Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Code Routines

code.claude.com

Post reply on HN
Print view View original

351–360 of 451 posts

Re: Claude Code Routines

#351

Post by redanddead »

jpcompartir wrote: post #156
pacha3000 wrote: post #116

Earlier quoted context omitted.

I'm the first to be tired of everyone, for every model, that says "uuuh became dumber" because I didn't believe them ... until this week! Opus is struggling worse than Sonnet those last two weeks.

Likewise, I foolishly assumed everybody else was just doing it wrong. But this week I've lost count of the times I've had to say something along the lines of: "Can you check our plan/instructions, I'm pretty sure I said we need to do [this thing] but you've done [that thing]..." And get hit with a "You're absolutely right...", which virtually never happened for me. I think maybe once since Opus 4-6.

They track our frustration, which is probably really good coding data. The reason why it's painful is because that's data annotation, it's literally a job people get paid to do, yet we're paying to do it. If they need good data, they just turn the models to shit and gaslight everyone

Re: Claude Code Routines

#352

Post by eru »

ElFitz wrote: post #220
joshstrange wrote: post #66

LLMs and LLM providers are massive black boxes. I get a lot of value from them and so I can put up with that to a certain extent, but these new "products"/features that Anthropic are shipping are very unappealing to me. Not because I can't see a use-case for them, but because I have 0 trust in them: - No trust that they won't nerf the tool/model behind the feature - No trust they won't sunset the feature (the graveya…

> Not because I can't see a use-case for them, but because I have 0 trust in them > […] > Put another way, LLM companies are trying to climb the ladder to be a platform, I have zero interest in that, I was a "dumb pipe", I want a commodity, I want a provider, not a platform. That is my sentiment precisely, and a big reason why I’ve started moving away from Claude Code in the past few weeks when I realised how much of…

> Claude Code’s "Memory" feature was the tipping point for me, with the model committing feedbacks and learnings to some local, provider-specific path, that won’t persist in the git repo itself.

It's a bit annoying, but as long as it's local and human (or LLM) readable, you can use your favourite agent to rework this stuff for itself.

Re: Claude Code Routines

#353

Post by eru »

matheusmoreira wrote: post #343
dzink wrote: post #245

Earlier quoted context omitted.

They can’t allow third party software because the third parties save the outputs of Claude responses and distill them into new models to compete with Claude.

Just like they distilled all those git repositories, all those books to train Claude? https://news.ycombinator.com/item?id=47567575 The lack of self-awareness is hilarious.

What makes you think they lack self-awareness?

Re: Claude Code Routines

#354

Post by whh »

I don’t think LLMs should be trying to replace what essentially should be well tested heuristics.

It’s fine if it’s a stop gap. But, it’s too inconsistent to ever be reliable.

Re: Claude Code Routines

#356

Post by matheusmoreira »

eru wrote: post #353
matheusmoreira wrote: post #343

Earlier quoted context omitted.

Just like they distilled all those git repositories, all those books to train Claude? https://news.ycombinator.com/item?id=47567575 The lack of self-awareness is hilarious.

What makes you think they lack self-awareness?

For the record, I was referring to the AI companies, not the author of the comment I replied to.

Re: Claude Code Routines

#357

Post by kusha »

suslik wrote: post #307
crystal_revenge wrote: post #153

Earlier quoted context omitted.

This sounds like someone complaining about how Windows is a black box while ignoring the existence of Linux/BSD. I'm currently hosting, on very reasonable consumer grade hardware, an LLM that is on par performance wise what every anyone was paying for about a year ago. Including all the layers in between the model and the user. Llama.cpp serves up Gemma-4-26B-A4B, Open WebUI handles the client details: system prompt,…

What is reasonable hardware in your case? Doesn’t this model require 50+ Gb vram?

Gemma-4-26B-A4B does not require 50+ Gb of vram. It is a MoE model so only 4B of active parameters at a time and not as GPU dependent. I can run it on 16gb of vram and ~20gb of DDR5 regular ram for a 8 bit quant.

Re: Claude Code Routines

#359

Post by rhlsthrm »

torginus wrote: post #218
troupo wrote: post #162

Earlier quoted context omitted.

They are now literally blaming users for using their product as advertised: https://x.com/lydiahallie/status/2039800718371307603 --- start quote --- Digging into reports, most of the fastest burn came down to a few token-heavy patterns. Some tips: • Sonnet 4.6 is the better default on Pro. Opus burns roughly twice as fast. Switch at session start. • Lower the effort level or turn off extended thinking when you don't…

Off topic, but I found Sonnet useless. It can't do the simplest tasks, like refactoring a method signature consistently across a project or following instructions accurately about what patterns/libraries should be used to solve a problem.

It's crazy because when Sonnet came out it was heralded as the best thing since sliced bread, and now people are literally saying it's "useless". I wonder if this is our collective expectations increasing or the models are getting worse.
Post reply on HN