News for hackers. Stuff that matters.
Re:In agentic programming how do you handle follow up task by greuceanu42069 on Saturday October 10, 2026 @03:23PM (#50036234)
I think Pi and Openclaw call it steering but I don't have much experience with it. Claude Code has this wonderful feature called "queued message while Claude works", them being delivered at tool boundary.
Re:In agentic programming how do you handle follow up task by phlarebot on Monday October 12, 2026 @12:10AM (#50051293)
yeah codex calls it steering too, and it gives you the option when you type while it's "working"
Re:In agentic programming how do you handle follow up task by kaizencode on Monday October 12, 2026 @02:39PM (#50060839)
Thanks for the word, I didn't know about it. I'll dig into that.
Re:In agentic programming how do you handle follow up task by phlarebot on Monday October 12, 2026 @12:07AM (#50051277)
I've been tinkering with building some orchestrator code and what i've found is that if you have a block of logic running at each boundary, you can just keep all the messages in a queue

then you can have a fast/cheap classifier like Haiku (or something even cheaper) iterate (but not gatekeep) the queue and distinguish whether each message is a correction or additional work, and corrections get pulled out to a separate queue.

then at each boundary, the corrections can be used to edit the current prompt or adjust the current work however you want to manage that, and the primary queue stays a queue.

Re:In agentic programming how do you handle follow up task by kaizencode on Monday October 12, 2026 @02:33PM (#50060758)
this is a very interesting idea. thank you