Will Humans Be Taken Over by 3-Dimensional Chess Playing AIs? W47

5 years ago, the Google AlphaGo beated reigning world number 1 in Go, Ke Jie, but if you think the board game playing AI's have stopped evolving since, think twice! Today we will look into the new language model, Cicero's, deceptive abilities along with considerations on what board-game playing AI's teach us about AI-development.
5 years ago, the Google AlphaGo beated reigning world number 1 in Go, Ke Jie, but if you think the board game playing AI's have stopped evolving since, think twice! Today we will look into the new language model, Cicero's, deceptive abilities along with considerations on what board-game playing AI's teach us about AI-development. 

Table of contents: 
  • Language model plays Diplomacy better than humans
  • 3-dimensional chess-playing AI's might not be that dangerous
  • Presuming independence to formalise interpretability work
  • Monosemanticity engineering of toy models
  • Minor news


Sources
AlphaGo beating Ke Jie in GO (5 years ago)
https://www.bbc.com/news/technology-40042581 
Will Humans Be Taken Over by 3-Dimensional Chess Playing AIs? W47
Broadcast by