AI Safety Fundamentals: Alignment

Un pódcast de BlueDot Impact

Categorías:

83 Episodo

  1. Constitutional AI Harmlessness from AI Feedback

    Publicado: 19/7/2024
  2. Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

    Publicado: 19/7/2024
  3. Illustrating Reinforcement Learning from Human Feedback (RLHF)

    Publicado: 19/7/2024
  4. Chinchilla’s Wild Implications

    Publicado: 17/6/2024
  5. Deep Double Descent

    Publicado: 17/6/2024
  6. Intro to Brain-Like-AGI Safety

    Publicado: 17/6/2024
  7. Eliciting Latent Knowledge

    Publicado: 17/6/2024
  8. Toy Models of Superposition

    Publicado: 17/6/2024
  9. Least-To-Most Prompting Enables Complex Reasoning in Large Language Models

    Publicado: 17/6/2024
  10. Discovering Latent Knowledge in Language Models Without Supervision

    Publicado: 17/6/2024
  11. ABS: Scanning Neural Networks for Back-Doors by Artificial Brain Stimulation

    Publicado: 17/6/2024
  12. Two-Turn Debate Doesn’t Help Humans Answer Hard Reading Comprehension Questions

    Publicado: 17/6/2024
  13. Imitative Generalisation (AKA ‘Learning the Prior’)

    Publicado: 17/6/2024
  14. An Investigation of Model-Free Planning

    Publicado: 17/6/2024
  15. Low-Stakes Alignment

    Publicado: 17/6/2024
  16. Gradient Hacking: Definitions and Examples

    Publicado: 17/6/2024
  17. Empirical Findings Generalize Surprisingly Far

    Publicado: 17/6/2024
  18. Compute Trends Across Three Eras of Machine Learning

    Publicado: 13/6/2024
  19. Worst-Case Thinking in AI Alignment

    Publicado: 29/5/2024
  20. Public by Default: How We Manage Information Visibility at Get on Board

    Publicado: 12/5/2024

1 / 5

Listen to resources from the AI Safety Fundamentals: Alignment course!https://aisafetyfundamentals.com/alignment

Visit the podcast's native language site