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

41–50 of 829 posts

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

#41

Post by pixel_popping »

summarity wrote: post #8

Not claude code specific, but I've been noticing this on Opus 4.6 models through Copilot and others as well. Whenever the phrase "simplest fix" appears, it's time to pull the emergency break. This has gotten much, much worse over the past few weeks. It will produce completely useless code, knowingly (because up to that phrase the reasoning was correct) breaking things. Today another thing started happening which are…

It's a bit insane that they can't figure out a cryptographic way for the delivery of the Claude Code Token, what's the point of going online to validate the OAuth AFTER being issued the code, can't they use signatures?

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

#43

Post by 01284a7e »

matheusmoreira wrote: post #33

That analysis is pretty brutal. It's very disconcerting that they can sell access to a high quality model then just stealthily degrade it over time, effectively pulling the rug from under their customers.

Seems like the logical conclusion, no matter what.

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

#44

Post by pixel_popping »

giwook wrote: post #40
summarity wrote: post #8

Not claude code specific, but I've been noticing this on Opus 4.6 models through Copilot and others as well. Whenever the phrase "simplest fix" appears, it's time to pull the emergency break. This has gotten much, much worse over the past few weeks. It will produce completely useless code, knowingly (because up to that phrase the reasoning was correct) breaking things. Today another thing started happening which are…

I think in general we need to be highly critical of anything LLMs tell us.

Claude code shows: OAuth error: timeout of 15000ms exceeded

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

#45

Post by me_vinayakakv »

mikepurvis wrote: post #37
summarity wrote: post #8

Not claude code specific, but I've been noticing this on Opus 4.6 models through Copilot and others as well. Whenever the phrase "simplest fix" appears, it's time to pull the emergency break. This has gotten much, much worse over the past few weeks. It will produce completely useless code, knowingly (because up to that phrase the reasoning was correct) breaking things. Today another thing started happening which are…

That helps explain why my sessions signed themselves out and won't log back in.

I just experienced this some time ago and could not sign in still.

Their status page shows everything is okay.

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

#46

Post by 8note »

giwook wrote: post #32

I wonder how much of this is simply needing to adapt one's workflows to models as they evolve and how much of this is actual degradation of the model, whether it's due to a version change or it's at the inference level. Also, everyone has a different workflow. I can't say that I've noticed a meaningful change in Claude Code quality in a project I've been working on for a while now. It's an LLM in the end, and even wi…

I've noticed a strong degradation as its started doing more skill like things and writing more one off python scripts rather than using tools.

the agent has a set of scripts that are well tested, but instead it chooses to write a new bespoke script everytime it needs to do something, and as a result writes both the same bugs over and over again, and also unique new bugs every time as well.

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

#47

Post by mrcwinn »

adonese wrote: post #42

Things had went downhill since they removed ultrathink /s

Ultrathink isn’t “removed.” Its behavior is different. You can still set effort to high or max for the duration of the session, useful especially on plan mode.

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

#48

Post by rzmmm »

Retr0id wrote: post #17

This seems anecdotal but with extra words. I'm fairly sure this is just the "wow this is so much better than the previous-gen model" effect wearing off.

I suspect you might be right but I don't really know. Wouldn't these proposed regressions be trivial to confirm with benchmarks?

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

#49

Post by salawat »

cute_boi wrote: post #20
_V_ wrote: post #16

[flagged]

Specially this openclaw which is almost chocking my website to death. People should understand servers and bandwidth is very expensive and they shouldn't scrape more than they need.

Most of us did. Then instead of people getting indoc'd by doing, we handed them AI that never asks questions or says no, leading to the script-kiddie effect at massive scale. Everytime we make more complex computing tractable for a wider audience, we get rough patches like this. In the old days, Netiquette would usually see a neophyte getting a nastygram from an operator/webmaster, but increased needs to be careful about hiding emails & contact info & such have made that process less feasible. Welcome to Eternal September on steroids.

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

#50

Post by giwook »

pixel_popping wrote: post #44
giwook wrote: post #40

Earlier quoted context omitted.

I think in general we need to be highly critical of anything LLMs tell us.

Claude code shows: OAuth error: timeout of 15000ms exceeded

Maybe a local or intermittent issue? Working for me.
Post reply on HN