Aligning Superintelligence: Ex-OpenAI & DeepMind Scientist Speaks Out
tobyordoxford · x · 2026-08-12
This podcast features Geoffrey Irving, former lead at OpenAI and DeepMind and ex-Chief Scientist of AISecurityInst, discussing his new venture @resolutionorg and how to align superintelligence (ASI).
Key Discussion Points:
- Misaligned ASI: What misaligned superintelligence will actually look like.
- Lab Optimism: Why AI labs are more optimistic than he is.
- Slowing Down: When and how to decelerate AI progress.
- Post-ASI Tech: Technology landscape after ASI.
- Character Training: Can good character training carry over to ASI?
- Early Prediction: His 2018 prediction that RL + LLMs would lead to AGI.
More from AGI Musings
- Critiquing the 'Sovereign AI' Trend: Self-Hosting as Corporate LARP — curious_vii · 2026-08-12
- A Decade Later: Distributed Systems and ML Remain the Ultimate Focus — yenkel · 2026-08-12
- Dwarkesh: Continual Learning and Accumulated Context Are Becoming AI's Strongest Moat — VibeMarketer_ · 2026-08-12
- McKinsey: AI Doubles Dev Speed, But Can't Replace Senior Engineer Oversight — CackleRooster · 2026-08-12
- Wrong Bottleneck: Why Implementing AI Isn't Speeding Up Your Business — davidtwaring · 2026-08-12
- E-commerce shift: Brands must now sell to both humans and AI agents — alifcoder · 2026-08-12