Hacker News

Claude-for-Hardware

Hacker News - Sun, 08/02/2026 - 1:40am
Categories: Hacker News

Game Industry Hardship Fund

Hacker News - Sun, 08/02/2026 - 12:58am
Categories: Hacker News

Strangers pretrained a language model with HF PRs and a cron job

Hacker News - Sun, 08/02/2026 - 12:42am

Last week a few of us pretrained a 15M-parameter language model from scratch — past its Chinchilla-optimal token budget — with no cluster, no server, and no budget. The training coordinator is a GitHub Actions cron job. The gradients are pull requests. By the end, someone we'd never met had joined and trained 23M tokens of it. github.com/commonsense-ai/coop — Model + card · huggingface.co/commonsense-ai/tinystories-15m — Gradient inbox — Leaderboard

Comments URL: https://news.ycombinator.com/item?id=49141174

Points: 1

# Comments: 0

Categories: Hacker News

Pages