Eliezer Yudkowsky ⏹️
On a first read, this paper seems far ahead of the pack in terms of (1) understanding some reasons why a task might stay difficult even in the face of gradient descent, and (2) distilling out propositions they'd need to somehow verify before they started expecting nice things.
Geoffrey Irving
But I just published “Automated alignment is harder than you think” (https://arxiv.org/abs/2605.06390)! Automated alignment is not the best plan! A better plan is to not build ASI yet, and the world should try hard to realise that plan. Alas, the speed of progress calls for backups.
