The Inside View

Recent episodes

52 episodes from the feed, newest first.

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

   with Owain Evans

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

   with Adam Gleave

   May 2024
3. Ethan Perez on Selecting Alignment Research Projects (ft. Mikita Balesni & Henry Sleight)

   with Ethan Perez

   Apr 2024
4. Emil Wallner on Sora, Generative AI Startups and AI optimism

   with Emil Wallner

   Feb 2024
5. Evan Hubinger on Sleeper Agents, Deception and Responsible Scaling Policies

   with Evan Hubinger

   Feb 2024
6. [Jan 2023] Jeffrey Ladish on AI Augmented Cyberwarfare and compute monitoring

   with Jeffrey Ladish

   Jan 2024
7. Holly Elmore on pausing AI

   with Holly Elmore

   Jan 2024
8. Podcast Retrospective and Next Steps
   Jan 2024
9. Paul Christiano's views on "doom" (ft. Robert Miles)

   with Robert Miles

   Sep 2023
10. Neel Nanda on mechanistic interpretability, superposition and grokking

    with Neel Nanda

    Sep 2023
11. Joscha Bach on how to stop worrying and love AI

    with Joscha Bach

    Sep 2023
12. Erik Jones on Automatically Auditing Large Language Models

    with Erik Jones

    Aug 2023
13. Dylan Patel on the GPU Shortage, Nvidia and the Deep Learning Supply Chain

    with Dylan Patel

    Aug 2023
14. Tony Wang on Beating Superhuman Go AIs with Advesarial Policies

    with Tony Wang

    Aug 2023
15. David Bau on Editing Facts in GPT, AI Safety and Interpretability

    with David Bau

    Aug 2023
16. Alexander Pan on the MACHIAVELLI benchmark

    with Alexander Pan

    Jul 2023
17. Vincent Weisser on Funding AI Alignment Research

    with Vincent Weisser

    Jul 2023
18. [JUNE 2022] Aran Komatsuzaki on Scaling, GPT-J and Alignment

    with Aran Komatsuzaki

    Jul 2023
19. Curtis Huebner on Doom, AI Timelines and Alignment at EleutherAI

    with Curtis Huebner

    Jul 2023
20. Eric Michaud on scaling, grokking and quantum interpretability

    with Eric Michaud

    Jul 2023
21. Jesse Hoogland on Developmental Interpretability and Singular Learning Theory

    with Jesse Hoogland

    Jul 2023
22. Clarifying and predicting AGI by Richard Ngo

    with Richard Ngo

    May 2023
23. Alan Chan And Max Kauffman on Model Evaluations, Coordination and AI Safety

    with Alan Chan

    May 2023
24. Breandan Considine on Neuro Symbolic AI, Coding AIs and AI Timelines

    with Breandan Considine

    May 2023
25. Christoph Schuhmann on Open Source AI, Misuse and Existential risk

    with Christoph Schuhmann

    May 2023