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

671–680 of 829 posts

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

#671

Post by rimliu »

sigbottle wrote: post #193
bluegatty wrote: post #176

Earlier quoted context omitted.

We don't even know what 'creativity' is, and most humans I know are unable to be creative even when compelled to be. AI is 'creative enough' - whether we call it 'synthetic creativity' or whatever, it definitely can explore enough combinations and permutations that it's suitably novel. Maybe it won't produce 'deeply original works' - but it'll be good enough 99.99% of the time. The reliability issue is real. It may n…

I think the terminology is just dogshit in this area. LLMs are great semantic searchers and can reason decently well - I'm using them to self teach a lot of fields. But I inevitably reach a point where I come up with some new thoughts and it's not capable of keeping up and I start going to what real people are saying right now, today, and trust the LLM less and instead go to primary sources and real people. But I wou…

do they reason? Where was a video by AI researcher, that showed, that they do not reason but actually come with the result first and then try to invent "reasoning" to match it.

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

#672

Post by mlrtime »

stldev wrote: post #340
dc_giant wrote: post #246

Earlier quoted context omitted.

All right so what do I need to do so it does its job again? Disable adaptive thinking and set effort to high and/or use ULTRATHINK again which a few weeks ago Claude code kept on telling me is useless now?

You can't. This is Anthropic leveraging their dials, and ignoring their customers for weeks. Switch providers. Anecdotally, I've had no luck attempting to revert to prior behavior using either high/max level thinking (opus) or prompting. The web interface for me though doesn't seem problematic when using opus extended.

Agreed, the only feedback is switching... however things move fast. Unfortunately that means for me is subscribing or using API for many providers and then just switching models when one gets worse.

If you have a paid plan, you may need to pay for more than one, and "hopefully" the drop in usage (not income) is a good enough signal that there is a issue.

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

#673

Post by mlrtime »

ai_slop_hater wrote: post #410
ai_slop_hater wrote: post #383

Earlier quoted context omitted.

I read his comment and still replied. I think his claim that nobody reads thinking blocks and that thinking blocks increase latency is nonsense. I am not going to figure out which settings I need to enable because after reading this thread I cancelled my subscription and switched over to Codex. Because I had the exact same experience as many in this thread. Also what is that "PR advice"—he might as well wear a suit.…

Alright, I just tested that setting and it doesn't work. https://i.imgur.com/MYsDSOV.png I tested because I was porting memories from Claude Code to Codex, so I might as well test. I obviously still have subscription days remaining. There is another comment in this thread linking a GitHub issue that discusses this. The GitHub issue this whole HN submission is about even says that Anthropic hides thinking blocks.

How are you porting over your memories, skills, commands (codex doesn't have commands).

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

#674

Post by Jenk »

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…

Claude's settings don't appear to be in sync with the published settings schema[0].

[0]: https://www.schemastore.org/claude-code-settings.json.

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

#676

Post by rkangel »

mangatmodi wrote: post #630
bcherny wrote: post #461

Earlier quoted context omitted.

Thanks for the feedback IDs — read all 5 transcripts. On the model behavior: your sessions were sending effort=high on every request (confirmed in telemetry), so this isn't the effort default. The data points at adaptive thinking under-allocating reasoning on certain turns — the specific turns where it fabricated (stripe API version, git SHA suffix, apt package list) had zero reasoning emitted, while the turns with d…

I am curious. Are you able to see our session text based on the session ID? That was big no in some of the tier-1 places I worked. No employee could see user texts.

IIRC for Enterprise, using /feedback or /bug is an exception to the "we promise not to use your data" agreement.

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

#677

Post by entrep »

armchairhacker wrote: post #134

Yet https://marginlab.ai/trackers/claude-code/ says no issue. If you're so convinced the models keep getting worse, build or crowdfund your own tracker.

One could argue that subscription based inference might differ from per-token billed API usage.

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

#678

Post by hakanderyal »

foltik wrote: post #555
latentsea wrote: post #489

Earlier quoted context omitted.

This should be part of the system prompt. It's absolutely unacceptable to just to not at least try to investigate failures like this. I absolutely hate when it reaches this conclusion on its own and just continues on as if it's doing valid work.

Based on the recent leaks, their system prompt explicitly nudges the model not to do anything outside of what was asked. That could very well explain why it’s not fixing preexisting broken tests. “Don't add features, refactor code, or make "improvements" beyond what was asked.” https://www.dbreunig.com/2026/04/04/how-claude-code-builds-a...

And it's very valid. Because otherwise you would ask Claude to trim a tree and it would go raze the whole forest and plant new seeds. This was the primary pain point last year, especially with Sonnet.

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

#679

Post by rimliu »

bityard wrote: post #476
hyperbovine wrote: post #432

Earlier quoted context omitted.

The only regularity I can discern in contemporary online debates about LLMs is that for every viewpoint expressed, with probability one someone else will write in with the diametrically opposite experience. Today it’s my turn to be that person. Large scientific code base with a bunch of nontrivial, handwritten modules accomplishing distinct, but structurally similar in terms of the underlying computation, tasks. Poin…

Thanks for the counterpoint, interesting to hear that things are better than I have experienced so far. :)

they are not. "scientific code" should give you a hint.

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

#680

Post by k9294 »

Anecdotally, I’ve been seeing a lot of weird behavior from Opus when it decides, mid-execution, to switch to a different "simpler" solution, and that really pissed me off.

At one point, I carefully designed a spec document, forced Opus to reread it, create a plan with the planning tool that followed the spec, and use the task tool to track the implementation... AND AFTER OPUS READS THE FIRST FUCKING FILE, it says, "Oh, there are missing dependencies in project X. It’ll be hard to add them, so I’m going to throw away the whole plan and just do a simple fix..."

After that, I canceled my $200 Max plan, which I’d been subscribed to since June 2025, and decided to check out Codex

Post reply on HN