London, England
Joined January 2012
New open source: cuthbert 🐛 State space models with all the hotness: (temporally) parallelisable, JAX, Kalman, SMC
1
16
78
10,905
Sam Duffield retweeted
Replying to @Sam_Duffield
adrientaylor.github.io/tutor… are all very good! I would guess that Adrien has some nice talks on YouTube also.
1
2
8
303
Sam Duffield retweeted
Maybe a good time to look inwards a bit, and clarify for oneself what makes { a good proof, a useful construction, an effective bound, ... } and so on. I guess that we will be 'complaining' for some time (who knows how long), and it seems healthy to articulate our standards well.
1
1
1
21
3,226
Looped transformer: Calling the model only once is very bad, we need to call it many times Consistency model: Calling the model many times is very bad, we need to call it only once
Wait how is looped transformer different from diffusion?
1
9
2,173
Sam Duffield retweeted
My new book written with @sirui_lu97 and @HoldijkLars is ready to be ordered! Major societal and economic shifts have always been anchored in foundational physics. During the 1st Industrial Revolution, thermodynamics showed us how to harness energy to power steam engines.
9
47
3
247
23,330
Which is the better invention the transformer or the transformer?
1
1
301
Which is more poorly named the transformer or the transformer?
1
46
Sam Duffield retweeted
Ok I do want to soften my statement a bit. I wouldn’t claim that the numerical majority of papers in these conferences are overclaiming or fraudulent. It’s more like, as a reader, if you select for the papers that seem most exciting, then those ones will be majority overclaims.
5
5
311
34,541
CN101 - A Digital Thermodynamic Computer for Generative AI is now live on arXiv. Conventional chips spend energy suppressing noise to compute deterministically; CN101 is a noisy system engineered so its settling behavior is the computation, implemented in digital CMOS and evaluated on generative AI workloads from image generation across six chips to molecular free-energy estimation. In a companion post, @ColesThermoAI, our Chief Scientist, shares reflections on the journey and why AI inference needs hardware built for its physics. Paper: arxiv.org/abs/2608.00754 Patrick's post: normalcomputing.com/blog/ai-… Quanta article: quantamagazine.org/thermodyn… #ThermodynamicComputing #AIHardware
8
3
25
2,906
Surely the best lineup in Newcastle since Demba Ba + Papiss Cisse
This quoted post is unavailable.
7
1,525
Sam Duffield retweeted
cuthberto-carlos predictions for the final 2 games of the world cup! I for one am excited for these games. model pits all teams at around the same skill levels, so it will be an interesting to see who comes out on top! state-space-models.github.io…
1
2
95
cuthberto this is all your fault
cuthberto predictions for the semi-finals are out! As the games get tighter and more difficult to predict, the difference to the market increases I sure hope it's wrong on the England game though 👀🏴󠁧󠁢󠁥󠁮󠁧󠁿 state-space-models.github.io…
6
304
cuthberto predictions for the semi-finals are out! As the games get tighter and more difficult to predict, the difference to the market increases I sure hope it's wrong on the England game though 👀🏴󠁧󠁢󠁥󠁮󠁧󠁿 state-space-models.github.io…
1
1
2
472
Sam Duffield retweeted
Our book "Generative AI and Stochastic Thermodynamics: A Tale of Free Energies" is out this month. Over the coming weeks @sirui_lu97, @wellingmax and I will post about some of the topics it covers. Starting it off: heat and work in latent variable models and variational EM.
13
74
4
624
43,362
cuthberto has been killing the knockout games so far! 2 out of 4 correct scores and the other two off by a single goal. state-space-models.github.io…
1
92
Sam Duffield retweeted
knockout stages predictions are out! 2/3 correct scores at the 90th minute i think thats pretty impressive @Sam_Duffield ! state-space-models.github.io…
1
1
1
132
Sam Duffield retweeted
so how does the model compare to other predictions? I think pretty close! the model doesnt take into account home advantage of team USA, so we see a big discrepancy in model estimates 😱😱😱 do you guys think that the home advantage should be that big? state-space-models.github.io…
1
1
51
Sam Duffield retweeted
after sweden's most recent 5-1 win against tunisia, we saw the Sweden's attack and defense scores improve! On 11 June, @Sam_Duffield 's model predicted that 2-0 was the most likely outcome. now its 1-1! check out the model predictions here state-space-models.github.io…
1
58