Personal AI agent trains a chess transformer on dual RTX 4090 and battles Sunfish
andreisavu · x · 2026-10-28
A developer shows his personal AI agent "dot" autonomously running an ML project: training a transformer with a custom tokenizer to play chess on a workstation with two RTX 4090s. Per the chat log, dot played 20 games against Sunfish (3 wins, 17 losses, all ending in checkmate), used a three-ply mate helper 5 times, and reported a 90.8% legal-move rate before legality filtering — then proposed building a harness to register itself as a playable bot.
More from coding & agent
- Parallel's Decisions API lands on Merge Gateway at $0.001 per request — shensi · 2026-10-29
- Drew Breunig's State of Context Engineering: 6 tactics, one key tradeoff — rseroter · 2026-10-29
- GitHub demos Copilot Code Review Max with stacked PR merge at Universe — kimmonismus · 2026-10-29
- IBM TechXchange: Three Big Challenges of Adopting AI Agents in the Enterprise — craigmullins · 2026-10-29
- Pydantic Author Samuel Colvin on Setting Up Feedback Loops for Code-Writing Models — samuelcolvin · 2026-10-29
- Open-Source Coding Tools Climb T3 Charts: opencode Hits #2 Most Engaged Repo — MeetPatelTech · 2026-10-29