Comment by literalAardvark
11 hours ago
I believe it's likely that you could train an auditor model. Might even be doable in RL.
As in real life it wouldn't be any good at doing anything but it'd be able to see fault in others and deny actions.
11 hours ago
I believe it's likely that you could train an auditor model. Might even be doable in RL.
As in real life it wouldn't be any good at doing anything but it'd be able to see fault in others and deny actions.
No comments yet
Contribute on Hacker News ↗