Yeah, kinda hoping 1) there exists a sweet spot for alignment where AIs are just nice enough from e.g. good values picked up during pre-training, but can’t be modified during post-training so much to have worse values, and that 2) given that this sweet spot does exist we do hit it with AGI / ASI.
I think there’s some evidence pointing to this happening with current models but I’m not highly confident that it means what I think it means. If this is the case though, further technical alignment research might be bad and acceleration might be good.
7 votes
Overall karma indicates overall quality.
Total points: 11
Agreement karma indicates agreement, separate from overall quality.
$10,000 seems reasonable.
A base rate of ~(1/number of top entries) for the chance of winning $100 isn’t going to motivate high effort tweets.