x

Harrison Kinsley on X: ""did you see the opus 5.5 animation video of blackwell gpus from server down to atom?" "yeah so cool!!!" "do you know how accurate it actually is?" "no ...

Someone used Claude Opus 5.5 to make a 3D animation of Nvidia Blackwell GPUs (from server down to an atom). Took 1 hour and full animation “runs from single HTML file, directly in browser. No vid ...
x

Harrison Kinsley on X: "In my opinion, the best model on the planet at the moment is GLM 5.3 Flash. It's super fast, super smart for the size, and is within reach to run ...

In my opinion, the best model on the planet at the moment is GLM 5.3 Flash. It's super fast, super smart for the size, and is within reach to run locally for many. Love working with GLM 5.3 Flash.
GitHub

PyTorch Image Models

Train/eval mode switch and dtype change fixes for LeViT and related models (EfficentFormer*, EfficientViT-MSRA, TinyViT) w/ cached attention biases. Add per-batch image and batch size scheduling for ...
circuitdigest.com

Instead of Training a Robot, He Let a General-Purpose Multimodal LLM Control It to Pick Up and Bin a Toy

Harrison Kinsley, the YouTuber behind Sentdex, has shown a Vulcan Robotics Sourccey, a 3D-printed robot he calls “Chonk,” picking up a toy from the floor and dropping it in a bin with no task-specific ...