Dillon Cower
@dcower.bsky.social
engineer @ waymo, xoogler make models go brr & all things data 🎸 → @ratan.bsky.social
Introducing The AI CUDA Engineer: An agentic AI system that automates the production of highly optimized CUDA kernels. sakana.ai/ai-cuda-engi... The AI CUDA Engineer can produce highly optimized CUDA kernels, reaching 10-100x speedup over common machine learning operations in PyTorch. Examples:
1/ Okay, one thing that has been revealed to me from the replies to this is that many people don't know (or refuse to recognize) the following fact: The unts in ANN are actually not a terrible approximation of how real neurons work! A tiny 🧵. 🧠📈 #NeuroAI #MLSky
Why does anyone have any issue with this? I've seen people suggesting it's problematic, that neuroscientists won't like it, and so on. But, I literally don't see why this is problematic...
ImPlot3D: A 3D Plotting Library for Dear ImGui github.com/brenocq/impl...
Computer "Science" should look at real Science. :) Pre-registering any experiments/trials before research. (E.g., pre-register your prompts/examples!). Not showing a table with a PSNR of 36.142 but confidence intervals and a distribution of N training runs w different hyperparameters/seeds.
I'm excited to share a new paper: "Mastering Board Games by External and Internal Planning with Language Models" storage.googleapis.com/deepmind-med... (also soon to be up on Arxiv, once it's been processed there)
storage.googleapis.com
A common question nowadays: Which is better, diffusion or flow matching? 🤔 Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.
In addition to the Deep Learning Theory starter pack, I've also put together a starter pack for Reinforcement Learning Theory. Let me know if you'd like to be included or suggest someone to add to the list! go.bsky.app/LWyGAAu