RSS

Matthew Rahtz

Karma: 55

Does Cir­cuit Anal­y­sis In­ter­pretabil­ity Scale? Ev­i­dence from Mul­ti­ple Choice Ca­pa­bil­ities in Chinchilla

Jul 20, 2023, 10:50 AM
44 points
3 comments2 min readLW link
(arxiv.org)

Speci­fi­ca­tion gam­ing: the flip side of AI ingenuity

May 6, 2020, 11:51 PM
66 points
9 comments6 min readLW link