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

531–540 of 829 posts

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

#531

Post by FiberBundle »

mikepurvis wrote: post #57
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.

Disconcerting for sure, but from a business point of view you can understand where they're at; afaiui they're still losing money on basically every query and simultaneously under huge pressure to show that they can (a) deliver this product sustainably at (b) a price point that will be affordable to basically everyone (eg, similar market penetration to smartphones). The constraints of (b) limit them from raising the p…

This could also be a marketing strategy. Make your models perform worse towards the end of a model's cycle, so that the next model appears as if more progress has been made than there actually has been.

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

#532

Post by necrotic_comp »

koverstreet wrote: post #249
bcherny wrote: post #219

Earlier quoted context omitted.

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…

Opus definitely pushes me to ignore problems. I've had to tell it multiple times to be thorough, and we tend to go back and forth a few times every time that happens. :)

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

#533

Post by libraryofbabel »

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...

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).

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

#534

Post by weird-eye-issue »

jfim wrote: post #244
nrds wrote: post #91

Earlier quoted context omitted.

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?

How would you do a parallel subagent if you don't have parallel tool calls? Sub agents are tools.

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

#535

Post by _3u10 »

matheusmoreira wrote: post #60
ex-aws-dude wrote: post #36

Its so silly everyone being dependent on a black box like this

It could actually be a health problem. Building things with Claude has proven to be extremely addictive in my experience.

Nah opencode / kimi is still satisfying. My feeling is Claude has been downhill since November / December.

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

#536

Post by _3u10 »

thiht wrote: post #388
ex-aws-dude wrote: post #36

Its so silly everyone being dependent on a black box like this

It’s not so much the black box that’s the issue here, but the fact you can’t even make sure doesn’t change. I’d be fine with downloading the black box and running it on my servers until I decide to update it.

Opencode w/ kimi. Problem solved.

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

#537

Post by _3u10 »

armchairhacker wrote: post #134

Yet https://marginlab.ai/trackers/claude-code/ says no issue. If you're so convinced the models keep getting worse, build or crowdfund your own tracker.

Why bother, i just use opencode now. ai is a commodity.

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

#538

Post by aurareturn »

mikepurvis wrote: post #57
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.

Disconcerting for sure, but from a business point of view you can understand where they're at; afaiui they're still losing money on basically every query and simultaneously under huge pressure to show that they can (a) deliver this product sustainably at (b) a price point that will be affordable to basically everyone (eg, similar market penetration to smartphones). The constraints of (b) limit them from raising the p…

  afaiui they're still losing money on basically every query
Source?

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

#539

Post by _3u10 »

jwr wrote: post #204

I wish they had a "and we won't screw you in two weeks" plan at, say, 5x the price. It's worth it for my business, I'd pay it. Should I switch back to API pricing? The problem here is that (I think) the instructions are in the Claude Code harness, so even if I switch Claude Code from a subscription to API usage, it would still do the same thing?

Opus is garbage use opencode and then directly compare it. It’s just as fucking dumb with opencode’s harness.

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

#540

Post by frog437 »

frog437 wrote: post #494
andoando wrote: post #482

Earlier quoted context omitted.

Isnt the codebase in the context window?

depending on how large your codebase is, hopefully not. At this point use something like the IX plugin to ingest codebase and track context, rather than from the LLM itself.

This is crazy..

tokensSaved = naiveTokens - actualTokens

  - naiveTokens = 19.4M — what ix estimates it would have cost to answer your queries without graph intelligence (i.e., dumping full files/directories into context)                                    
  - actualTokens = 4.7M — what ix's targeted, graph-aware responses actually used
  - tokensSaved = 14.7M — the difference
Post reply on HN