Join Daniel Filan as he talks with researchers about their work on AI safety and risk. Explore insights that could shape a safer future for humanity.
45 - Samuel Albanie on DeepMind's AGI Safety Approach
76 mins • Jul 6, 2025
Charts
- 80Decreased by 12
- 159Decreased by 7
- 200Decreased by 17
- 130Increased by 1
- 132Decreased by 7
Recent Episodes

Jul 6, 2025
45 - Samuel Albanie on DeepMind's AGI Safety Approach
76 mins

Jun 28, 2025
44 - Peter Salib on AI Rights for Human Safety
202 mins

Jun 15, 2025
43 - David Lindner on Myopic Optimization with Non-myopic Approval
101 mins

Jun 6, 2025
42 - Owain Evans on LLM Psychology
134 mins

Jun 3, 2025
41 - Lee Sharkey on Attribution-based Parameter Decomposition
136 mins

Language
English
Country
United States
Feed Host
Website
Feed
Request an Update
Updates may take a few minutes.