The Inside View

54 Épisodes

1. Curtis Huebner on Doom, AI Timelines and Alignment at EleutherAI

   Publié: 16/07/2023
2. Eric Michaud on scaling, grokking and quantum interpretability

   Publié: 12/07/2023
3. Jesse Hoogland on Developmental Interpretability and Singular Learning Theory

   Publié: 06/07/2023
4. Clarifying and predicting AGI by Richard Ngo

   Publié: 09/05/2023
5. Alan Chan And Max Kauffman on Model Evaluations, Coordination and AI Safety

   Publié: 06/05/2023
6. Breandan Considine on Neuro Symbolic AI, Coding AIs and AI Timelines

   Publié: 04/05/2023
7. Christoph Schuhmann on Open Source AI, Misuse and Existential risk

   Publié: 01/05/2023
8. Simeon Campos on Short Timelines, AI Governance and AI Alignment Field Building

   Publié: 29/04/2023
9. Collin Burns On Discovering Latent Knowledge In Language Models Without Supervision

   Publié: 17/01/2023
10. Victoria Krakovna–AGI Ruin, Sharp Left Turn, Paradigms of AI Alignment

    Publié: 12/01/2023
11. David Krueger–Coordination, Alignment, Academia

    Publié: 07/01/2023
12. Ethan Caballero–Broken Neural Scaling Laws

    Publié: 03/11/2022
13. Irina Rish–AGI, Scaling and Alignment

    Publié: 18/10/2022
14. Shahar Avin–Intelligence Rising, AI Governance

    Publié: 23/09/2022
15. Katja Grace on Slowing Down AI, AI Expert Surveys And Estimating AI Risk

    Publié: 16/09/2022
16. Markus Anderljung–AI Policy

    Publié: 09/09/2022
17. Alex Lawsen—Forecasting AI Progress

    Publié: 06/09/2022
18. Robert Long–Artificial Sentience

    Publié: 28/08/2022
19. Ethan Perez–Inverse Scaling, Language Feedback, Red Teaming

    Publié: 24/08/2022
20. Robert Miles–Youtube, AI Progress and Doom

    Publié: 19/08/2022