54 Episoder

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

    Udgivet: 23.8.2024

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

    Udgivet: 17.5.2024

  3. Ethan Perez on Selecting Alignment Research Projects (ft. Mikita Balesni & Henry Sleight)

    Udgivet: 9.4.2024

  4. Emil Wallner on Sora, Generative AI Startups and AI optimism

    Udgivet: 20.2.2024

  5. Evan Hubinger on Sleeper Agents, Deception and Responsible Scaling Policies

    Udgivet: 12.2.2024

  6. [Jan 2023] Jeffrey Ladish on AI Augmented Cyberwarfare and compute monitoring

    Udgivet: 27.1.2024

  7. Holly Elmore on pausing AI

    Udgivet: 22.1.2024

  8. Podcast Retrospective and Next Steps

    Udgivet: 9.1.2024

  9. Kellin Pelrine on beating the strongest go AI

    Udgivet: 4.10.2023

  10. Paul Christiano's views on "doom" (ft. Robert Miles)

    Udgivet: 29.9.2023

  11. Neel Nanda on mechanistic interpretability, superposition and grokking

    Udgivet: 21.9.2023

  12. Joscha Bach on how to stop worrying and love AI

    Udgivet: 8.9.2023

  13. Erik Jones on Automatically Auditing Large Language Models

    Udgivet: 11.8.2023

  14. Dylan Patel on the GPU Shortage, Nvidia and the Deep Learning Supply Chain

    Udgivet: 9.8.2023

  15. Tony Wang on Beating Superhuman Go AIs with Advesarial Policies

    Udgivet: 4.8.2023

  16. David Bau on Editing Facts in GPT, AI Safety and Interpretability

    Udgivet: 1.8.2023

  17. Alexander Pan on the MACHIAVELLI benchmark

    Udgivet: 26.7.2023

  18. Vincent Weisser on Funding AI Alignment Research

    Udgivet: 24.7.2023

  19. [JUNE 2022] Aran Komatsuzaki on Scaling, GPT-J and Alignment

    Udgivet: 19.7.2023

  20. Nina Rimsky on AI Deception and Mesa-optimisation

    Udgivet: 18.7.2023

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