[renmillar]

That last part is a real one though, mine tried to debug a Dockerfile by poking around my local environment outside of Docker today.

[josephg]

I’ve had it make some pretty obvious mistakes. I have to hold back the impulse to “unstick” it manually. In my case, it’s been surprisingly good at eventually figuring out what it was doing wrong - though sometimes it burns a few minutes of tokens in the process.

[tiltowait]

Claude's willingness to poke outside of its present directory can definitely be a little worrying. Just the other day, it started trying to access my jails after I specifically told it not to.

[e1g]

On a Mac, I use built-in sandboxing to jail Claude (and every other agent) to $CWD so it doesn’t read/write anything it shouldn’t, doesn’t leak env, etc. This is done by dynamically generating access policies and I open sourced this at https://agent-safehouse.dev

[teaearlgraycold]

For the moment it’s best practice to run it and all of your dev stuff in a VM.