AI Safety Fundamentals: Alignment

83 Episoade

1. Public by Default: How We Manage Information Visibility at Get on Board

   Publicat: 12.05.2024
2. Writing, Briefly

   Publicat: 12.05.2024
3. Being the (Pareto) Best in the World

   Publicat: 04.05.2024
4. How to Succeed as an Early-Stage Researcher: The “Lean Startup” Approach

   Publicat: 23.04.2024
5. Become a Person who Actually Does Things

   Publicat: 17.04.2024
6. Planning a High-Impact Career: A Summary of Everything You Need to Know in 7 Points

   Publicat: 16.04.2024
7. Working in AI Alignment

   Publicat: 14.04.2024
8. Computing Power and the Governance of AI

   Publicat: 07.04.2024
9. AI Control: Improving Safety Despite Intentional Subversion

   Publicat: 07.04.2024
10. Emerging Processes for Frontier AI Safety

    Publicat: 07.04.2024
11. AI Watermarking Won’t Curb Disinformation

    Publicat: 07.04.2024
12. Challenges in Evaluating AI Systems

    Publicat: 07.04.2024
13. Interpretability in the Wild: A Circuit for Indirect Object Identification in GPT-2 Small

    Publicat: 01.04.2024
14. Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

    Publicat: 31.03.2024
15. Zoom In: An Introduction to Circuits

    Publicat: 31.03.2024
16. Weak-To-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision

    Publicat: 26.03.2024
17. Can We Scale Human Feedback for Complex AI Tasks?

    Publicat: 26.03.2024
18. Machine Learning for Humans: Supervised Learning

    Publicat: 13.05.2023
19. Visualizing the Deep Learning Revolution

    Publicat: 13.05.2023
20. Four Background Claims

    Publicat: 13.05.2023