Approval should be mandatory for any non-read tool call. You should read everything your LLM intends to do, and approve it manually.
"But that is annoying and will slow me down!" Yes, and so will recovering from disastrous tool calls.
"But that is annoying and will slow me down!" Yes, and so will recovering from disastrous tool calls.
Lol, good luck to you!
Even if you get people to sit and press a button every time the agent wants to do anything, you're not getting the actual alertness and rigor that would prevent disasters. You're getting a bored, inattentive person who could be doing something more valuable than micromanaging Claude.
Managing capabilities for agents is an interesting problem. Working on that seems more fun and valuable than sitting around pressing "OK" whenever the clanker wants to take actions that are harmless in a vast majority of cases.
You're right it's an interesting problem that seems fun to work on. Hopefully we'll get better harnesses. For now I'm checking everything.
Secure, yes? Annoying, also yes. Very error-prone too.