News for hackers. Stuff that matters.
Re:Tell HN: Anthropic no longer allowing Claude Code subscri... by lherron on Saturday April 04, 2026 @12:31AM (#47635771)
I think maybe you are not familiar with what /loop and the Claude cron tools do.

https://code.claude.com/docs/en/scheduled-tasks

Re:Tell HN: Anthropic no longer allowing Claude Code subscri... by gregjw on Saturday April 04, 2026 @01:02AM (#47635942)
I need a hypothetical use case for things like this, I don't get how so many people have so much desire for use of features like this.
Re:Tell HN: Anthropic no longer allowing Claude Code subscri... by goosejuice on Saturday April 04, 2026 @02:19AM (#47636372)
https://martinfowler.com/articles/harness-engineering.html it's being talked about everywhere.

If you manage developers or product folk, do you allow them to work when you're not looking over their shoulder? All developers can be managers/team leads now. You plan, you delegate, you review.

You're welcome to not do this, surely that's appropriate in quite a few areas of work, but many of us are because we can get more work done than if we we're micromanaging every line of code change. For startups, where a bit of quality can suffer in favor of finding market fit, this is huge.

Re:Tell HN: Anthropic no longer allowing Claude Code subscri... by jmalicki on Saturday April 04, 2026 @12:39PM (#47640646)
The actual /loop and cron are beyond the normal "agentic loop"
Re:Tell HN: Anthropic no longer allowing Claude Code subscri... by goosejuice on Saturday April 04, 2026 @04:04PM (#47642824)
I'm not sure what point you're trying to make. `claude remote` on a secure vm is basically all you need to operate a factory from your phone. I suspect a lot of people with your line of reasoning are stuck on human in the loop while awake level of AI use. Anthropic has no interest in that long term and all of their product moves validate that.
Re:Tell HN: Anthropic no longer allowing Claude Code subscri... by vasco on Saturday April 04, 2026 @02:27AM (#47636415)
Every morning it summarizes a bunch of stuff for me, suggests me PRs to review, emails to reply to, freshly cloned any new repos, pulled all others, presents me with the suggested approaches to my PRs of that day, and gives me a list of my slack mentions that look more urgent.

This is just the morning ones, and saves shitloads of time of clicking around from tool to tool, freeing up time for the thinking and deciding.

Re:Tell HN: Anthropic no longer allowing Claude Code subscri... by vichle on Saturday April 04, 2026 @06:45AM (#47637864)
Wow, you should probably ask it to write a script for 90+% of that instead . Sounds like a huge waste of electricity.
Re:Tell HN: Anthropic no longer allowing Claude Code subscri... by pickleRick243 on Saturday April 04, 2026 @02:31PM (#47641878)
How? Most of what was mentioned requires discretion and judgment. You can question whether an LLM would be able to offer that, but there’s no script that can do b it.
Re:Tell HN: Anthropic no longer allowing Claude Code subscri... by tomjen3 on Saturday April 04, 2026 @04:36AM (#47637144)
Deduplicating/validating/processing incoming bug reports?
Re:Tell HN: Anthropic no longer allowing Claude Code subscri... by throwthrowuknow on Saturday April 04, 2026 @07:41AM (#47638154)
I think maybe you still don’t understand that not everyone will max out their usage, regardless of the methods available.
Re:Tell HN: Anthropic no longer allowing Claude Code subscri... by muyuu on Saturday April 04, 2026 @03:03PM (#47642164)
People don't pay double the $100 account in fixed recurrent payments if they don't intend to use a lot more than they would use in the $100 subscription.

Perhaps people at Anthropic should ask Sonnet (or Kimi, it's much better value) how power laws and pareto distributions work? You are advertising for people who can justify a virtually unlimited amount of tokens, why is it surprising that they would use as many as you're offering them in the plan?

PS: interesting that you'd use a throwaway account to post this