PodcastIntel
Sign in Get Started Free
The Gradient: Perspectives on AI
The Gradient: Perspectives on AI

Davidad Dalrymple: Towards Provably Safe AI

Sep 5, 2024 · 1h 20m
AI Summary
  • Davidad Dalrymple discusses calibration approaches to AI risk and the UK's ARIA Safeguarded AI Programme for provably safe systems
  • Examines the Orthogonality Thesis and how current AI development trajectories relate to potential AGI scenarios
  • Balances optimism about technical breakthroughs with realism about AGI timelines and existential impact

More from The Gradient: Perspectives on AI

The Gradient: Perspectives on AI
Jan 22, 2026 · 1h 1m
The Gradient: Perspectives on AI
Dec 26, 2024 · 1h 48m
View all episodes →

Get AI Summaries for Every New Episode

Subscribe to The Gradient: Perspectives on AI and get AI summaries, guest tracking, and email digests delivered automatically.

Sign Up Free →