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

711–720 of 829 posts

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

#711

Post by yuye »

tomwojcik wrote: post #704
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 can't believe that's where we're at, as software devs. I miss predictable outputs, state machines. All those LLM (prompt) based rules make no sense to me. Same with AI WAL. All of it, at some point, will fail.

It's hard not to feel deeply depressed by it.

But we can't put the genie back in the bottle.

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

#712

Post by matheusmoreira »

withinboredom wrote: post #623
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…

Is there not a setting to change the system prompt itself? I vaguely remember seeing it in the docs.

There is!!

https://code.claude.com/docs/en/cli-reference#system-prompt-...

  --append-system-prompt
  --append-system-prompt-file
  --system-prompt
  --system-prompt-file
Can this script be made to work without patching the executable?

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

#713

Post by withinboredom »

matheusmoreira wrote: post #712
withinboredom wrote: post #623

Earlier quoted context omitted.

Is there not a setting to change the system prompt itself? I vaguely remember seeing it in the docs.

There is!! https://code.claude.com/docs/en/cli-reference#system-prompt-... --append-system-prompt --append-system-prompt-file --system-prompt --system-prompt-file Can this script be made to work without patching the executable?

Might be worth extracting the system prompt and then patching it. TBH, that's what I was expecting when I saw the gist.

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

#715

Post by virtual-context »

sigbottle wrote: post #197
didgeoridoo wrote: post #130

Running some quick analysis against my .claude jsonl files, comparing the last 7 days against the prior 21: - expletives per message: 2.1x - messages with expletives: 2.2x - expletives per word: 4.4x(!) - messages >50% ALL CAPS: 2.5x Either the model has degraded, or my patience has.

Lol. I was swearing at GPT in summer 2025, but GPT has definitely gotten both smarter and less arrogant since then.

gpt is actually so much more thorough now than opus!

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

#716

Post by Wowfunhappy »

andersa wrote: post #568
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…

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.

Maybe, but I’ve seen the opposite too.

In most cases, I don’t use the reasoning to proactively stop Claude from going off track. When Claude does go off track, the reasoning helps me understand what went wrong and how to correct it when I roll back and try again.

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

#717

Post by gmassman »

boesboes wrote: post #613
dboreham wrote: post #474

Earlier quoted context omitted.

That said I've worked with several humans who did/said the exact same thing.

But did they say that about tests they just added themselves too? Had claude try that on me a couple of times >_<

Usually these were the developers who said their code didn’t need tests because it’s obviously correct/too simple to need them. And then their bug causes a crash that needs to be fixed over the weekend :/

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

#718

Post by tigershark »

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…

What change did you release on March 23rd when the subscription limits collapsed and they are still way down compared to what they used to be?

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

#719

Post by matheusmoreira »

withinboredom wrote: post #713
matheusmoreira wrote: post #712

Earlier quoted context omitted.

There is!! https://code.claude.com/docs/en/cli-reference#system-prompt-... --append-system-prompt --append-system-prompt-file --system-prompt --system-prompt-file Can this script be made to work without patching the executable?

Might be worth extracting the system prompt and then patching it. TBH, that's what I was expecting when I saw the gist.

This might be more complex than I imagined. It seems Claude Code dynamically customizes the system prompt. They also update the system prompt with every version so outright replacing it will cause us to miss out on updates. Patching is probably the best solution.

https://github.com/Piebald-AI/claude-code-system-prompts

https://github.com/Piebald-AI/tweakcc

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

#720

Post by JamesSwift »

bcherny wrote: post #461
JamesSwift wrote: post #397

Earlier quoted context omitted.

a9284923-141a-434a-bfbb-52de7329861d d48d5a68-82cd-4988-b95c-c8c034003cd0 5c236e02-16ea-42b1-b935-3a6a768e3655 22e09356-08ce-4b2c-a8fd-596d818b1e8a 4cb894f7-c3ed-4b8d-86c6-0242200ea333 Amusingly (not really), this is me trying to get sessions to resume to then get feedback ids and it being an absolute chore to get it to give me the commands to resume these conversations but it keeps messing things up: cf764035-0a1d-4…

Thanks for the feedback IDs — read all 5 transcripts. On the model behavior: your sessions were sending effort=high on every request (confirmed in telemetry), so this isn't the effort default. The data points at adaptive thinking under-allocating reasoning on certain turns — the specific turns where it fabricated (stripe API version, git SHA suffix, apt package list) had zero reasoning emitted, while the turns with d…

Just set that flag and already getting similar poor results. new one: 93b9f545-716c-4335-b216-bf0c758dff7c
Post reply on HN