World Modeling: Evaluation and State Computation
About this lesson
Yoav Artzi (Cornell University) https://simons.berkeley.edu/talks/yoav-artzi-cornell-university-2026-06-11 Topics in Intelligence: World Models and Social Reasoning This talk briefly describes three projects. The first two focus on evaluating world modeling capabilities in frontier models through the evaluation of dual perspective reasoning and knot manipulation. The third part describes the state separation hypothesis, which posits that mechanically separating prediction from state computation in LLMs benefits performance.
Original Description
Yoav Artzi (Cornell University)
https://simons.berkeley.edu/talks/yoav-artzi-cornell-university-2026-06-11
Topics in Intelligence: World Models and Social Reasoning
This talk briefly describes three projects. The first two focus on evaluating world modeling capabilities in frontier models through the evaluation of dual perspective reasoning and knot manipulation. The third part describes the state separation hypothesis, which posits that mechanically separating prediction from state computation in LLMs benefits performance.
Watch on YouTube ↗
(saves to browser)
Sign in to unlock AI tutor explanation · ⚡30
Related Reads
📰
📰
📰
📰
The Creator Economy Has a Geography Problem. We Built Around It.
Medium · Startup
Tencent moves to sell up to $1.6B of its Kuaishou stake
The Next Web AI
Sell BEFORE You Build. I Learned It the Expensive Way.
Medium · AI
Sell BEFORE You Build. I Learned It the Expensive Way.
Medium · Startup
🎓
Tutor Explanation
DeepCamp AI