54 Avsnitt

  1. Owain Evans - AI Situational Awareness, Out-of-Context Reasoning

    Publicerades: 2024-08-23
  2. [Crosspost] Adam Gleave on Vulnerabilities in GPT-4 APIs (+ extra Nathan Labenz interview)

    Publicerades: 2024-05-17
  3. Ethan Perez on Selecting Alignment Research Projects (ft. Mikita Balesni & Henry Sleight)

    Publicerades: 2024-04-09
  4. Emil Wallner on Sora, Generative AI Startups and AI optimism

    Publicerades: 2024-02-20
  5. Evan Hubinger on Sleeper Agents, Deception and Responsible Scaling Policies

    Publicerades: 2024-02-12
  6. [Jan 2023] Jeffrey Ladish on AI Augmented Cyberwarfare and compute monitoring

    Publicerades: 2024-01-27
  7. Holly Elmore on pausing AI

    Publicerades: 2024-01-22
  8. Podcast Retrospective and Next Steps

    Publicerades: 2024-01-09
  9. Kellin Pelrine on beating the strongest go AI

    Publicerades: 2023-10-04
  10. Paul Christiano's views on "doom" (ft. Robert Miles)

    Publicerades: 2023-09-29
  11. Neel Nanda on mechanistic interpretability, superposition and grokking

    Publicerades: 2023-09-21
  12. Joscha Bach on how to stop worrying and love AI

    Publicerades: 2023-09-08
  13. Erik Jones on Automatically Auditing Large Language Models

    Publicerades: 2023-08-11
  14. Dylan Patel on the GPU Shortage, Nvidia and the Deep Learning Supply Chain

    Publicerades: 2023-08-09
  15. Tony Wang on Beating Superhuman Go AIs with Advesarial Policies

    Publicerades: 2023-08-04
  16. David Bau on Editing Facts in GPT, AI Safety and Interpretability

    Publicerades: 2023-08-01
  17. Alexander Pan on the MACHIAVELLI benchmark

    Publicerades: 2023-07-26
  18. Vincent Weisser on Funding AI Alignment Research

    Publicerades: 2023-07-24
  19. [JUNE 2022] Aran Komatsuzaki on Scaling, GPT-J and Alignment

    Publicerades: 2023-07-19
  20. Nina Rimsky on AI Deception and Mesa-optimisation

    Publicerades: 2023-07-18

1 / 3

The goal of this podcast is to create a place where people discuss their inside views about existential risk from AI.

Visit the podcast's native language site