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

771–780 of 829 posts

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

#771

Post by asobalife »

faitswulff wrote: post #513
Wowfunhappy wrote: post #509

Earlier quoted context omitted.

> 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…

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...

I have seen this to be true many times. The CoT being completely different from the actual model output.

Not limited to Claude as well.

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

#772

Post by asobalife »

pjc50 wrote: post #621
xvector wrote: post #564

Earlier quoted context omitted.

If distilled models were commercially banned they'd probably be willing to show the thinking again.

Intellectual property rights in models? But then wouldn't the model maker have to pay for all the training IP? (just kidding, I know that the legal rule for IP disputes is "party with more money wins")

how does one actually enforce that? I mean especially for code? You can always just clean room it

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

#773

Post by zamber »

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.

It's not rug pulling, it's simple price anchoring. They'll degrade when it makes financial sense for them. You will pay for it. There's no way around it besides self hosting or using reality metered endpoints like openrouter.

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

#774

Post by stldev »

naasking wrote: post #730
hackboyfly wrote: post #560

Earlier quoted context omitted.

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?”

They're a business. The alternative to keep costs in check would to ask you for more money, and you'd likely be even more upset with that.

They are definitely that. Regardless of their approach, being upfront and transparent would have been nice. Bricking their own software that previously worked well for their customers isn't cool.

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

#775

Post by areoform »

oriettaxx wrote: post #614
areoform wrote: post #349

Earlier quoted context omitted.

Hey Boris, thanks for the awesomeness that's Claude! You've genuinely changed the life of quite a few young people across the world. :) not sure if the team is aware of this, but Claude code (cc from here on) fails to install / initiate on Windows 10; precise version, Windows 10.0.19045 build 19045. It fails mid setup, and sometimes fails to throw up a log. It simply calls it quits and terminates. On MacOS, I use Cla…

why is this post down graded?

I angered the mob elsewhere by being a heretic.

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

#776

Post by Jimpulse »

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…

Thanks for transparency here. Claude code if fun to use again! The thinking is huge when working with Claude as planner.

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

#778

Post by germandiago »

bluegatty wrote: post #752
germandiago wrote: post #554

Earlier quoted context omitted.

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 (somethi…

First - I'm doubting your assumptions about "What they will do is to find all the solutions someone did and mix and match". That's not quite how AI works. Second - You'll have to provide some comparable reference for how 'humans' come up with creative solutions. Remember - as a 'starting point' AI has 'all of human knowledge' ingested, accessibly instantly. Everything except for a few contemporary events. That's an i…

> First - I'm doubting your assumptions about "What they will do is to find all the solutions someone did and mix and match".

I never, ever got from a LLM a solution that either I could have never thought of or it was available almost verbatim in internet (take this last one with a grain of salt, we know how they can combine and fake it, but essentially, solutions looking like templates from existing things, often hallucinating things that do not exist or cannot be done, inventing parameter names for APIs that do not exist, etc).

When I give some extra thought to a problem (20 years almost in software business) I think solutions that I come up with are often simpler, less convoluted and when I analyze LLMs they give you a lot of extra code that is not even needed, as if they were doing guessing even if you ask them something more narrow. Well, guessing is what they are doing actually, via interpolation.

This makes them useful for "bulky", run fast, first approach problems but the cost later is on you: maintenance, understanding, modifying, etc.

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

#779

Post by mial »

voxelc4L wrote: post #66

Wonder how many of these cases are using the 1M context window. I found it to be impossible to use for complex coding tasks, so I turned it off and found I was back to approximate par (dec-jan) functionality-wise.

How did you disable it?

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

#780

Post by thesz »

richardjennings wrote: post #600
Avamander wrote: post #424

Earlier quoted context omitted.

I feel like the maximum effort mode kind-of wraps around and starts becoming "desperate" to the extent of lazy or a monkey's paw, similar to how lower effort modes or a poor prompt.

I think over-thinking is only solved by thinking more, not less. This is only viable once some intelligence threshold is reached, which I think Anthropic has borderline achieved.

  > I think over-thinking is only solved by thinking more, not less.
Despite "thinking" tokens being determined by the preceding tokens, they still are taken from some probability distribution, just a complex one. This means that at each token selection step there is a probability P_e of an error, of selecting a wrong token.

These errors compound exponentially: the probability of not selecting wrong token for N steps is 1-(1-P_e)^N.

The shorter "thinking" is, the less is the probability of it going astray.

Post reply on HN