3. Evan Hubinger on Takeoff speeds, Risks from learned optimization & Interpretability
The Inside View
00:00
How Fast Do We Build Really Powerful Ai Systems?
How quickly do the a systems get better? A, are they other sort of big discontinuities in how they get better? How concentrated is the sort of s power over the systemseteara? And so i think this is like, in some sense, the more important dimensions.
Transcript
Play full episode
