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

801–810 of 829 posts

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

#801

Post by sigbottle »

germandiago wrote: post #793
sigbottle wrote: post #788

Earlier quoted context omitted.

I mean humans do that too, and I don't think it's very unjustified. The "we deduce from a deep base premise P down a chain of inferences" picture is extremely incomplete and has been challenged all over the place - by normal people, by analytic and continental philosophers, by science itself, etc. Not trying to say that LLM's are equivalent to humans but that the concept of reasoning is undefined. And the fact that t…

But humans verify things. AI just fools you and I would say it is the biggest problem.I have with AIs. They give me stuff that I do not know whether to trust or not and what surprises I will find down the way later. So now my task is to review everything, remove cruft. It starts to compete against investing my time to deep-think and do it thoughtfully from the get go and come up with something simpler, with less code…

I mean yeah ultimately it's a tool and I've even leaned off of AI recently for coding because it was exhausting dealing with all its hallucinations

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

#802

Post by andoando »

frog437 wrote: post #494
andoando wrote: post #482

Earlier quoted context omitted.

Isnt the codebase in the context window?

depending on how large your codebase is, hopefully not. At this point use something like the IX plugin to ingest codebase and track context, rather than from the LLM itself.

I mean whatever part of the code that is read by the AI has to be in the content window at some point or another nSprewd throughout your sessions Id think even with a huge codebase, 90% of it is going to be there

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

#803

Post by dmboyd »

brainwad wrote: post #572
grey-area wrote: post #523

Earlier quoted context omitted.

So like many of the promises from AI companies, reported chain of thought is not actually true (see results below). I suppose this is unsurprising given how they function. Is chain of thought even added to the context or is it extraneous babble providing a plausible post-hoc justification? People certainly seem to treat it as it is presented, as a series of logical steps leading to an answer. ‘After checking that the…

I mean, obviously, it's not going to be a faithful representation of the actual thinking. The model isn't aware of how it thinks any more than you are aware how your neurons fire. But it does quantitatively improve performance on complex tasks.

if its not a faithful representation of the actual thinking, why would they be scared of people distilling against it

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

#804

Post by brainwad »

dmboyd wrote: post #803
brainwad wrote: post #572

Earlier quoted context omitted.

I mean, obviously, it's not going to be a faithful representation of the actual thinking. The model isn't aware of how it thinks any more than you are aware how your neurons fire. But it does quantitatively improve performance on complex tasks.

if its not a faithful representation of the actual thinking, why would they be scared of people distilling against it

Because even though it's not representative of the actual thought process, chain of thought improves model performance.

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

#805

Post by hansmayer »

axegon_ wrote: post #681
hansmayer wrote: post #607

Earlier quoted context omitted.

You guys realise you are about 3 months into another one of your CEOs announcements that AI would "write all code in 6 months", right? Based on the problems you are facing, would you say your CEO gave a realistic announcement this time around ?

Almost as if every CEO is making promises and predictions that either exist solely in their heads or know full well that the odds of this working out are about the same as finding the fountain of youth and are just milking whatever cash they can out of the hype.

Well, there is a ton of normal CEOs of "normal" companies doing a great job, due diligence and all. Its just these weird CEOs of weird companies with weird business models, who burn hundreds of billions of dollars to produce effectively peanuts, that make a lot of decent CEOs look bad.

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

#806

Post by aibuthuman »

bcherny wrote: post #209

Hey all, Boris from the Claude Code team here. I just responded on the issue, and cross-posting here for input. --- Hi, thanks for the detailed analysis. Before I keep going, I wanted to say I appreciate the depth of thinking & care that went into this. There's a lot here, I will try to break it down a bit. These are the two core things happening: > `redact-thinking-2026-02-12` This beta header hides thinking from th…

[dead]

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

#807

Post by alexclapp »

sixothree wrote: post #142
StanAngeloff wrote: post #4

Earlier quoted context omitted.

That is the kind of thing that I've been fighting by being super explicit in CLAUDE.md. For whatever reason, instead of being much more thorough and making sure that files are being changed only after fully understanding the scope of the change (behaviour prior to Feb/Mar), Claude would just jump to the easiest fix now, with no backwards compatibility thinking and to hell with all existing tests. What is even worse i…

Superpowers, Serena, Context7 feel like requried plugins to me. Serena in particular feels like a secret weapon sometimes. But superpowers (with "brainstorm" keyword) might be the thing that helps people complaining about quality issues.

[dead]

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

#809

Post by nrds »

itemize123 wrote: post #632
nrds wrote: post #91

Earlier quoted context omitted.

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?

Yes, absolutely.

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

#810

Post by olejorgenb »

kouteiheika wrote: post #798
olejorgenb wrote: post #784

Earlier quoted context omitted.

So this means I can not resume a session older than 30 days properly?

I have no idea; you have to check their docs. AFAIK what they do is that they calculate a hash of the true thinking trace, save it into a database, and only send those hashes back to you (try to man-in-the-middle Claude Code and you'll see those hashes). So then when you send then back your session's history you include those hashes, they look them up in their database, replace them with the real thinking trace, and…

I see. If that's just hashes and not encrypted content I can't see how they can resume old sessions properly. IIRC they have a 30 days retention policy and surely the thinking traces must be considered data. Wonder how this works with the zero-retention enterprise plans...
Post reply on HN