Issue: Claude Code is unusable for complex engineering tasks with Feb updates • Hacker News Board

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

#131

Post by jmount » Mon, Apr 06, 2026, 5:07 PM UTC

riskassessment wrote: post #67

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.

Stealthily degrade the model or stealthily constrain the model with a tighter harness? These coding tools like Claude Code were created to overcome the shortcomings of last year's models. Models have gotten better but the harnesses have not been rebuilt from scratch to reflect improved planning and tool use inherent to newer models. I do wonder how much all the engineering put into these coding tools may actually in…

Love your point. Instructions found to be good by trial and error for one LLM may not be good for another LLM.

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

#132

Post by nphardon » Mon, Apr 06, 2026, 5:08 PM UTC

jp57 wrote: post #119

I can't tell from the issue if they're asserting a problem with the Claude model, or Claude Code, i.e. in how Claude Code specifically calls the model. I've been using Roo Code with Claude 4.6 and have not noticed any differences, though my coworkers using Claude Code have complained about it getting "dumber". Roo Code has its own settings controlling thinking token use. (I'm sure it benefits Anthropic to blur the li…

I also havent noticed the degradation and I'm not on Claude Code. I'm on week 4 of a continuous, large engineering project, C, massive industrial semiconductor codebase, with Opus, and while it's the biggest engagement I've had, its a single agent flow, and it's tiny on the scale of the use case in the post, so I wonder if they are just stressing the system to the point of failure.

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

#133

Post by talim » Mon, Apr 06, 2026, 5:09 PM UTC

onlyrealcuzzo wrote: post #115

summarity wrote: post #8

Not claude code specific, but I've been noticing this on Opus 4.6 models through Copilot and others as well. Whenever the phrase "simplest fix" appears, it's time to pull the emergency break. This has gotten much, much worse over the past few weeks. It will produce completely useless code, knowingly (because up to that phrase the reasoning was correct) breaking things. Today another thing started happening which are…

> Whenever the phrase "simplest fix" appears, it's time to pull the emergency break. Second! In CLAUDE.md, I have a full section NOT to ever do this, and how to ACTUALLY fix something. This has helped enormously.

What wording do you use for this, if you don't mind? This thread is a revelation, I have sworn that I've seen it do this "wait... the simplest fix is to [use some horrible hack that disregards the spec]" much more often lately so I'm glad it's not just me.

However I'm not sure how to best prompt against that behavior without influencing it towards swinging the other way and looking for the most intentionally overengineered solutions instead...

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

#134

Post by armchairhacker » Mon, Apr 06, 2026, 5:10 PM UTC

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.

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

#135

Post by ambicapter » Mon, Apr 06, 2026, 5:10 PM UTC

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.

First time interacting with a corporation in America?

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

#136

Post by devmor » Mon, Apr 06, 2026, 5:11 PM UTC

jonnycoder wrote: post #104

ex-aws-dude wrote: post #36

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

Everything in our life is a black box, but I agree that depending on non-deterministic and sporadic quality black boxes is a huge red flag.

No, most systems in daily life can be understood if you are willing to take the time.

That doesn’t mean you personally are required to, but some people do and your interaction with the system of social trust determines how much of that remains opaque to you.

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

#137

Post by semiinfinitely » Mon, Apr 06, 2026, 5:12 PM UTC

maybe dont outsource your brain then

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

#138

Post by gloosx » Mon, Apr 06, 2026, 5:12 PM UTC

andai wrote: post #65

Aperocky wrote: post #56

In my opinion cramming invisible subagents are entirely wrong, models suffer information collapse as they will all tend to agree with each other and then produce complete garbage. Good for Anthropic though as that's metered token usage. Instead, orchestrate all agents visibly together, even when there is hierarchy. Messages should be auditable and topography can be carefully refined and tuned for the task at hand. Ot…

Isn't Claude Code supposed to be like a person? What would the Unix equivalent of that be?

File. In Unix everything is a file.

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

#139

Post by addandsubtract » Mon, Apr 06, 2026, 5:13 PM UTC

matheusmoreira wrote: post #63

tmpz22 wrote: post #53

Earlier quoted context omitted.

> effectively pulling the rug from under their customers. This is the whole point of AI. Its a black box that they can completely control.

I hope local models advance to the point they can match Opus one day...

We said this since ChatGPT 3. People will never be content with local models.

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

#140

Post by SkyPuncher » Mon, Apr 06, 2026, 5:14 PM UTC

rubicon33 wrote: post #77

SkyPuncher wrote: post #69

I've noticed this as well. I had some time off in late January/early February. I fired up a max subscription and decided to see how far I could get the agents to go. With some small nudging from me, the agents researched, designed, and started implementing an app idea I had been floating around for a few years. I had intentionally not given them much to work with, but simply guided them on the problem space and my co…

There is a huge difference between greenfield development and working with an existing codebase. I'm not trying to discredit your experience and maybe it really is something wrong with the model. But in my experience those first few prompts / features always feel insanely magical, like you're working with a 10x genius engineer. Then you start trying to build on the project, refactor things, deploy, productize, etc. a…

This isn't the case. I basically did an entire business/project/product exploration before building the first feature.

Even after deleting everything from the first feature and going back to the checkpoint just before initial development, I can no longer get it to accomplish anything meaningful without my direct guidance.