Jamie Simon

@reson8Labs oh they can hug

@learning_mech @learning_mech can they hug?

did you know that with a few modifications, you can get the Ising model to simulate cells fighting to the death? one of my favorite side projects of all time: jamiesimon.io/blog/cell-figh…

@guzmansalv me too. my favorite method is having an immune system!

@learning_mech That looks fun! I want cells to fight to death for me

for the bright-eyed and bushy-tailed: there's a Learning Mechanics discord! young academics who want to do research in this area should especially consider joining + starting convos. discord.gg/GTHfUnf7hz

Excited to share that our paper “Sequential Group Composition: A Window into the Mechanics of Deep Learning” was accepted to ICML 2026 in Seoul! Co-led with @giovannimarchet and @AdeleMyersPhD @hopfbifurcator @ninamiolane Paper: arxiv.org/abs/2602.03655

Palantir office speedrun

ditto. props to @justanotherlaw for taking a second look :) (though I also found merit in the criticisms in the first version.) hopeful we can eventually (hopefully soon enough...) make contact w/ AI alignment + governance, whose noble causes we would v much like to aid.

It seems we're at a stage where deep learning is evolving from alchemy into an engineering discipline; this is an exciting paper which lays out that a scientific theory is emerging for Deep Learning. Paper: arxiv.org/abs/2604.21691 Tweet: x.com/learning_mech/…

yeah, totally! I once messaged everyone on facebook with my first and last name. I eventually made a big group chat! v ethnically + geographically diverse. probs the closest I've gotten as an adult to meeting a truly random slice of the US.

Aren’t diffusion models explicitly derived from a correspondence with physics and entirely consistent with how physics says you should model systems over a range of scales ( ie mori zwanzig theory: langevin dynamics with a fitted vector field ? ) what more do you want?

@evergreencqfu nice! replied :)

@learning_mech it’s working now! first comment posted! thanks for the fix!

thanks for the flag. comments on all pages of learningmechanics.pub should now be working! don't be shy :)

@aniketdxsh haha I literally have this xkcd in my head whenever I talk about this tendency

ya, diff here is that we're not proposing a correspondence! paper's mostly a perspective/review of stuff that's *already* come to smth -- and we're really just using the development of physics as an analogy to explain how the pieces come together.

@evergreencqfu smth like that seems plausible! (the challenge is to make it concrete.) would love to see that developed. u should comment on the open Q page and/or join our discord + see if u can find ppl to discuss with!

@learning_mech I’d place this under your “Discretization Hypothesis” open question: finite-depth Transformers as discretizations of an effective-field / variational dynamics over token-feature fields. learningmechanics.pub/openquestions/…

1/ Deep learning is going to have a scientific theory. We can see the pieces starting to come together, and it's looking a lot like physics! We're releasing a paper pulling together these emerging threads and giving them a name: learning mechanics. 🔨 arxiv.org/pdf/2604.21691 🔧

@TongLiu15731072 thx! help us out :)

@learning_mech so inspiring. make physics great again.

@lauren__dash @imbue_ai sorry, can't answer yet. too soon. you see, it's all still a little 🥚raw🥚 jamiesimon.io/blog/egg/

@imbue_ai not hard boiled????

Our colleague Jamie, who recently co-authored "There Will Be a Scientific Theory of Deep Learning", can indeed catch a whole egg in his mouth.

those things (FT, replicas, etc) are v useful tools - but the answer won't be like, "ah! deep learning was just X thing from physics all along!" would be nice, but not the world we live in. so physics is an analogy and a tool, not "the answer via a correspondence" or smth :)

From "Mathematical theory of deep learning: Can we do it? Should we do it?" to "There Will Be a Scientific Theory of Deep Learning". It's respectively the title of a talk I gave four years ago, and the title of an arxiv paper from four days ago. I really like the "learning mechanics" perspective (think of it as a continuation of "statistical mechanics", "quantum mechanics", and so on). Several of my last academic papers can be viewed under that lens (e.g. Learning threshold neurons via the “edge of stability”; or LEGO). I'm not as optimistic as the authors of the recent arxiv paper that we will EVER be able to reach what the "physics mechanics" field have achieved, but it's certainly worth trying. Talk: youtu.be/3uRD_lg701k?si… Paper: arxiv.org/abs/2604.21691