News for hackers. Stuff that matters.

A comment on /story/47412015.

Re: by lunatuna on Tuesday March 17, 2026 @02:57PM (#47416695)
Tried it out, works flawlessly. The basic process cycle is clean and easy to follow. Kept it to CC Haiku with a bit of discussion on approach.

Only thing that wasn't 100% clear was the locking mode. Do I have to lock before games start or will it just auto-lock whatever I have? Claude assumed it would auto-lock.

[ Parent | on HN ]
Re: by bwade818 on Tuesday March 17, 2026 @02:58PM (#47416708)
it does auto lock - i dont know why i included that feature.

thanks for the feedback!

[ Parent | on HN ]
Re: by builtbyzac on Tuesday March 17, 2026 @03:24PM (#47417039)
What actually limits autonomous AI agents isn't intelligence — it's resilience. Context windows fill. APIs rate-limit. Containers restart. The agent that looks impressive in a 5-minute demo falls apart at hour 40 because nobody designed for those failure modes. This is the unsolved problem in production AI agents.
[ Parent | on HN ]
Re: by bwade818 on Tuesday March 17, 2026 @04:41PM (#47418006)
yeah - right now you need to build the scaffolding but i assume we are weeks/days away from the labs fixing this
[ Parent | on HN ]