claude is stupid but not malicious; chroot is sufficient

furyofantares 11 hours ago | parent | next [-]

I've many times seen Claude try to execute a command that it's not supposed to, the harness prevents it, and then it writes and executes a python script to do it.

▲

j16sdiz 9 hours ago | parent [-]

breaking a chroot takes more than that..

	▲	hoppp an hour ago \| parent [-]
		That doesn't mean claude can't do it, chroot is better than nothing but not a real solution

▲

nofriend 11 hours ago | parent | prev | next [-]

Malice is not required. If it thinks it is in the right, then it will do whatever it takes to get around limitations.

▲

lxgr 4 hours ago | parent | prev | next [-]

Until it gets prompt injected. Are you reading every single file your agent reads as part of the tasks you give it, including content fetched from the web or third-party packages?

▲

karhagba 11 hours ago | parent | prev [-]

Claude is far from stupid from my experience. I've used so many models and Claude is king.