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
- 'Will you end humanity?' AI's candid answer becomes a clown meme — dermflork · 2026-10-16
- Stanford professor: AI-done homework scores high, students fail in-person finals — FinanceYF5 · 2026-10-16
- Data brokers pay $100K–$2M for SaaS datasets that may train their own replacements — FinanceYF5 · 2026-10-16
- tszzl: Pretraining science is like steam engines before thermodynamics, slouching toward interpretability — tszzl · 2026-10-16
- eigenrobot: AI acceleration will collapse human capital investment — eigenrobot · 2026-10-16
- As AI decompilation and vibe coding surge, who trusts AI-cloned software? — Honest_Risk3903 · 2026-10-16