"Announcing Timaeus" by Jesse Hoogland et al.
LessWrong (Curated & Popular)
00:00
Introduction
Timaeus, a new AI safety research organization, discusses their focus on making fundamental breakthroughs in technical AI alignment using deep ideas from mathematics and the sciences. They are currently working on singular learning theory and developmental interpretability to better understand large-scale learning machines and prevent the development of dangerous capabilities.
Play episode from 00:00
Transcript
