The Inside View

54 Épisodes

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

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

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

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

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

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

   Publié: 27/01/2024
7. Holly Elmore on pausing AI

   Publié: 22/01/2024
8. Podcast Retrospective and Next Steps

   Publié: 09/01/2024
9. Kellin Pelrine on beating the strongest go AI

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

    Publié: 29/09/2023
11. Neel Nanda on mechanistic interpretability, superposition and grokking

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

    Publié: 08/09/2023
13. Erik Jones on Automatically Auditing Large Language Models

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

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

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

    Publié: 01/08/2023
17. Alexander Pan on the MACHIAVELLI benchmark

    Publié: 26/07/2023
18. Vincent Weisser on Funding AI Alignment Research

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

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

    Publié: 18/07/2023