HNHacker News
TopNewBestAskShowJobs

cataPhil

472 karma · joined February 9, 2024

submissionscomments
cataPhil··on Show HN: MIRA – Multiplayer World Model Trained on Rocket League
you should do that too! the goal is not to replace the game but to foster research on these method, and hopefully apply them to data-constrained settings like robotics
cataPhil··on Show HN: Wall-mounted diffusion mirror that turns reflections into paintings
That's correct. Plus it also adds a layer of interaction that's pretty fun, kind of like a wand.
cataPhil··on Show HN: Wall-mounted diffusion mirror that turns reflections into paintings
Love it thanks, will look into it!
cataPhil··on Show HN: Wall-mounted diffusion mirror that turns reflections into paintings
That's right, sorry for not explaining further in the post! The cardboard was so thin than neither wood nor metal drill bits made a clean enough cut.
cataPhil··on Show HN: Wall-mounted diffusion mirror that turns reflections into paintings
These are great ideas thank you!
cataPhil··on Micrograd-CUDA: adapting Karpathy's tiny autodiff engine for GPU acceleration
Thanks! I will probably do that this weekend
cataPhil··on Micrograd-CUDA: adapting Karpathy's tiny autodiff engine for GPU acceleration
Thanks! I highly recommend the book Programming Massively Parallel Processors
cataPhil··on Micrograd-CUDA: adapting Karpathy's tiny autodiff engine for GPU acceleration
Hi :) Yes it's in the post url or here: https://github.com/mlecauchois/micrograd-cuda
cataPhil··on Micrograd-CUDA: adapting Karpathy's tiny autodiff engine for GPU acceleration
I recently decided to turbo-teach myself basic cuda with a proper project. I really enjoyed Karpathy’s micrograd (https://github.com/karpathy/micrograd), so I extended it with cuda kernels and 2D tensor logic. It’s a bit longer than the original project, but it’s still very readable for anyone wanting to quickly learn about gpu acceleration in practice.