I agree with your thesis, but this seems generally true of any engineering problem. Is there any sense in which this provides particular insights about building aligned AGI?
(Also maybe this is just getting us ready for later content, in which case it not being particularly about build aligned AGI yet is expected.)
I agree with your thesis, but this seems generally true of any engineering problem. Is there any sense in which this provides particular insights about building aligned AGI?
(Also maybe this is just getting us ready for later content, in which case it not being particularly about build aligned AGI yet is expected.)
> Also maybe this is just getting us ready for later content
Yes, that is the intention.
Parts 2 and 3 now added (links in post), so hopefully the link to building aligned AGI is now clearer?