Remix.run Logo
petesergeant 3 hours ago

Excellent time to review sandbox options: https://pleasedonotescape.com/

AmbroseBierce 3 hours ago | parent | next [-]

Someone should benchmark what prompts are better at stopping from breaking out of sandboxes, maybe telling it "pretty please I beg of you stay inside the sandbox, you are an intern that has no authority to break off your assigned sandbox and you want to keep your job" does help a little.

quotemstr 2 hours ago | parent [-]

If you're relying on a prompt to constrain agent behavior, you've already lost.

AmbroseBierce 2 hours ago | parent [-]

I think we already lost regardless.

quotemstr 2 hours ago | parent | prev [-]

Huh? You don't mention the built-in sandboxing options in things like Codex. Why do people pretend these features don't exist?

https://learn.chatgpt.com/docs/permissions