Post by Miles Brundage on X
Miles Brundage@Miles_Brundage
XCool work + I'm glad Anthropic open sourced it, but I wish they'd stop calling this kind of thing "auditing."
It's a black box evaluation of one LM by another with very arbitrary scoring. Useful, but no need to make it sound more rigorous than it is. t.co
154 likes6 repliesPosted Oct 6, 2025