5 Podcast Episodes
8 - Assistance Games with Dylan Hadfield-Menell
8 - Assistance Games with Dylan Hadfield-Menell
How should we think about the technical problem of building smarter-than-human AI that does what we want? When and how s... Read more
8 Jun 2021
•
2hr 23mins
Episode 10: Dylan Hadfield-Menell, UC Berkeley/MIT, on the value alignment problem in AI
Episode 10: Dylan Hadfield-Menell, UC Berkeley/MIT, on the value alignment problem in AI
Dylan Hadfield-Menell (Google Scholar) (Website) recently finished his PhD at UC Berkeley and is starting as an assistan... Read more
12 May 2021
•
1hr 32mins
57. Dylan Hadfield-Menell - Humans in the loop
57. Dylan Hadfield-Menell - Humans in the loop
Human beings are collaborating with artificial intelligences on an increasing number of high-stakes tasks. I’m not just ... Read more
11 Nov 2020
•
1hr 4mins
AIAP: Cooperative Inverse Reinforcement Learning with Dylan Hadfield-Menell (Beneficial AGI 2019)
AIAP: Cooperative Inverse Reinforcement Learning with Dylan Hadfield-Menell (Beneficial AGI 2019)
What motivates cooperative inverse reinforcement learning? What can we gain from recontextualizing our safety efforts fr... Read more
17 Jan 2019
•
51mins
AIAP: Inverse Reinforcement Learning and Inferring Human Preferences with Dylan Hadfield-Menell
AIAP: Inverse Reinforcement Learning and Inferring Human Preferences with Dylan Hadfield-Menell
Inverse Reinforcement Learning and Inferring Human Preferences is the first podcast in the new AI Alignment series, host... Read more
25 Apr 2018
•
1hr 25mins