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

821–829 of 829 posts

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

#821

Post by liamsfr »

unsupp0rted wrote: post #668
nayroclade wrote: post #646

Earlier quoted context omitted.

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…

It's better PR to close issues and tell users they're holding it wrong, and meanwhile quietly fix the issue in the background. Also possibly safer for legal reasons.

Isn’t that what they just did here? Close Stella’s Issue, cross post to hn, then completely sidestep an observation users are making, and attack the analyst of transcripts with a straw man attack blaming… thinking summaries….

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

#822

Post by liamsfr »

Avamander wrote: post #427
murkt wrote: post #392

Earlier quoted context omitted.

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…

That Gist does explain quite a few flaws Claude has. I wonder if MEMORY.md is sufficient to counteract the prompt without patching.

And if memory.md can’t and you need something quick and dirty for flat memory management, I wrote a plugin just for this.

https://github.com/NominexHQ/pmm-plugin

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

#825

Post by airstrike »

robeym wrote: post #707
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…

This is confusing. ULTRATHINK is a step below /effort max? ULTRATHINK triggers high effort. /effort max is above high. Calling it ULTRATHINK sounds like it would be the highest mode. If someone has max set and types ULTRATHINK, they're lowering their effort for that turn. For anyone reading this trying to fix the quality issues, here's what I landed on in ~/.claude/settings.json: { "env": { "CLAUDE_CODE_EFFORT_LEVEL"…

Whaaa this is insanely stupid from their part.

Also I'm curious if telling subagents to ultrathink has any impact.

I guess I can always ask a friend of mine to read the source...

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

#827

Post by grey-area »

brainwad wrote: post #796
grey-area wrote: post #738

Earlier quoted context omitted.

As you can see from posts on this story, most people believe it reflects what the model is thinking and use it as a guide to that so they can ‘correct’ it. If it is not in fact chain of thought or thinking it should not be called that.

It is the same with human chain of thought, though. Both of them are post-hoc rationalisations justifying "gut feelings" that come from thought processes the human/agent doesn't have introspection into. And yet asking humans or machines to "think out loud" this way does increase the quality of their work.

I disagree - humans often reason in a series of steps, and can write these down before they've reached an answer. They don't always wait till they reach a conclusion (with no self-insight into how they did so) and then retrospectively generate a plausible answer as LLMs do.

In mathematical proofs they may guess and answer and then work out a proof, but that is a different process.

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

#829

Post by macformula2gx »

Claude is great I really love it but keen to know will you ever have one plan and one history / context across all the different tools you have ? agents on cloud - platform console, cli, desktop(chat+code+cowork), claude.ai, chrome addons ? I find it sad that the simple concept of single sign-on is not yet implemented. The history of conversations is not across all conversations. the choice of model switch in between or automatically is not there. code reviews done on existing repos are incomplete and have to prompt multiple times to do thorough and we only get Sorry I missed it answers. Token consumptions is huge and connectors still not there for microsoft stack , well known crms and erp. and you need to oay seperatrlt for api versus platform versus others. there - I said it ;) Hoping the next version will be truly for developers .
Post reply on HN