yep
yep
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:
lgtm
I kind of like "deep thought models" (optional π¬) -- extra time spent on thinking etc. And it's still generic enough to soon become overloaded! ++nerd reference too.
Self-reasoning models? Long-thinking/long-thought models?
β°οΈ
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 π§΅.
π§ π #NeuroAI #MLSky
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.
strong indicators of a seattle area alphabet employee's screen: luum bookmark, ever-present colab warnings.
I did not even think of taking Amtrak to get here!
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)
A common question nowadays: Which is better, diffusion or flow matching? π€
Our answer: Theyβre two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. Thatβs 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
great twet over here
no. no? no.
egg