I meant the latter, what sort of oversight do you suggest? I can’t think of a good mechanism either, aside from obvious things like evaluating the evidence and being aware of the possibility of bad actors.
I don’t think trying to build guardrails/monitoring systems around a misaligned A(G/S?)I that you are letting operate very autonomously and giving large amounts of control to (since it’s doing a lot of stuff in the company) is possible.
I meant the latter, what sort of oversight do you suggest? I can’t think of a good mechanism either, aside from obvious things like evaluating the evidence and being aware of the possibility of bad actors.
I don’t think trying to build guardrails/monitoring systems around a misaligned A(G/S?)I that you are letting operate very autonomously and giving large amounts of control to (since it’s doing a lot of stuff in the company) is possible.