complex engineering tasks with Feb updates

#631

Post by jacquesm »

matheusmoreira wrote: post #562
jacquesm wrote: post #549

Earlier quoted context omitted.

I can see how that works: this is like building a dependency, a habit if you wish. I think the tighter you couple your workflow to these tools the more dependent you will become and the greater the let-down if and when they fail. And they will always fail, it just depends on how long you work with them and how complex the stuff is you are doing, sooner or later you will run into the limitations of the tooling. One wa…

Good advice about the dependency. This stuff is definitely addictive. I've been in something of a manic episode ever since I subscribed to this thing. I started getting anxious when I hit limits. I wouldn't say that Claude is failing though. It's just that they're clearly messing with it. The real Opus is great.

Take good care of yourself and don't get sucked in too deep. I can see the danger just as clearly in programmers around me (and in myself). I keep a very strict separation between anything that can do AI and my main computer, no cutting-and-pasting and no agents. I write code because I understand what I'm doing and if I do not understand the interaction then I don't use it. I see every session with an AI chatbot as totally disposable. No long term attachment means I can stand alone any time I want to. It may not be as fast but I never have the feeling that I'm not 100% in control.

Re: Issue: Claude Code is unusable for complex engineering tasks with Feb updates

#632

Post by itemize123 »

nrds wrote: post #91
riskassessment wrote: post #67

Earlier quoted context omitted.

Stealthily degrade the model or stealthily constrain the model with a tighter harness? These coding tools like Claude Code were created to overcome the shortcomings of last year's models. Models have gotten better but the harnesses have not been rebuilt from scratch to reflect improved planning and tool use inherent to newer models. I do wonder how much all the engineering put into these coding tools may actually in…

I've been using pi.dev since December. The only significant change to the harness in that time which affects my usage is the availability of parallel tool calls. Yet Claude models have become unusable in the past month for many of the reasons observed here. Conclusion: it's not the harness. I tend to agree about the legacy workarounds being actively harmful though. I tried out Zed agent for a while and I was SHOCKED…

you find that pay-per-use API's degraded too?

Re: Issue: Claude Code is unusable for complex engineering tasks with Feb updates

#633

Post by zernie »

fer wrote: post #64

Called it 10 days ago: https://news.ycombinator.com/item?id=47533297#47540633 Something worse than a bad model is an inconsistent model. One can't gauge to what extent to trust the output, even for the simplest instructions, hence everything must be reviewed with intensity which is exhausting. I jumped on Max because it was worth it but I guess I'll have to cancel this garbage.

This is why you should never ever trust an AI coding agent to produce good code.

Use it to set up the strictest possible custom linting rules.

Re: Issue: Claude Code is unusable for complex engineering tasks with Feb updates

#635

Post by pbowyer »

dev_l1x_be wrote: post #419
murkt wrote: post #392

Earlier quoted context omitted.

Was there a change in Claude Code system prompt at that time that nudges Claude into simplistic thinking? Here is a gist that tries to patch the system prompt to make Claude behave better https://gist.github.com/roman01la/483d1db15043018096ac3babf5... I haven’t personally tried it yet. I do certainly battle Claude quite a lot with “no I don’t want quick-n-easy wrong solution just because it’s two lines of code, I wan…

Holy sweet LLM, this gist is crazy. Why did they do this to themselves? I am going to try this at home, it might actually fix Claude.

Let us know if it does, because we all want it to work :)

Re: Issue: Claude Code is unusable for complex engineering tasks with Feb updates

#636

Post by andersa »

murkt wrote: post #392
bcherny wrote: post #234

Earlier quoted context omitted.

When you submit a /bug we get a way to see the contents of the conversation. We don't see anything else in your codebase.

Was there a change in Claude Code system prompt at that time that nudges Claude into simplistic thinking? Here is a gist that tries to patch the system prompt to make Claude behave better https://gist.github.com/roman01la/483d1db15043018096ac3babf5... I haven’t personally tried it yet. I do certainly battle Claude quite a lot with “no I don’t want quick-n-easy wrong solution just because it’s two lines of code, I wan…

I didn't know we could change the base system prompt of Claude Code. Just tried, and indeed it works. This changes everything! Thank you for posting this!

Re: Issue: Claude Code is unusable for complex engineering tasks with Feb updates

#637

Post by xnorswap »

jen729w wrote: post #588
dinobones wrote: post #579

Earlier quoted context omitted.

Wait, the linter re-ordered the file. Let me restore it to the previous state. whisper: There is no linter.

Those test failures are pre-existing. We're all done!

Wait, I should check if they pre-exist on master.

Re: Issue: Claude Code is unusable for complex engineering tasks with Feb updates

#638

Post by itemize123 »

bityard wrote: post #81

The assertion in the issue report is that Claude saw a sharp decline in quality over the last few months. However, the report itself was allegedly generated by Claude. Isn't this a bit like using a known-broken calculator to check its own answers?

if it's not broken then we trust the assertion that it's broken. if it's broken then it's broken.

it's analysis of what is broken is probably wrong or at least incomplete though

Re: Issue: Claude Code is unusable for complex engineering tasks with Feb updates

#639

Post by zkmon »

In general, I never allowed Claude to manage the complexity. Claude is fantastic coder, but very bad at higher level work. I engage gemini or qwen top models for anything that happens before getting to write code. Claude gets a very strict and elaborate requirement and design spec that it need to execute without any variation.

Claude could get too much creative and bloat it's way for non-coding tasks, as these tasks cannot be "sandboxed" with full specs as it can be done for coding.

Re: Issue: Claude Code is unusable for complex engineering tasks with Feb updates

#640

Post by otabdeveloper4 »

lukewarm707 wrote: post #447
TonyAlicea10 wrote: post #333

Earlier quoted context omitted.

I've noticed this as well. "Now you should stop X and go do Y" is a phrase I see repeated a lot. Claude seems primed to instruct me to stop using it.

as someone who uses deepseek, glm and kimi models exclusively, an llm telling me what to do is just off the wall glm and kimi in particular, they can't stop writing... seriously very eager to please. always finishing with fireworks emoji and saying how pleased it is with the test working. i have to say to write less documentation and simplify their code.

LLMs are next token predictors. Outputting tokens is what they do, and the natural steady-state for them is an infinite loop of endlessly generated tokens.

You need to train them on a special "stop token" to get them to act more human. (Whether explicitly in post-training or with system prompt hacks.)

This isn't a general solution to the problem and likely there will never be one.

Post reply on HN