Jamie Simon ретвитнул
Jamie Simon
135 posts
Jamie Simon
@learning_mech
doing fundamental science of deep learning | PhD from Berkeley | can catch a whole egg in my mouth
Berkeley, CA Присоединился Aralık 2023
75 Подписки1.4K Подписчики
Jamie Simon ретвитнул
Mechanistic interpretability aspires to be the biology of deep learning. @KuninDaniel and @learning_mech say that an emerging theory of deep learning they and their team call 🛠️ learning mechanics 🛠️ will be the physics.
English
Jamie Simon ретвитнул
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…
English
@guzmansalv me too. my favorite method is having an immune system!
English
@learning_mech That looks fun! I want cells to fight to death for me
English
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
English
Jamie Simon ретвитнул
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
English
Jamie Simon ретвитнул
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.
Alex Atanasov@ABAtanasov
This is a great post and I especially respect the author for updating his view when presented with new information. I strongly encourage young researchers interested in interpretability, science of DL, and safety to look at it. lesswrong.com/posts/6SRq7mZ9…
English
Jamie Simon ретвитнул
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/…
Jamie Simon@learning_mech
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 🔧
English
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.
Devon ☀️@devonzuegel
Jury selection is cool. It's probably the closest you ever get to seeing a true random sample of the population
English
Jamie Simon ретвитнул
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?
Pedro Domingos@pmddomingos
Sorry, but these correspondences between AI and physics are vacuous. People have been making them since (at least) the 80s, and they always come to nothing.
English
@learning_mech it’s working now! first comment posted! thanks for the fix!
English
thanks for the flag. comments on all pages of learningmechanics.pub should now be working! don't be shy :)
Changqing Fu@evergreencqfu
@learning_mech thanks Jamie! the open Q page’s comment system seems not working :P I tried but the comment will not appear on the page
English
@aniketdxsh haha I literally have this xkcd in my head whenever I talk about this tendency
English
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.
Pedro Domingos@pmddomingos
Sorry, but these correspondences between AI and physics are vacuous. People have been making them since (at least) the 80s, and they always come to nothing.
English
@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!
English
@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/…
English
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 🔧
English
