Issue: Claude Code is unusable for complex engineering tasks with Feb updates • Hacker News Board

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

#241

Post by root_axis » Mon, Apr 06, 2026, 6:14 PM UTC

simooooo wrote: post #202

summarity wrote: post #8

Not claude code specific, but I've been noticing this on Opus 4.6 models through Copilot and others as well. Whenever the phrase "simplest fix" appears, it's time to pull the emergency break. This has gotten much, much worse over the past few weeks. It will produce completely useless code, knowingly (because up to that phrase the reasoning was correct) breaking things. Today another thing started happening which are…

How complex are we talking? I one shotted a game boy emulator in <6 minutes today

There are countless reference examples online, that's just a slower, buggier, and more expensive git clone.

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

#242

Post by starkparker » Mon, Apr 06, 2026, 6:15 PM UTC

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…

> You can also use the ULTRATHINK keyword to use high effort for a single turn

First I've heard that ultrathink was back. Much quieter walkback of https://decodeclaude.com/ultrathink-deprecated/

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

#243

Post by bcherny » Mon, Apr 06, 2026, 6:15 PM UTC

DennisL123 wrote: post #240

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…

Happy to have my mind changed, yet I am not 100% convinced closing the issue as completed captures the feedback.

From the contents of the issue, this seems like a fairly clear default effort issue. Would love your input if there's something specific that you think is unaddressed.

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

#244

Post by jfim » Mon, Apr 06, 2026, 6:16 PM UTC

nrds wrote: post #91

riskassessment wrote: post #67

Earlier quoted context omitted.

Stealthily degrade the model or stealthily constrain the model with a tighter harness? These coding tools like Claude Code were created to overcome the shortcomings of last year's models. Models have gotten better but the harnesses have not been rebuilt from scratch to reflect improved planning and tool use inherent to newer models. I do wonder how much all the engineering put into these coding tools may actually in…

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…

Out of curiosity, what can parallel tool calls do that one can't do with parallel subagents and background processes?

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

#245

Post by plexicle » Mon, Apr 06, 2026, 6:16 PM UTC

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…

Ultrathink is back? I thought that wasn't a thing anymore.

If I am following.. "Max" is above "High", but you can't set it to "Max" as a default. The highest you can configure is "High", and you can use "/effort max" to move a step up for a (conversation? session?), or "ultrathink" somewhere in the prompt to move a step up for a single turn. Is this accurate?

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

#246

Post by dc_giant » Mon, Apr 06, 2026, 6:17 PM UTC

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…

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?

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

#247

Post by tatrions » Mon, Apr 06, 2026, 6:17 PM UTC

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…

[flagged]

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

#248

Post by capnchaos » Mon, Apr 06, 2026, 6:17 PM UTC

bcherny wrote: post #220

aizk wrote: post #214

Earlier quoted context omitted.

How do you guys manage regressions as a whole with every new model update? A massive test set of e2e problem solving seeing how the models compare?

A mix of evals and vibes.

Are you doing any Digital Twin testing or simulations? I imagine you can't test a product like Claude Code using traditional means.

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

#249

Post by koverstreet » Mon, Apr 06, 2026, 6:18 PM UTC

bcherny wrote: post #219

koverstreet wrote: post #217

Earlier quoted context omitted.

There's been more going on than just the default to medium level thinking - I'll echo what others are saying, even on high effort there's been a very significant increase in "rush to completion" behavior.

Thanks for the feedback. To make it actionable, would you mind running /bug the next time you see it and posting the feedback id here? That way we can debug and see if there's an issue, or if it's within variance.

I'll have a look. The CoT switch you mentioned will help, I'll take a look at that too, but my suspicion is that this isn't a CoT issue - it's a model preference issue.

Comparing Opus vs. Qwen 27b on similar problems, Opus is sharper and more effective at implementation - but will flat out ignore issues and insist "everything is fine" that Qwen is able to spot and demonstrate solid understanding of. Opus understands the issues perfectly well, it just avoids them.

This correlates with what I've observed about the underlying personalities (and you guys put out a paper the other day that shows you guys are starting to understand it in these terms - functionally modeling feelings in models). On the whole Opus is very stable personality wise and an effective thinker, I want to complement you guys on that, and it definitely contrasts with behaviors I've seen from OpenAI. But when I do see Opus miss things that it should get, it seems to be a combination of avoidant tendencies and too much of a push to "just get it done and move into the next task" from RHLF.

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

#250

Post by bcherny » Mon, Apr 06, 2026, 6:18 PM UTC

tatrions wrote: post #247

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…

[flagged]

Yep totally -- think of this as "maximum effort". If a task doesn't need a lot of thinking tokens, then the model will choose a lower effort level for the task.