Artificial General Intelligence (AGI) Show with Soroush Pour cover image

Ep 11 - Technical alignment overview w/ Thomas Larsen (Director of Strategy, Center for AI Policy)

Artificial General Intelligence (AGI) Show with Soroush Pour

CHAPTER

Critiques and Heuristic Arguments in AI Alignment Research

This chapter discusses critiques of certain methods used in AI alignment research, such as spurious correlations and lack of generalization. It also explores heuristic arguments from the Alignment Research Center (ARC) to determine the safety of models. They highlight the need for a formal statement to prove model safety and mention ongoing research on model evaluations and governing AI.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner