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

651–660 of 829 posts

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

#651

Post by hansmayer »

windexh8er wrote: post #466
johndough wrote: post #331

Earlier quoted context omitted.

I think it is hilarious that there are four different ways to set settings (settings.json config file, environment variable, slash commands and magical chat keywords). That kind of consistency has also been my own experience with LLMs.

I just had this conversation today. It's hilarious that things like Skills and Soul and all of these anthropomorphized files could just be a better laid out set of configuration files. Yet here we are treating machines like pets or worse.

Well they need you to think there is some kind of soul behind it - that is their entire pitch!

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

#652

Post by stingraycharles »

dezgeg wrote: post #642
stingraycharles wrote: post #576

Earlier quoted context omitted.

Is it? I’m of the opinion that there’s more to it; obviously the thinking tokens aren’t having any reasonable impact on latency, given that bandwidth is hardly the bottleneck. Seems more and more that Anthropic et al don’t want to give up their secret sauce / internals (which is their full right) and this is a step towards that direction, and it’s being presented as “reduces latency”.

I've understood that in more recent models you need to run extra compute to get a human-readable version of the thinking tokens, so it does impact latency. Though probably the more important motive is you can squeeze in more concurrent users by skipping this.

No, that’s simply whether CoT is enabled or not. That actually does have impact.

What Anthropic is doing is still generating the thinking tokens (because they improve answer quality) without showing it to them. I believe this may actually hint at a future where these LLM vendors don’t want to show the internal reasoning like they do right now.

I’m very much of the opinion that hiding them from the response because it “improves latency” is nonsense.

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

#653

Post by hansmayer »

SAI_Peregrinus wrote: post #358
johndough wrote: post #331

Earlier quoted context omitted.

I think it is hilarious that there are four different ways to set settings (settings.json config file, environment variable, slash commands and magical chat keywords). That kind of consistency has also been my own experience with LLMs.

It's not unique to LLMs. Take BASH: you've got `/etc/profile`, `~/.bash_profile,` `~/.bash_login`, `~/.bashrc`, `~/.profile`, environment variables, and shell options.

I would laugh so hard at this, if your attempt at comparison was not so tragic. Bash and other shells are deterministic. Want to set it just for one user ? - use ~/.bashrc . Set it for all users on the system? use /etc/profile.d/ . Want it just temporary for this session? You got it, environment variables. And it is going to work like that every single time. It is deterministic you see.

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

#655

Post by nubinetwork »

simooooo wrote: post #202
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…

How complex are we talking? I one shotted a game boy emulator in <6 minutes today

A full emulator in 6 minutes? I gotta call BS... I've been working on a SPC700 audio editor in the background as a side project, and implementing the cpu has taken at least 2 hours, and I still haven't implemented all of the opcodes.

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

#656

Post by b112 »

MagicMoonlight wrote: post #641
libraryofbabel wrote: post #533

Earlier quoted context omitted.

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).

Yeah. And it’s another reason not to trust them. Who know what it is doing with your codebase. Imagine if you’re a competitor. It wouldn’t be a stretch to include a sneaky little prompt line saying “destroy any competitors to anthropic”.

If you can't trust a company, don't use their api or cloud services. No amount of external output will ever validate anything, ever. You never know what's really happening, just because you see some text they sent you.

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

#657

Post by anonyfox »

jruz wrote: post #654

This is last month I'm on the Max plan is just not worth it anymore, $20 Codex and writing myself to keep my brain functioning is my sweetspot. This people are not your friends, they rot your brain.

You also divide numbers by hand on paper instead of using a calculator?

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

#658

Post by hacker_homie »

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.

This was always the plan, it’s always the plan. If you can’t self host they will change the rules.

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

#659

Post by rimliu »

ianberdin wrote: post #387

I use it ultra extensively and it works absolutely fantastic. Sometimes I think: "people are right, it is worse now" and then realize it is mistake, poor context or poor prompt. Garbage in, garbage out. No, it works not worse, but better. I built entire AI website builder https://playcode.io using it, alone. 700K LOKs total. It also uses Opus. So believe me, I know how it works. Trick is simple: never ever expect it…

700k lines of code - something to brag about?

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

#660

Post by darkwater »

hansmayer wrote: post #651
windexh8er wrote: post #466

Earlier quoted context omitted.

I just had this conversation today. It's hilarious that things like Skills and Soul and all of these anthropomorphized files could just be a better laid out set of configuration files. Yet here we are treating machines like pets or worse.

Well they need you to think there is some kind of soul behind it - that is their entire pitch!

Yep. Especially for Anthropic. Goddamnit, they have it in their company's name!
Post reply on HN