33 min
World Modeling: Evaluation and State Computation
Artificial Intelligence, Machine Learning and seminar by Yoav Artzi, Cornell University
Thursday 13:30 Los Angeles (GMT-7)
Recording available
Berkeley, United States
Recording
Abstract
Three projects investigate world modelling and state computation in frontier AI systems. Two evaluate dual-perspective reasoning and knot manipulation. The third tests the state-separation hypothesis: that separating the mechanism for predicting outputs from the mechanism for computing state can improve language-model performance.
Topics
World Modellingstate computationfrontier AI systemsdual-perspective reasoningknot manipulationstate-separation hypothesislanguage-model performance