This is a linkpost for https://alignment.anthropic.com/2026/automated-em-search
I'm not sure what to think about this comment (or the disagreement votes), since you seem to be comparing two approaches I'd expect to fail:
More generally, I'd appreciate any pointer to an argument of the form [we should expect alignment automation to work (or that we're on the path to this)] rather than [this approach to alignment automation would be less obviously bad than various other approaches].
I'm aware of:
(my views provided for context; no need to respond to them!)
Are there any better high-level cases?
Authors: Oscar Balcells Obeso, Richard Qi, Monte MacDiarmid, Evan Hubinger
Abstract
Twitter thread
Read the full blog post here!