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

41–50 of 451 posts

Re: Claude Code Routines

#41

Post by grafmax »

unshavedyak wrote: post #39
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…

Wait we can't use claude -p around other tools? What is the point of the JSON SDK then? Anthropic is confusing here, ugh. edit : And specifically i'm making an IDE, and trying to get ClaudeCode into it. I frankly have no clue when Claude usage is simply part of an IDE and "okay" and when it becomes a third party harness..

They’re shooting themselves in the foot with these dumb restrictions.

Re: Claude Code Routines

#42

Post by dockerd »

ctoth wrote: post #6

You'd think that if they were compute-limited ... Trying to get people to use it less ... The rational thing to do would be to not ship features that will use more compute automatedly? Or does this use extra usage?

It's how they can lock more users into their eco-system.

Re: Claude Code Routines

#43

Post by pkulak »

andai wrote: post #20
whicks wrote: post #8

Earlier quoted context omitted.

I would imagine that this sort of scheduling allows them to have more predictable loads, and they may be hoping that people will schedule some of their tasks in “off hours” to reduce daytime load.

It also beats OC's heartbeat where it auto-runs every 30 minutes and runs a bunch of prompts to see if it actually needed to run or not.

Man, this just bit me too. I started playing with OC over the weekend (in a VM), and the spend was INSANE even though I wasn't doing anything. I don't see this as very useful as an "assistant" that wanders around and anticipates my needs. But I do like the job system, and the ability to make skills, then run them on a schedule or in response to events. But when I looked into what it was doing behind my back, 48 times a day it was packaging up 20K tokens of silly context ("Be a good agent, be helpful, etc, for 30 paragraphs"), shipping it off to the model, and then responding with a single HEARTBEAT_OK.

Luckily you can turn if off pretty easily, but I don't know why it's on by default to begin with. I guess holdover from when people used it with a $20 subscription and didn't care.

Re: Claude Code Routines

#44

Post by unshavedyak »

slopinthebag wrote: post #10
bpodgursky wrote: post #4

OpenClawd had about a two week moat... Feature delivery rate by Anthropic is basically a fast takeoff in miniature. Pushing out multiple features each week that used to take enterprises quarters to deliver.

You're delusional if you think these features would take competent programmers quarters to deliver.

Maybe they were accounting for huge layers of red tape in large orgs. God knows those are far slower than "competent programmers" lol

Re: Claude Code Routines

#46

Post by gavinray »

summarity wrote: post #5

If you’re trying this for automating things on GitHub, also take a look at Agentic Workflows: https://github.github.com/gh-aw/ They support much of the same triggers and come with many additional security controls out of the box

Why have I not heard of this? Was looking for a way to integrate LLM CLI's to do automated feature development + PR submission triggered by Github issues, seems like this would solve it.

Re: Claude Code Routines

#47

Post by buster »

slopinthebag wrote: post #10
bpodgursky wrote: post #4

OpenClawd had about a two week moat... Feature delivery rate by Anthropic is basically a fast takeoff in miniature. Pushing out multiple features each week that used to take enterprises quarters to deliver.

You're delusional if you think these features would take competent programmers quarters to deliver.

He said "enterprises" not "competent programmers".

Re: Claude Code Routines

#48

Post by taytus »

grafmax wrote: post #41
unshavedyak wrote: post #39

Earlier quoted context omitted.

Wait we can't use claude -p around other tools? What is the point of the JSON SDK then? Anthropic is confusing here, ugh. edit : And specifically i'm making an IDE, and trying to get ClaudeCode into it. I frankly have no clue when Claude usage is simply part of an IDE and "okay" and when it becomes a third party harness..

They’re shooting themselves in the foot with these dumb restrictions.

They are not dumb restrictions. They just don't have the compute. That is the dumb part. Dario did not secure the compute they need so now they are obviously struggling.

Re: Claude Code Routines

#50

Post by dgellow »

taytus wrote: post #48
grafmax wrote: post #41

Earlier quoted context omitted.

They’re shooting themselves in the foot with these dumb restrictions.

They are not dumb restrictions. They just don't have the compute. That is the dumb part. Dario did not secure the compute they need so now they are obviously struggling.

Their growth over the past months has been more than insane. It’s completely expected they don’t have the compute. You don’t have infinite data centers around
Post reply on HN