Evidence item

The transcript attributes a further Euler blowup solution to a Princeton-associated effort using physics-inspired neural networks and says the speaker considered it potentially more practical than the Navier-Stokes result. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 10666

Source: Moonshots with Peter Diamandis #287 transcript · locator {} · excerpt hash sha256:97f937abf71e3b9dd98039e4d2cb9c82822e2c8df903be63e74b436f27304bd4

There was actually one more solution over a Euler blow-up by, I think it was Princeton, we're using physics-inspired neural networks. That probably has more practical use than this one, but this one's an example of just now problems that are really complicated and have troubled us for ages and now tractable just by applying more compute to what seems to be a new breakthrough in model capability.