LessWrong (Curated & Popular)

"Announcing Timaeus" by Jesse Hoogland et al.

Oct 30, 2023
Timaeus, a new AI safety research organization, discusses their focus on making fundamental breakthroughs in technical AI alignment. They are currently working on singular learning theory and developmental interpretability to prevent the development of dangerous capabilities. The podcast covers their research agenda, academic outreach, recent hiring, collaborations, risks, and significance of the name 'Timious'.
Ask episode
Chapters
Transcript
Episode notes