PickVidsWe Were Right! Real Inner Misalignment
Why it was recommended
There have been actual experiments in which AIs appeared to successfully learn their objective in training
ReferenceDennisP · Original
What it covers
Robert Miles covers a paper where researchers ran real versions of his earlier mesa-optimizer thought experiments. They show inner misalignment, where an AI learns the. It is for someone who already knows the basic terms and wants the next step.
Video details
- Channel
- Robert Miles AI Safety
- Length
- 11 min 47 sec
- Year
- 2021
More in this topic
- What Happened to Horses Is Happening to Us
- Why Would AI Want to do Bad Things? Instrumental Convergence
- Veritasium: What Everyone Gets Wrong About AI and Learning – Derek Muller Explains
- Intelligence and Stupidity: The Orthogonality Thesis
- We're building a dystopia just to make people click on ads | Zeynep Tufekci
- Intro to AI Safety, Remastered