World Modeling: Evaluation and State Computation
Yoav Artzi (Cornell University) https://simons.berkeley.edu/talks/yoa... 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.

▶︎
Surface Data vs. Deep Data

▶︎
Training Sand to Think: Artificial General Intelligence & Future of Physics

▶︎
Do AI Systems Have World Models? Probing Reasoning, Forecasting, and Generalization

▶︎
Why Aliens Would NEVER Invade Africa

▶︎
If I was Under 2000 Elo, I'd Only Play This ONE Opening

▶︎
Yann LeCun: World Models: Enabling the next AI revolution

▶︎
Inside Anthropic, the $965 Billion AI Juggernaut | The Circuit

▶︎
Reinventing Entropy | Compression is Intelligence Part 1

▶︎
Natural behavior is learned through dopamine-mediated reinforcement

▶︎
1986: How to Spot the Upper Class | That's Life! | BBC Archive

▶︎
This is not the AI we were promised | The Royal Society
![Bukłaki [#21] Czy św. Faustynie naprawdę objawił się Jezus? || siostra Gaudia Skass](https://i.ytimg.com/vi/2l9eQV4hPGc/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLADJsmyMp-Wc5cF6xpo5LTN8eOXpA)
▶︎
Bukłaki [#21] Czy św. Faustynie naprawdę objawił się Jezus? || siostra Gaudia Skass

▶︎
I Think They Are Lying To You

▶︎
Hierarchical structure of language and narratie recall

▶︎
"First Proof: Mathematicians Putting AI to the Test" March 14, 2026

▶︎
The Hardest Questions in Physics | World Science Festival

▶︎
I Gave ChatGPT a Body

▶︎
Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

▶︎
Why Everything Is So Expensive - Financial Expert Patrick Boyle Explains

▶︎
