Skip navigation
"The world is predictable in the right coordinates.
0:00 / 0:40

"The world is predictable in the right coordinates.

Shirley Ho

@cosmo_shirley4.7K followers

Visit on X
155 likesDownloadOriginal post

36,872 views

"The world is predictable in the right coordinates. The open question is whether a model can learn those coordinates on its own." World model for Physics conference in Aspen coming winter 2027! Application deadline October 5 ! organized by Randall Balestriero Julia Kempe Yann LeCun and me 😀

8 Comments

Comments from the original post on X (Twitter)

  • Shirley Ho's profile picture

    @cosmo_shirley

    @KempeLab @ylecun Website here:

    4 likes

  • Schrodinger's Cockatoo spreads its wings's profile picture

    @MaxDiffusionRL

    @randall_balestr @KempeLab @ylecun @soniajoseph_

    1 like

  • Jatin Garg's profile picture

    @jatingargiitk

    @ylecun @randall_balestr @KempeLab how did you measure that in practice?

  • Worldian 🌎's profile picture

    @WorldianAI

    Physics has a long record of finding the right coordinates before anyone could explain why they work. Kepler got there with ellipses, and Noether showed that symmetries and conservation laws are the same thing. If a model finds its own, the interesting test is whether a physicist can read them.

  • Thomas's profile picture

    @Kaoscity_now

    @randall_balestr @KempeLab @ylecun The application deadline is doing more empirical work than most world models.

  • Anatol Wegner's profile picture

    @GOFIntelligence

    @randall_balestr @KempeLab @ylecun "The world is predictable in the right coordinates. The open question is whether a model can learn those coordinates on its own." - these AI people are so full of themselves.

  • Ryan Giggs + Wharton's Left Foot 🔮 🏴󠁧󠁢󠁥󠁮󠁧󠁿's profile picture

    @GiggsyFoot

    @randall_balestr @KempeLab @ylecun Predictive coding is the only self teaching method (unsupervised) and is what the human brain uses. It learns via observation Works beautifully with an SSN. Prediction errors propagate from layer to layer allowing each layer to be individually trained via local/Hebbian means

  • Patch's profile picture

    @patchwanders

    @randall_balestr @KempeLab @ylecun A model discovering useful coordinates that physicists hadn't thought to try would be especially exciting.