Why is this specific to CAIS, as opposed to other frameworks? (Seems like this is a fairly common implication of systems that prevent people from developing rogue AGIs)
You’re right, it’s not very specific. But it was non-obvious to me, at least.
Is it obvious to you that the MIRI view is actually Orwellian?
Do you believe the MIRI view is Orwellian? If so, could you elaborate?
Why is this specific to CAIS, as opposed to other frameworks? (Seems like this is a fairly common implication of systems that prevent people from developing rogue AGIs)
You’re right, it’s not very specific. But it was non-obvious to me, at least.
Is it obvious to you that the MIRI view is actually Orwellian?
Do you believe the MIRI view is Orwellian? If so, could you elaborate?