
Note: As with any research done in a couple of days, this is all very tentative. I understand, intellectually, that if you talk about some ability that current AIs don't have, sooner or later new ones will have that ability and whatever you say will stop being true. I just didn't expect it to take, you know, four days. % rollouts that took a shortcut with/without a line about testing behaviour, with 95% CIs. This is to say that Fable 5.2 seems to be the first model whose cheating beh...
Podzilla Summary coming soon
Sign up to get notified when the full AI-powered summary is ready.
Free forever for up to 3 podcasts. No credit card required.

[Linkpost] "AIFP: Looks Like the Intelligence Explosion Will Happen in 2027 After All" by Zach Stein-Perlman

"We don’t understand whether GDM intentionally trains on CoT" by Alek Westover, Buck

"Modern LLMs Don’t Know What Yudkowsky and Soares Think of Them" by N8 Programs

"Have you considered Actually Trying?" by Michaël Trazzi
Free AI-powered recaps of LessWrong (Curated & Popular) and your other favorite podcasts, delivered to your inbox.
Free forever for up to 3 podcasts. No credit card required.