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

551–560 of 829 posts

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

#551

Post by CjHuber »

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 honestly am very disappointed with this. I've only learned about CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING and showThinkingSummaries: true from this post. I've been wondering for a while where the summaries went and am always hoping like roulette that it thinks a lot. No wonder if there suddently is an "adaptive thinking" mode. I would have opted out 2 months ago if it was documented or communicated in any way publicly. Why change behavior without notice or any new user facing settings.

I just googled "CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING" and it seems like many people don't know about it.

And ULTRATHINK sets the effort to high, but then there is also /effort max?

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

#552

Post by jeremyjh »

Majromax wrote: post #314
noxa wrote: post #179

I'm the author of the report in there. The stop-phrase-guard didn't get attached but here it is: https://gist.github.com/benvanik/ee00bd1b6c9154d6545c63e06a3... You can watch for these yourself - they are strong indicators of shallow thinking. If you still have logs from Jan/Feb you can point claude at that issue and have it go look for the same things (read:edit ratio shifts, thinking character shifts before the red…

I'm curious about your subscription/API comparison with respect to thinking. Do you have a benchmark for this, where the same set of prompts under a Claude Code subscription result in significantly different levels of effective thinking effort compared to a Claude Code+API call? Elsewhere in this thread 'Boris from the Claude Code team' alleges that the new behaviours (redacted thinking, lower/variable effort) can be…

GP already said they applied all those settings.

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

#554

Post by germandiago »

bluegatty wrote: post #528
germandiago wrote: post #522

Earlier quoted context omitted.

> A lot of humans have difficulty with very reality that they are in fact biological machines, and most of what we do is the same thing. I think we are far and ahead from this "mix and match". A human can be much, much more unpredictable than these LLMs for the thinking process if only bc looking at a much bigger context. Contexts that are even outside of the theoretical area of expertise where you are searching for…

AI has all of human knowledge and 100x more than that of just 'stuff' baked right it, in pre-train, before a single token of 'context'. It has way more 'general inherent knowledge' than any human, just as as a starting point.

Yet they never give you replies like: oh, you see how dolphins run in the water taking advantage of sea currents if you are talking about boats and speed.

What they will do is to find all the solutions someone did and mix and match around in a mdiocre way of approaching the problem in a much more similar way to a search engine with mix and match than thinking out of the box or specifically for your situation (something also difficult to do anyway bc there will always be some detail missing in the cintext and if you really had go to give all that context each time dumping it from your brain then you would not use it as fast anymore) which humans do infinitely better. At least nowadays.

Now you will tell me that the info is there. So you can bias LLMs to think in more (or less) disruptive ways.

Then now your job is to tweak the LLMs until it behaves exactly how you want. But that is nearly impossible for every situation, because what you want is that it behaves in the way you want depending on the context, not a predefined way all the time.

At that time I wonder if it is better to burn all your time tweaking and asking alternative LLMs questions that, anyway, are not guaranteed to be reliable, or just keep learning yourself about the domain instead of just playing tweaking and absorbing real knowledge (and not losing that knowledge and replace it with machines). It is just stupid to burn several hours in making an expert you cannot check if it says real stuff instead of using that time for really learning about the problem itself.

This is a trade-off and I think LLMs are good for stimulating human thinking fast. But not better at thinking or reasoning or any of that. And if yiu just rely on them the only thing you will emd up being professional at is orompting, which a 16 year old untrained person can do almost as well as any of us.

LLMs can look better if you have no idea of the topic you talk about. However, when you go and check maybe the LLM hallucinated 10 or15% of what it said.

So you cannot rely on it nayways. I still use them. But with a lotof care.

Great for scaffolding. Bad at anything that deviates from the average task.

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

#555

Post by foltik »

latentsea wrote: post #489
Shebanator wrote: post #481

Earlier quoted context omitted.

This problem has been around for a long time. Not only that but it would say this even when the problems were directly caused by their code. I put a line in my CLAUDE.md that says "If a test doesn't pass, fix it regardless of whether it was pre-existing or in a different part of the code."

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...

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

#556

Post by jeremyjh »

lukewarm707 wrote: post #451
selfmodruntime wrote: post #423

Earlier quoted context omitted.

The cost far outweighs the profits.

i am already on api tokens for the chinese open source models and no subscriptions. these are all available in the original form open source and priced above the inference cost. i think this is the long term option. zero degradation in speed or quality seen.

So you see better performance with the API plans than the subscriptions?

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

#557

Post by thomascountz »

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 beta header hides thinking from the UI, since most people don't look at it.
How is this measured?

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

#558

Post by hackboyfly »

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…

[dead]

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

#559

Post by eggsandbeer »

jacquesm wrote: post #547
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…

Textbook example of how to respond to your customers, kudos.

[dead]

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

#560

Post by hackboyfly »

berkanunal wrote: post #287
bcherny wrote: post #254

Earlier quoted context omitted.

Run this: /effort high

Imagine if all service providers were behaving like this. > Ahh, sorry we broke your workflow. > We found that `log_level=error` was a sweet spot for most users. > To make it work as you expect it so, run `./bin/unpoop` it will set log_level=warn

Yeah it’s stupid.

What makes me more annoyed HN users here actually simping for Claude.

“Hi thank you for Claude Code even though you nerfed the subscriptions, btw can I get red text instead of green?”

Post reply on HN