More Is Different for AI - Scaling Up, Emergence, and Paperclip Maximizers

More Is Different for AI - Scaling Up, Emergence, and Paperclip Maximizers

Yannic Kilcher via YouTube Direct link

Remarks

19 of 19

19 of 19

Remarks

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

More Is Different for AI - Scaling Up, Emergence, and Paperclip Maximizers

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Introduction
  2. 2 Start of Interview
  3. 3 Blog posts series
  4. 4 More Is Different for AI Blog Post
  5. 5 Do you think this emergence is mainly a property from the interaction of things?
  6. 6 How does phase transition or scaling-up play into AI and Machine Learning?
  7. 7 GPT-3 as an example of qualitative difference in scaling up
  8. 8 GPT-3 as an emergent phenomenon in context learning
  9. 9 Brief introduction of different viewpoints on the future of AI and its alignment
  10. 10 How does the phenomenon of emergence play into this game between the Engineering and the Philosophy viewpoint?
  11. 11 Paperclip Maximizer on AI safety and alignment
  12. 12 Thought Experiments
  13. 13 Imitative Deception
  14. 14 TruthfulQA: Measuring How Models Mimic Human Falsehoods Paper
  15. 15 ML Systems Will Have Weird Failure Models Blog Post
  16. 16 Is there any work to get a system to be deceptive?
  17. 17 Empirical Findings Generalize Surprisingly Far Blog Post
  18. 18 What would you recommend to guarantee better AI alignment or safety?
  19. 19 Remarks

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.