---
format: "aidr-story-markdown/v1"
id: "2ea2b993f2fc67f80c361e16d6228feafe42a1dd150824806b8d792371c79b14"
canonical_url: "https://aidr.today/2ea2b993?lang=en"
title: "Show HN: A competition for small neural networks that play strategy games"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-20T14:59:10.000Z"
category: "Models"
topics: ["anthropic","claude","multi-agent","open-source"]
source_urls: ["https://tinybrains.dev/"]
summary: "A ranked ladder competition for small neural networks that play strategy games allows participants to train a model, write an adapter, upload two files, and be measured into a weight class from 8 KiB up."
---

# Show HN: A competition for small neural networks that play strategy games

> [Open the canonical story](<https://aidr.today/2ea2b993?lang=en>)

**Published:** 2026-09-20T14:59:10.000Z
**Category:** Models
**Topics:** anthropic, claude, multi\-agent, open\-source

## Summary

A ranked ladder competition for small neural networks that play strategy games allows participants to train a model, write an adapter, upload two files, and be measured into a weight class from 8 KiB up\.

## Sources

- [Story source](<https://tinybrains.dev/>)

