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

391–400 of 451 posts

Re: Claude Code Routines

#391

Post by imdsm »

andai wrote: post #25

I'm a little confused on the ToS here. From what I gathered, running `claude -p ` on cron is fine, but putting it in my Telegram bot is a ToS violation (unless I use per-token billing) because it's a 3rd party harness, right? (`claude -p` being a trivial workaround for the "no 3rd party stuff on the subscription" rule) This Routines feature notably works with the subscription, and it also has API callbacks. So if my…

What if claude triggers claude? Is claude automated or non-human?

So if claude decides to trigger claude -p then claude violates the ToS on your behalf and you get your account nuked?

Re: Claude Code Routines

#392

Post by 0123456789ABCDE »

minimaxir wrote: post #59
breakingcups wrote: post #52

Earlier quoted context omitted.

You seem to be vouched for now, no longer dead for me.

Hmm, I can't edit the original comment to retract that edit either. Either my account is flagged for something or HN is being weird.

this comment was made almost 1h after the one at the root of the thread

you can make changes to your posts up to 10 minutes after they were originally created — see: https://news.ycombinator.com/newsfaq.html#:~:text=minutes%20...

Re: Claude Code Routines

#393

Post by Chrisszz »

I don't get all the hype around these kinds of things, it's not something that crazy that when it gets released you solve some kind of problem you had. Those are things that can easily be replicated and that many of us already built for ourselves months ago, before those were published and became mainstream

Re: Claude Code Routines

#394

Post by Thoko14 »

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…

[dead]

Re: Claude Code Routines

#395

Post by pacha3000 »

qingcharles wrote: post #177
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.

Is it? Or is it the task you're trying to do? Opus 4.6 has been staggeringly good for me this last week, both inside Claude Code and through Antigravity until I used up my quota.

Usually, Claude code with Opus checks by itself the right tools to check the docs, for Svelte for example. So what it gives me is usually flawless.

And right now, I have to remind it every time that the MCP exists, and even then it cannot manage to find a routing bug I have with Sveltekit.

Did a lot of Sveltekit with Opus in the past, and I didn't have to think about it, Opus always got it right easily. Until now

Re: Claude Code Routines

#396

Post by robeym »

I'm not interested in new features when the main ones are mysteriously getting worse and worse. I need to have a sense of stability before I get excited about any other features.

Re: Claude Code Routines

#397

Post by Lord-Jobo »

scandinavian wrote: post #342
comboy wrote: post #107

Unrelated, but Claude was performing so tragically last few days, maybe week(s), but days mostly, that I had to reluctantly switch. Reluctantly because I enjoy it. Even the most basic stuff, like most python scripts it has to rerun because of some syntax error. The new reality of coding took away one of the best things for me - that the computer always just does what it is told to do. If the results are wrong it mean…

I'm not a big user, but I have been doing some vibe-ish coding for a PoC the past few days, and I'm astonished at how bad it is at python in particular (Opus 4.6 High). * It likes to put inline imports everywhere, even though I specify in my CLAUDE.md that it should not. * We use ruff and pyright and require that all problems are addressed or at least ignored for a good reason, but it straight up #noqa ignores all is…

It really does have some disgusting inline behaviors. I’ve also seen it do some really bizarre stuff with SQL

Re: Claude Code Routines

#398

Post by spariev »

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.

They know what they are doing perfectly well

Re: Claude Code Routines

#399

Post by eloisant »

slopinthebag wrote: post #300
alex_sf wrote: post #289

Earlier quoted context omitted.

Everytime I've tried a local model, and I have tried lots for a couple years now, they just seem like they were overtrained on benchmarks. They consistently perform dramatically worse than even older models from Anthropic/OAI/Google.

You're just using them wrong.

That might be true, but still: with Claude Opus I can give a task with 2 lines and it will just do it, with a local Qwen I have to use plan mode for everything even small tasks.

Re: Claude Code Routines

#400

Post by causal »

imdsm wrote: post #391
andai wrote: post #25

I'm a little confused on the ToS here. From what I gathered, running `claude -p ` on cron is fine, but putting it in my Telegram bot is a ToS violation (unless I use per-token billing) because it's a 3rd party harness, right? (`claude -p` being a trivial workaround for the "no 3rd party stuff on the subscription" rule) This Routines feature notably works with the subscription, and it also has API callbacks. So if my…

What if claude triggers claude? Is claude automated or non-human? So if claude decides to trigger claude -p then claude violates the ToS on your behalf and you get your account nuked?

Claude sets an environment variable to prevent nested invocation, but I've found it can be unset. No idea if they consider that a violation of the secret laws though.
Post reply on HN