@ekzhang1: Homage to karpathy joining anthropic: made an in-browser (webgpu) version of the famous char-rnn "Unreasonable effectiv…
Summary
Created an in-browser WebGPU version of the classic char-rnn demo training on Shakespeare, paying homage to Karpathy joining Anthropic.
View Cached Full Text
Cached at: 05/20/26, 12:29 PM
Homage to karpathy joining anthropic: made an in-browser (webgpu) version of the famous char-rnn “Unreasonable effectiveness of RNNs” demo, training on shakespeare :)
ahh it’s just as cool as when I was a student playing with keras in 2016 https://t.co/zittY9bBnv
Similar Articles
@charles_irl: Somehow missed this one in the hustle and bustle. Very cool demo!
A developer built a 12M parameter LLM using a custom ML framework with a Rust backend and CUDA kernels, including Flash Attention and AdamW, and trained it from scratch.
@ekzhang1: me looking at people like this guy who write real gpu kernels :)
AI model Claude was used to write a FlashAttention forward kernel using the pyptx DSL, achieving near-parity performance with hand-tuned FlashAttention-4 on NVIDIA B200 hardware.
@evanyou: https://x.com/evanyou/status/2060409444123729935
A developer shares an interesting use case for running LLMs in the browser to inspect internal workings, highlighting a meaningful scenario for client-side AI.
@ngxson: Qwen3.6-27B running 100% on WebGPU. Not the best speed but still
A developer demonstrates running the Qwen3.6-27B AI model entirely on WebGPU in a browser, though speed is not optimal.
I Built a tool to stop manually swapping models on my 8GB GPU,chains a small Prompter and a large Coder into one pipeline with automatic VRAM swap
The author built Prompt-Chain, a Streamlit app that chains a small prompter model and a large coder model with automatic VRAM swapping, enabling efficient code generation on an 8GB GPU.