Get the latest tech news
I don't want AI agents controlling my laptop
’t want AI agents controlling my laptop Part of me is always unnerved when I see people running claude --dangerously-skip-permissions or codex --yolo to give them unfettered ability to run commands on their machine. Admittedly, I do usually hit approve when I’m asked about a specific command, so I certainly understand the temptation to just avoid all that fuss and do a blanket approval.
The problem is, modern desktop operating systems are not really designed for strong security boundaries between different things running on your machine. A bit more annoying to set up but you also get the bonus of reproducibility across a team, being able to run multiple sessions in parallel, and easier collaboration. In corporate environments, it will make more sense to give AI agents their own credentials that don’t necessarily have all the permissions that are available to the user who spawned them.
Or read this on Hacker News
