Skip to content
0:00 / 0:00

#aialignment#scalinglaws#anthropic

The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence, Task Complexity, and...

Simons Institute for the Theory of Computing

77K subscribers • 30 videos on Hallway • University channel

YouTube
  • One of the most-watched uploads on Simons Institute, a conference or university channel Hallway lists. Nobody has recommended it in the communities yet, so it ranks below community picks.
  • Presented by Jascha Sohl-Dickstein, Anthropic

Advanced. Deep dive for people who know the field.

5.9K views3 weeks ago

AI and machine learningAI safety and impactNeural networks and deep learning

Jascha Sohl-Dickstein explores how AI model misalignment scales with model intelligence and task complexity.

Jascha Sohl-Dickstein (Anthropic) simons.berkeley.edu/talks/jascha-sohl-dickstein-anthropic-20… Trustworthy AI: From Hallucinations to Reliable Autonomy

Why it's here

A top upload from a listed channel

Simons Institute is on Hallway's list of conference and university channels, and this upload is one of its most-watched talks or lectures. Nobody has recommended it in the communities yet, so it ranks below community picks.