Hacker News Reader

I wasn't using Claude Code, but I told an agent to add something like this to the AGENTS.md, it did it and then a few minutes later it attempted to grant itself permission to do something and managed to delete the VM it was running on in the process. I have since adjusted the way I sandbox agents to make that less likely, but the moral of the story is clear.

it's a probabilistic model so, while you can put that in there, it has some probability of just ignoring you and doing it anyway.

Once the session gets long enough, agents start getting amnesia.

Replacing docker with podman could help in this particular case. Running everything in an insulated throwaway VM should help even better.

Unless you trust an AI as much as you trust yourself, there's no reason to allow it to act with your privileges.

In addition to what people already said, this also risks the agent failing to continue after things it's supposed to be able to figure it out.