Keyon Vafa @keyonV · 11 Jul 2025
Last year we proposed different tests that studied single tasks. We now think that studying behavior on new tasks better captures what we want from foundation models: tools for new problems. It's what separates Newton's laws from Kepler's predictions. https://t.co/CwqGY6obUV
26 402Views
176Likes
4Reposts
3Replies
0Quotes
27Bookmarks
Is that a lot?
8.74×vs under 10K median3 020 views is typical
4.9× audienceReachviews ÷ followers
0.69%Engagement rateof viewers reacted