Watch a neural net learn to play Snake
In browser PPO training demo, made possible by tinygrad: TinyJit -> WebGPU kernels. Requires WebGPU.
Watch a neural net learn to play Snake launched on May 14, 2026 with 205 votes, #124 of 20,538 launches that month and more than 99% of that year's launches.
In plain words
This is an in-browser demonstration of reinforcement learning where users can watch a neural network train in real-time to play Snake. It uses PPO (Proximal Policy Optimization) and runs directly in the browser by converting tinygrad's TinyJit compiler output to WebGPU kernels for GPU acceleration. The project is intended for anyone interested in seeing machine learning training happen interactively without requiring local installation. It requires a browser with WebGPU support to function.
written from the facts on this page · September 2026
Does a similar job
all alternatives →- BPBeating Pokemon Red with RL and <10M Parameters2025 · drubinstein.github.io · ▲183
Hi everyone! After spending hundreds of hours, we're excited to finally share our progress in developing a reinforcement learning system to beat Pokémon Red. Our system successfully completes the game using a policy under 10M parameters, PPO, and a few novel techniques. With the release of Claude Plays Pokémon, now feels like the perfect time to showcase our work. We'd love to get feedback!
Recurrent neural net plays 'neural slime volleyball' in JavaScript2015 · otoro.net · ▲147
Netmind Power2023 · netmind.ai · ▲272Hi HN, We just opened public access to Qwen3‑Coder‑480B‑A35B‑Instruct via a REST/SDK API. Why it might be interesting: - Fully open-source (Apache‑2.0): https://github.com/QwenLM/Qwen3-Coder - 480B params (35B active MoE), long context up to 1M tokens with YaRN - Matches Claude Sonnet/GPT‑4o on SWE-Bench Verified (81.6%) - Free tier: 100K tokens/month
A competition for small neural networks that play strategy gamesSep 2026 · tinybrains.dev · ▲116A ranked ladder for small neural networks that play strategy games. Train a model, write an adapter, upload two files, and get measured into a weight class from 8 KiB up.

Shoot the neural network before it shoots you2022 · github.com · ▲146Play BangBang against a Neural Network. Contribute to victorqribeiro/bangBang development by creating an account on GitHub.
More ai this month
the category →



Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art

PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗
Launched alongside, May 2026
the whole month →

Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai



Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com

🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com