Ryan Greenblatt joins the podcast to discuss AI control, timelines, takeoff speeds, misalignment, and slowing down around human-level AI.
You can learn more about Ryan's work here: https://www.redwoodresearch.org/team/ryan-greenblatt
Timestamps:
00:00 AI control
09:35 Challenges to AI control
23:48 AI control as a bridge to alignment
26:54 Policy and coordination for AI safety
29:25 Slowing down around human-level AI
49:14 Scheming and misalignment
01:27:27 AI timelines and takeoff speeds
01:58:15 Human cognition versus AI cognition