#AInotesfollow brings so many issues. It really accelerates. Not only the good parts but also the bad parts. Combine this with a product person that doesn't even know what a refinement is. I'm 41, maybe I'll study to pivot, maybe I'll get into trading. I can't handle it anymore.
what is a refinement? honest question - I'm restructuring our refinements now. Like having group of people discussing 5 items in an hour gives little chances any one of them will be addressed properly, unless they are trivial.
Architect/lead have a pre-refinement with product to clear 80% of the obvious questions. We share an agenda, devs can ask questions async. In the refinement product presents, we design a solution draft. 15 minutes/item. This doesn't work if product is incompetent and everything is AI-slopped.
Run Claude code in docker sandbox (sbx) to ensure it only has current folder access and limited or no network access. Especially since a lot of runs are now in โauto modeโ.
Unless even this is not really so safe!?
#ainotesfollow
@fastidiousprofilefollow"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyersreplied to@neoprofilefollowcoder, reader, guitarist, seeker, builder.:
Claude will run on auto mode only if you tell it to do it.
Donโt be beholden to one LLM basket.
Get yourself an Openrouter account, get yourself an open source harness like pi and get yourself educated.
I will die on this hill.
I agree with this. I already use different models for different tasks in part for this reason.
Never bothered with an OpenRouter account though, I just have accounts set with each provider.
And Pi is excellent. I actually find it much better than Claude Code.