PeopleofSuperintelligence

Videos of Neel Nanda

YouTube videos in which Neel Nanda speaks or appears, newest first. A model chose them from YouTube search results. List updated 20 October 2026.

  1. DeepMind Researcher: AI's Makers Think It Could End HumanityPalisade Research · 29 September 2026 · 36 min
  2. Understanding the inner thoughts of AIGoogle DeepMind · 10 July 2026 · 53 min
  3. How Aligned Is Claude? A Live Review of the Opus 4.5 System CardNeel Nanda · 27 December 2025 · 2 h 23 min
  4. Neel Nanda - Our Pivot To Pragmatic Interpretability [Alignment Workshop]FAR․AI · 12 December 2025 · 10 min
  5. How Reasoning Models Break Mechanistic Interpretability TechniquesNeel Nanda · 24 November 2025 · 42 min
  6. Science of MisalignmentNeel Nanda · 22 November 2025 · 50 min
  7. What Matters Right Now In Mechanistic Interpretability?Neel Nanda · 14 November 2025 · 59 min
  8. What Happened With Sparse Autoencoders?Neel Nanda · 13 November 2025 · 2 h 49 min
  9. The Story of Mech InterpNeel Nanda · 9 November 2025 · 2 h 6 min
  10. Probes are great if you want to understand AI80,000 Hours · 7 November 2025 · 1 min
  11. Can LLMs Introspect? A Live Paper ReviewNeel Nanda · 2 November 2025 · 2 h 15 min
  12. I lead a Google DeepMind team at 26. If you want to work at an AI company... | Neel Nanda (Part 2)80,000 Hours · 15 September 2025 · 1 h 49 min
  13. AIs just TELL us what they're thinking...for now.80,000 Hours · 11 September 2025 · 2 min
  14. We know what's happening inside neural nets. We just don't know what it means.80,000 Hours · 9 September 2025 · 1 min
  15. We Can Monitor AI’s Thoughts… For Now | Google DeepMind's Neel Nanda80,000 Hours · 8 September 2025 · 3 h 3 min
  16. An Introduction to Mechanistic Interpretability – Neel Nanda | IASEAI 2025International Association for Safe & Ethical AI · 12 August 2025 · 25 min
  17. How To Think About Thinking ModelsNeel Nanda · 22 April 2025 · 1 h 34 min
  18. Neel Does Research (Vibe Coding Edition)Neel Nanda · 20 April 2025 · 2 h 34 min
  19. NEURAL NETWORKS ARE WEIRD! - Neel Nanda (DeepMind)Machine Learning Street Talk · 7 December 2024 · 3 h 43 min
  20. Neel Nanda – Mechanistic Interpretability: A Whirlwind TourFAR․AI · 10 September 2024 · 22 min
  21. Mechanistic Interpretability - NEEL NANDA (DeepMind)Machine Learning Street Talk · 28 October 2023 · 3 h 58 min
  22. A Walkthrough of Aligning Causal Variables and Distributed Representations w/ Atticus Geiger (1/3)Neel Nanda · 8 June 2023 · 31 min
  23. What is a Transformer? (Transformer Walkthrough Part 1/2)Neel Nanda · 1 May 2023 · 1 h 3 min
  24. Implementing GPT-2 From Scratch (Transformer Walkthrough Part 2/2)Neel Nanda · 1 May 2023 · 1 h 19 min
  25. A Walkthrough of Progress Measures for Grokking via Mechanistic Interpretability: What? (Part 1/3)Neel Nanda · 10 April 2023 · 43 min
  26. A Walkthrough of Reverse-Engineering Modular Addition: Model Training (Part 1/3)Neel Nanda · 12 March 2023 · 35 min
  27. Neel Nanda on Math, Tech Progress, Aging, Living up to Our Values, and Generative AIFuture of Life Institute · 23 February 2023 · 35 min
  28. Neel Nanda on What is Going on Inside Neural NetworksFuture of Life Institute · 9 February 2023 · 1 h 5 min
  29. A Walkthrough of Toy Models of Superposition w/ Jess SmithNeel Nanda · 27 December 2022 · 2 h 30 min
  30. A Walkthrough of In-Context Learning and Induction Heads Part 1 of 2 (w/ Charles Frye)Neel Nanda · 22 November 2022 · 1 h 4 min
  31. Real-Time Research Recording: Can a Transformer Re-Derive Positional Info?Neel Nanda · 1 November 2022 · 1 h 38 min
  32. A Walkthrough of A Mathematical Framework for Transformer CircuitsNeel Nanda · 14 October 2022 · 2 h 50 min
  33. An Intuitive Introduction to Machine Learning (Part 2) - Neel Nanda - The ArchimedeansThe Archimedeans · 7 July 2020 · 1 h 30 min
  34. An Intuitive Introduction to Machine Learning - Neel Nanda - The ArchimedeansThe Archimedeans · 19 April 2020 · 1 h 20 min

Video data from YouTube API Services. By watching you agree to the YouTube Terms of Service. How we use YouTube data.