Report
Are we building world models the wrong way?
The Information's episode considers whether interpretability could improve training and why language alone may not be enough for physical AI.
TLDR
The Information's sixth AI Deep Dive episode explores how models represent physics. Guests discuss whether interpretability could improve training and why language alone may not be enough for physical AI. The episode also covers surgical robots, manufacturing, specialized world models and what video models learn about physics.
Combined views
9.3K
5 Sources, first seen ago
