alt Hacker NewsI really wish that there was an “almost yolo” mode that was permissive but with light restrictions (eg no rm), or even better, a light supervisor model to prevent very dangerous commands but allow everything else.
I really wish that there was an “almost yolo” mode that was permissive but with light restrictions (eg no rm), or even better, a light supervisor model to prevent very dangerous commands but allow everything else.
Have you seen an agentic AI work its way through blockers? If it’s in the mood, it will find something not blocked that can do what it wanted.