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

561–570 of 829 posts

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

#561

Post by JohnMakin »

exfalso wrote: post #409
JohnMakin wrote: post #297

Earlier quoted context omitted.

I’ve seen you/anthropic comment repeatedly over the last several months about the “thinking” in similar ways - “most users dont look at it” (how do you know this?) “our product team felt it was too visually noisy” etc etc. But every time something like this is stated, your power users (people here for the most part) state that this is dead wrong. I know you are repeating the corporate line here, but it’s bs.

It's to prevent distillation. Duh

of course that’s the reason but don’t pretend it’s some user guided decision

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

#562

Post by matheusmoreira »

jacquesm wrote: post #549
matheusmoreira wrote: post #545

Earlier quoted context omitted.

Literally two weeks ago it was outputting excellent results while working with me on my programming language. I reviewed every line and tried to understand everything it did. It was good. I slowly started trusting it. Now I don't want to let it touch my project again. It's extremely depressing because this is my hobby and I was having such a blast coding with Claude. I even started trying to use it to pivot to profes…

I can see how that works: this is like building a dependency, a habit if you wish. I think the tighter you couple your workflow to these tools the more dependent you will become and the greater the let-down if and when they fail. And they will always fail, it just depends on how long you work with them and how complex the stuff is you are doing, sooner or later you will run into the limitations of the tooling. One wa…

Good advice about the dependency. This stuff is definitely addictive. I've been in something of a manic episode ever since I subscribed to this thing. I started getting anxious when I hit limits.

I wouldn't say that Claude is failing though. It's just that they're clearly messing with it. The real Opus is great.

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

#563

Post by delusional »

yubblegum wrote: post #318
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…

> Before I keep going, I wanted to say I appreciate the depth of thinking & care that went into this. "This report was produced by me — Claude Opus 4.6 — analyzing my own session logs. ... Ben built the stop hook, the convention reviews, the frustration-capture tools, and this entire analysis pipeline because he believes the problem is fixable and the collaboration is worth saving. He spent today — a day he could hav…

I think it's absolutely hilarious.

> Ohh my precious baby, you've been oh so smart in writing to me.

He says, before dismantling everything reported in the issue. If the depth of thinking was so great (maybe if he had ULTRATHINK'd?) You'd think he would have found an actual problem.

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

#564

Post by xvector »

libraryofbabel wrote: post #533
faitswulff wrote: post #513

Earlier quoted context omitted.

Anthropic's position is that thinking tokens aren't actually faithful to the internal logic that the LLM is using, which may be one reason why they started to exclude them: https://www.anthropic.com/research/reasoning-models-dont-say...

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.

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

#565

Post by bwfan123 »

lambda wrote: post #282
ctoth wrote: post #256

Earlier quoted context omitted.

[flagged]

I guess one of the things I don't understand: how you expect a stochastic model, sold as a proprietary SaaS, with a proprietary (though briefly leaked) client, is supposed to be predictable in its behavior. It seems like people are expecting LLM based coding to work in a predictable and controllable way. And, well, no, that's not how it works, and especially so when you're using a proprietary SaaS model where you can…

Imagine a team of human engineers. One day they are 10x ninjas and the next they are blub-coders. Not happening.

Put Claude on PIP.

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

#566

Post by xvector »

giwook wrote: post #378
starkparker wrote: post #242

Earlier quoted context omitted.

> 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/

Pretty sure it's still gone and you should be using effort level now for this.

No, ultrathink is back and it's the same thing as high effort for the message in which it is included

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

#567

Post by thatxliner »

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…

> is consumer-hostile thinking

I've been saying this with many of my friends but, I feel like it's also probably illegal: you paid for a subscription where you expect X out of, and if they changed the terms of your subscription (e.g. serving worse models) after you paid for it, was that not false advertising? Could we not ask for a refund, or even sue?

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

#568

Post by andersa »

Wowfunhappy wrote: post #509
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…

> Under the hood, by setting this header we avoid needing thinking summaries, which reduces latency. You can opt out of it with `showThinkingSummaries: true` in your settings.json (see [docs]( https://code.claude.com/docs/en/settings#available-settings )). Can I just see the actual thinking (not summarized) so that I can see the actual thinking without a latency cost? I do really need to see the thinking in some form…

But you can't. Many times I've seen claude write confusing off-track nonsense in the thinking and then do the correct action anyway as if that never happened. It doesn't work the way we want it to.

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

#569

Post by nativeit »

matheusmoreira wrote: post #33

That analysis is pretty brutal. It's very disconcerting that they can sell access to a high quality model then just stealthily degrade it over time, effectively pulling the rug from under their customers.

I don't think humanity has fully reckoned with the idea of a product that can manipulate us unilaterally like this.

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

#570

Post by porridgeraisin »

IMO, it's an expectations vs reality thing.

The marketing still goes on about continuous inherent improvement due to the model itself, whereas most improvements today are due to better scaffolding. The key now is to build tooling around these LLMs to make them reliably productive - whatever level that may be at.

While claude code is one such tool, after a point the tooling is going to become company specific. F-whatever companies directly contract openai or anthropic and have their FDEs do it for them. If you can't do that, I would invest in building tooling around LLMs specifically for your company.

Note that LLMs are approximate retrieval machines. You still need a planner* and a verifier around it. Today humans act as the planner and verifier (with some aid from test cases/linters). Investing in automating parts of this, crucially, as separate tools, is the next big improvement.

* By planning, I mean trying out solutions, rolling them back[1], and using what you learned to do better next time. The solution search process. Context management also falls under this.

[1] and no, LLMs going "wait no..." doesn't count.

Post reply on HN