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

621–630 of 829 posts

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

#621

Post by pjc50 »

xvector wrote: post #564
libraryofbabel wrote: post #533

Earlier quoted context omitted.

That's interesting research, but I think a more important reason that you don't have access to them (not even via the bare Anthropic api) is to prevent distillation of the model by competitors (using the output of Anthropic's model to help train a new model).

If distilled models were commercially banned they'd probably be willing to show the thinking again.

Intellectual property rights in models? But then wouldn't the model maker have to pay for all the training IP?

(just kidding, I know that the legal rule for IP disputes is "party with more money wins")

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

#622

Post by Sayrus »

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…

> If you are analyzing locally stored transcripts, you wouldn't see raw thinking stored when this header is set, which is likely influencing the analysis. When Claude sees lack of thinking in transcripts for this analysis, it may not realize that the thinking is still there, and is simply not user-facing.

Claude often fetches past transcript for information after compaction. Wouldn't this effectively distort the view it has of past discussions?

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

#623

Post by withinboredom »

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…

Is there not a setting to change the system prompt itself? I vaguely remember seeing it in the docs.

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

#624

Post by withinboredom »

taylorfinley wrote: post #465
stefan_ wrote: post #382

Earlier quoted context omitted.

Theres also been tons of thinking leaking into the actual output. Recently it even added thinking into a code patch it did (a[0] &= ~(1 << 2); // actually let me just rewrite { .. 5 more lines setting a[0] .. }).

I've seen this frequently also

I suspect it happens when the model's adaptive thinking was too conservative and it could have thought more, but didn't.

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

#625

Post by subscribed »

HumanOstrich wrote: post #471
nickvec wrote: post #357

Earlier quoted context omitted.

Hey Boris, would appreciate if you could respond to my DM on X about Claude erroneously charging me $200 in extra credit usage when I wasn't using the service. Haven't heard back from Claude Support in over a month and I am getting a bit frustrated.

Did the receipt show it as being a gift? There's a lot of fraud happening the past few months with Claude Code Gift purchases. Anthropic support is ignoring all of it and just not responding to support requests. Happened to a close friend of mine. A bit of digging revealed the same pattern with fraudulent gift purchases for several other people before I stopped looking. They were also being ignored by Anthropic suppo…

Still, its on Anthropic to respond to it.

When a third party leaked my CC number which then was used to buy Spotify premium, all it took was 10 minutes of chat with a very polite support agent to have it resolved.

Ignoring the customer is not going to fix it. They'd know if they asked Claude.

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

#626

Post by saidnooneever »

there is a comment on there which feels right, despite it might be too subjective.

Ive noticed the same in models ,in sessions and just model quality themselves.. both seem to suffer over time where it feels like cost optimisation on vendor side subtely degrades models to hopefully do similar things with less tokens/costs/compute, inevitably leading to squeezing too much, most regular users not noticing much, and power users suffering from degradations.

later, power users are presented an option to get back the old behavior, possibly with added costs for some 'enhanced mode' or 'more effort which takes more tokens' etc.

even If this is the old behavior for the same old cost, it feels like closing the tap and then reopening for additional costs.

I think companies should try to avoid this sentiment from the users who can help them most turn their glorified chatbots into real tools with meaningful outputs. (ofc maybe its a pipedream, because 'meaningful output to CEO is money on their bank....)

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

#627

Post by saidnooneever »

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…

did the cost go up, or did you lower costs (token consumptions) for all users and then now want to default enterprise/teams back to normal mode. Because it seems like a long way aroundabout to say now it will cost more for same quality.

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

#628

Post by subscribed »

niteshpant wrote: post #484
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…

I added `CLAUDE_CODE_EFFORT_LEVEL=max` to my shell's env so that every session is always effort:max by default :)

Why would I use Claude otherwise anyway! :)

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

#629

Post by Jweb_Guru »

jgrahamc wrote: post #3
StanAngeloff wrote: post #2

(Being true to the HN guidelines, I’ve used the title exactly as seen on the GitHub issue) I was wondering if anyone else is also experiencing this? I have personally found that I have to add more and more CLAUDE.md guide rails, and my CLAUDE.md files have been exploding since around mid-March, to the point where I actually started looking for information online and for other people collaborating my personal observat…

What I've noticed is that whenever Claude says something like "the simplest fix is..." it's usually suggesting some horrible hack. And whenever I see that I go straight to the code it wants to write and challenge it.

Yup. Every single time it's about to do the dumbest thing I've seen in my life.

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

#630

Post by mangatmodi »

bcherny wrote: post #461
JamesSwift wrote: post #397

Earlier quoted context omitted.

a9284923-141a-434a-bfbb-52de7329861d d48d5a68-82cd-4988-b95c-c8c034003cd0 5c236e02-16ea-42b1-b935-3a6a768e3655 22e09356-08ce-4b2c-a8fd-596d818b1e8a 4cb894f7-c3ed-4b8d-86c6-0242200ea333 Amusingly (not really), this is me trying to get sessions to resume to then get feedback ids and it being an absolute chore to get it to give me the commands to resume these conversations but it keeps messing things up: cf764035-0a1d-4…

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.
Post reply on HN