Keyon Vafa @keyonV · 11 Jul 2025
Summary: 1. We propose inductive bias probes: a model's inductive bias reveals its world model 2. Foundation models can have great predictions with poor world models 3. One reason world models are poor: models group together distinct states that have similar allowed next-tokens
20 483Views
274Likes
11Reposts
6Replies
3Quotes
51Bookmarks
Is that a lot?
6.78×vs under 10K median3 020 views is typical
3.8× audienceReachviews ÷ followers
1.44%Engagement rateof viewers reacted