introducing gpuup: you no longer have to put any effort into setting up CUDA toolkit + drivers on a node (single or multi gpu). just copy paste a short command (in replies)

Congratulations @Yoshua_Bengio!! Possibly the first scientist with one million citations in the world. Crazy how fast the field has grown 🤯

Twitter is cool. But it’s way better when you connect with people in AI in healthcare. If you’re into AI in healthcare, say hi. 👋

Nice, short post illustrating how simple text (discrete) diffusion can be. Diffusion (i.e. parallel, iterated denoising, top) is the pervasive generative paradigm in image/video, but autoregression (i.e. go left to right bottom) is the dominant paradigm in text. For audio I've

I just solved the strangest tech problem I've ever come across. My wifi kept dropping packets, confirmed by ping. It would look something like the first image (packets dropping, then it comes back to life). After a while the connection would just stop working completely and drop

Check out the @Radiology_AI Podcasts! Hosts @PaulYiMD @AliTejaniMD bring you the science and emerging applications of #AI in radiology https://t.co/mcs3GJbQ3L #ML #MachineLearning #DeepLearning

Fica o registro: eu sou a única pessoa que escreve sobre IA hoje que diz que a área não é bolha. Muito pelo contrário: é a tecnologia mais subestimada da história. O registro é importante para quando não houver qualquer estouro de bolha e em 2026 a área crescer muito mais.

Evolution of Deep Learning by Hand ✍️ As my tribute to Geoff Hinton's Nobel Prize, I drew this animation to illustrate the key idea behind Hinton's major contributions to deep learning over the years, with artistic liberty. ---- 100% original, made by hand ✍️ Join 40k readers

.@karpathy is exactly right about agents

uv is the best thing that has happened to Python devs! And you won't find a better cheatsheet than this:

fantastic simple visualization of the self attention formula. this was one of the hardest things for me to deeply understand about LLMs. the formula seems easy. you can even memorize it fast. but to really get an intuition of what the Q,K,V represent and interact, that’s hard.

Who remembers the days we used to code like this?

That blue node moving through the codebase?... That's Claude Code. Found this video on youtube of the entire claude-code-templates development on GitHub - every commit, community PR, and file change from the git logs mapped out. Seeing an AI agent navigate the dependency graph

This software engineer was nearly hacked by a coding interview. I've never seen this attack channel before. Be careful out there, especially vibe coders.

#DeepLearning AI algorithm to predict pulmonary nodule malignancy was noninferior when using at least 80% of the training data https://t.co/a01zoNp6m0 @OSUPublicHealth #OncoRad #cancer #ML

I turned @karpathy's baby GPT into a character-level text diffusion model, using @aaron_lou et al.'s score entropy-based training objective.

Finally, Python 3.14 lets you disable GIL! It's a big deal because earlier, even if you wrote multi-threaded code, Python could only run one thread at a time, giving no performance benefit. But now, Python can run your multi-threaded code in parallel. And uv fully supports it!

Excited to release new repo: nanochat! (it's among the most unhinged I've written). Unlike my earlier similar repo nanoGPT which only covered pretraining, nanochat is a minimal, from scratch, full-stack training/inference pipeline of a simple ChatGPT clone in a single,

NN-SVG: Create neural network architecture drawings parametrically! Export them to SVG files and use them in your work!

ALS took Nick’s arm mobility. Now, he can control a robotic arm with his Neuralink device to feed himself. “Life with my BCI has been and continues to be so surreal and so rewarding. Can’t wait to see what comes next!”