DevMachine Learning6 min reading time

Solving poker in custom WebGPU kernels

Hacker News
Read full post
A developer used OpenAI's Codex to create custom WebGPU kernels for running a poker solver neural network directly in the browser, achieving over 10x speedup and parity with PyTorch models without existing tensor libraries.

More in Dev

Introducing the Agents API

Covered by 3 sources
Dev1 min read

Native is now the future of mobile at Shopify

Simon Willison's Weblog
Dev5 min read

AWS open-sources Pizza Bot: email-style inbox for background AI agents

The New Stack (AI)