@mingjie@linear "trust" as in I don't check each and every line of code Fable writes either. Which of course can fire back.
we learned it's super helpful to let the "analysing Claude" dump all its context into a Linear issue so that the "implementing Claude" knows where to start.
@linear what if issues had separate human and agent descriptions? agent would store deep contexts in neuralese and maintain a clean readable version in UI
@toddsaunders I think we all want our todos in @linear because they've got the greatest UX. but I want to be able plan, delegate or assign through my @claude with all its connectors to my context.
that's where Claude is headed atm. the super connector and assistant layer.
Wow, I totally disagree with this statement. At the current state, AI actually amplifies the developer to developer difference. If you were a 10x developer, you had good ideas + architectural clarity, this is a brutal advantage when using AI. Steering is a fundamental part of today's AI development.