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

691–700 of 829 posts

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

#691

Post by gilrain »

diavelguru wrote: post #491
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…

Love this. Responding to users. Detail info investigating. Action being taken (at least it seems so).

And all hidden in the comments of a niche forum, while the actual issue is closed and whitewashed? You got played.

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

#693

Post by Terretta »

taspeotis wrote: post #502
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…

Hi, thanks for Claude Code. I was wondering though if you'd considering adding a mode to make text green and characters come down from the top of the screen individually, like in The Matrix?

Ergonomics studies back in the day demonstrated amber beats green. Our shop spent extra for amber CRTs over green.

On MacOS Terminal, edit the Homebrew profile and set Text and Bold Text to Apple color Orange, consider setting Selection to Apple color Green and Cursor to Block, Blink, and Apple color Yellow.

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

#695

Post by hyperbovine »

rimliu wrote: post #679
bityard wrote: post #476

Earlier quoted context omitted.

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.

Ooh, I feel the burn. Care to elaborate? Are you just negging science in general, or ... ?

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

#697

Post by phyzome »

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.

LLMs are nondeterministic.

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

#698

Post by giancarlostoro »

theptip wrote: post #542
giancarlostoro wrote: post #516

Earlier quoted context omitted.

I only ever use high effort, the only thing I've run into sometimes I ask Claude to do every item on a list of items, and not stop until they're all done, it finishes maybe 80% of them then says "I've stopped doing things" for no reasonable reason. I don't need it to run for 18 hours nonstop, but 10 or 20 minutes more it would have kept going for wouldn't have hurt, especially when I am usually on Claude Code during…

I’ve been playing with /loop 5m check if you have any actionable tasks for this scenario.

Is that baked in?

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

#699

Post by torrienaylor »

Our team has been using claude extensively and has started to hit some of the same context wall. Specifically around knowledge transfer. Everyone is coding, including PMs and Design and the classic 1x1 and team stand-up rotation wasn't keeping up.

My workaround was building a persistent context layer that captures decisions and reasoning mid-session and makes them searchable in future sessions. Consider this a "Team Memory".

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

#700

Post by kenmacd »

nayroclade wrote: post #646
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…

Hey bcherny, I'm confused as to what's happening here. The linked issue was closed, with you seeming to imply there's no actual problem, people are just misunderstanding the hidden reasoning summaries and the change to the default effort level. But here you seem to be saying there is a bug, with adaptive reasoning under-allocating. Is this a separate issue from the linked one? If not, wouldn't it help to respond to t…

There's a 5 hour difference between the replies, and new data that came in, so the posts aren't really in conflict.

Also it doesn't sound like they know "there's a model issue", so opening it now would be premature. Maybe they just read it wrong, do better to let a few others verify first, then reopen.

Post reply on HN