I'm personally interested about the intersection of AI and physics
In practice, Sonnet 3.7 and Gemini 2.5 are just often too good compared to competitors.
We need to advance mechanistic interpretability (field reverse engineering neural networks) https://www.youtube.com/watch?v=P7sjVMtb5Sg https://www.youtube.com/watch?v=7t9umZ1tFso…
I'm personally interested about the intersection of AI and physics
In practice, Sonnet 3.7 and Gemini 2.5 are just often too good compared to competitors.
We need to advance mechanistic interpretability (field reverse engineering neural networks) https://www.youtube.com/watch?v=P7sjVMtb5Sg https://www.youtube.com/watch?v=7t9umZ1tFso…