alt Hacker NewsAs a casual AI code user, I can’t even go 30 seconds without claude grinding to a halt asking for permission to run a bash script for the 10th time.
As a casual AI code user, I can’t even go 30 seconds without claude grinding to a halt asking for permission to run a bash script for the 10th time.
The first step is building a sandbox (vm, container, whatever) that allows you to trust the agent in its most permissive mode.
This varies based on the maturity of my projects but most of my sessions live in VMs with very specific egress rules and permissions.