The Inside View

54 Episoder

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

   Publisert: 16.7.2023
2. Eric Michaud on scaling, grokking and quantum interpretability

   Publisert: 12.7.2023
3. Jesse Hoogland on Developmental Interpretability and Singular Learning Theory

   Publisert: 6.7.2023
4. Clarifying and predicting AGI by Richard Ngo

   Publisert: 9.5.2023
5. Alan Chan And Max Kauffman on Model Evaluations, Coordination and AI Safety

   Publisert: 6.5.2023
6. Breandan Considine on Neuro Symbolic AI, Coding AIs and AI Timelines

   Publisert: 4.5.2023
7. Christoph Schuhmann on Open Source AI, Misuse and Existential risk

   Publisert: 1.5.2023
8. Simeon Campos on Short Timelines, AI Governance and AI Alignment Field Building

   Publisert: 29.4.2023
9. Collin Burns On Discovering Latent Knowledge In Language Models Without Supervision

   Publisert: 17.1.2023
10. Victoria Krakovna–AGI Ruin, Sharp Left Turn, Paradigms of AI Alignment

    Publisert: 12.1.2023
11. David Krueger–Coordination, Alignment, Academia

    Publisert: 7.1.2023
12. Ethan Caballero–Broken Neural Scaling Laws

    Publisert: 3.11.2022
13. Irina Rish–AGI, Scaling and Alignment

    Publisert: 18.10.2022
14. Shahar Avin–Intelligence Rising, AI Governance

    Publisert: 23.9.2022
15. Katja Grace on Slowing Down AI, AI Expert Surveys And Estimating AI Risk

    Publisert: 16.9.2022
16. Markus Anderljung–AI Policy

    Publisert: 9.9.2022
17. Alex Lawsen—Forecasting AI Progress

    Publisert: 6.9.2022
18. Robert Long–Artificial Sentience

    Publisert: 28.8.2022
19. Ethan Perez–Inverse Scaling, Language Feedback, Red Teaming

    Publisert: 24.8.2022
20. Robert Miles–Youtube, AI Progress and Doom

    Publisert: 19.8.2022