I did, it went great until it borked my mac user to the point it's non recoverable (separate mac mini, I just created a new one)

I then moved to Claude CoWork + computer use + dispatch. (before Anthropic disabled the subscription option, although that would have pushed me even more... sadly)

Now use it less and use more Claude Code Remote Routines... all it needs is computer use and I'm selling my Mac Mini... (I probably won't, need something to pay with paperclip, gastown, nanoclaw and the next 100k stars FOMO hype)

Built in Co-Pilot I believe can do this better than gh-aw (or a click away).

Cursor has that too by the way (issue -> remote coding session -> PR -> update slack)

If anyone from anthropic reads it. I love this feature very much, when it works. And it mostly doesn't.

The main bugs / missing features are

1. It loses connection to it's connectors, mostly to the slack connector. It does all the work, then says it can't connect to slack. Then when you show it a screenshot of itself with the slack connector, it will say, oh, yeah, the tools are now loaded and does the rest of the routine.

2. ability to connect it to github packages / artifactory (private packages) - or the dangerous route of allowing access to some sort of vault (with non critical dev only secrets... although it's always a risk. But cursor has it...)

3. the GitHub MCP not being able to do simple things such as update release markdown (super simple use case of creating automated release notes for example)

You are so close, yet so far...

It's remarkable how often it refuses to introspect but a SCREENSHOT of itself and suddenly "yeah this works fine".

This happens in all their UIs, including, say, Claude in Excel, as well.

+1 for that, having that said, because GH agentic workflows require a bit more handholding and testing to work, (and have way more guardrails, which is great, but limiting), and lack some basic connectors (for example - last time I tried it, it had no easy slack connector, I had to do it on my own). This is why I'm moving some of the less critical gh-aw (all the read only ones) to Claude Routines.

I've been using it for a while (it was just called "Scheduled", so I assume this is an attempt to rebrand it?)

It was a bit buggy, but it seems to work better now. Some use cases that worked for me:

1. Go over a slack channel used for feedback for an internal tool, triage, open issues, fix obvious ones, reply with the PR link. Some devs liked it, some freaked out. I kept it.

2. Surprisingly non code related - give me a daily rundown (GitHub activity, slack messages, emails) - tried it with non Claude Code scheduled tasks (CoWork) not as good, as it seems the GitHub connector only works in Claude Code. Really good correlation between threads that start on slack, related to email (outlook), or even my personal gmail.

I can share the markdowns if anyone is interested, but it's pretty basic.

Very useful, (when it works).

Same here it just feels like something so simple, I’d rather have it under my own control. That way I can keep it independent of claude as well. I use it for all kind of routine tasks like updating the summary of projects I am working on or tracking some personal activities. My setup looks like this: https://www.dev-log.me/click_recurring_tasks_for_claude/

I'd be curious to take a look if you can share

For those who switched, what is the main selling point that made you stay with Jujutsu?

For me, can do anything complex in terms of history rewriting without ever shooting myself in the foot (worse case just `jj undo`).

And the UI is pretty intuitive so don't really have to search for a solution, usually the command to use is obvious (tho I guess now you could delegate the UI to an LLM to ask it to give you the right incantations).

Few thoughts

- Either we'll slowly become the Expanse universe (basic UBI, very few jobs, you win them via lottery)

- Or we'll go to simpler times - economics is supply and demand, if there will be more demand to human generated work (the same way there is demand for hand made arts, vinyls, paper books, vintage furniture), people will flock more to family, community. Think something between moving to the suburbs and the Amish. If people will "ban" some products generated by AI, or will prefer products generated by humans, then AI will have harder times to take their jobs. It's unlikely to happen, but think about the Organic food industry, about the high end products industry, about the farm to table / buy local industry, about the "support local artists" (farmers markets) - this will likely just grow. Won't help at scale, but it's a possibility

- Or, the Dune way, banning of thinking machines altogether on the state level, I assume some countries might go that way, for religious or other reasons, but again unlikely

- Or, current AI technology will plateau just short of full AGI, and the centaur period will stay for longer. As long as a human + AI can do things slightly better than just AI, (in my book this is not full AGI) - then there is economic incentive to hire a human instead of replacing them.

- Or full apocalypse, the matrix / skynet, idiocracy, hunger games, red rising. I hope for the ignorance is bliss option...

The end game is like the Asimov world which had only a few people and everyone else was robot servants.

The trillionaires will survive, everyone else will be exterminated. This is the world that Musk and his kind dream about.

HN hug of death probably, but your scorecard returns an error :(

The analysis request failed.

Hosted shell completed without parseable score_repo.py JSON output. 11 command(s), 11 output(s). (rest redacted)

Thank you for the feedback, we are working on it!

Edit: just noticed this is a semi duplicate question to https://news.ycombinator.com/item?id=47723506 so rephrasing my question - will you have computer use and will you have self-hosted runners option? (you being just the controlplane / task orchestrator, which is the hardest problem apparently...)

Additional question - what types of sandboxes you use? (just docker or also firecracker etc...)

Original comment:

Congrats on the launch!

What's the benefit over cursor cloud agents with computer use? (other than preventing vendor lock in?)

https://cursor.com/blog/agent-computer-use

Or the existing Claude Code Web?

We already support computer use out of the box (linux sandboxes). Self hosted runners are not available yet, but Twill is built on a runtime agnostic layer (see https://github.com/TwillAI/agentbox-sdk) so it is feasible!

You definitely got my interest... will try it out!

Let us know how it goes!

I’m an enterprise customer, and still waiting for a human to respond for over 2 weeks, and there’s a special form for enterprise expedited support. I understand growing pains but this borders incompetence. If Comcast gives better customer service, you have a problem. (I would recommend to stay on the teams plan or personal plan if you can, by the way, unless you really have to)

Not to mention their 1 9s availability (I am not joking, check for yourself).

Insert victims of their own success cliche here.