This is a special post for quick takes by joanv. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.
Some mixed feelings about Anthropic’s Auto-Alignment Researcher post here:
TLDR: if we really want to turn alignment in a “number go up game”, we better make sure evals/envs we use are water-tight (which tbc may be easier than “solving” alignment), and I claim that this eval/env may not be super robust.