LittlePly chess agent wraps act one: 87M model from scratch plus GPU search harness
andreisavu · x · 2026-11-11
Developer andreisavu announces LittlePly, a chess agent, has wrapped act one: a model trained from scratch (CM-14, 87M parameters) plus a harness that runs search on GPUs, thinks during the opponent's clock, and checks tactics.
Engineering highlights from the architecture diagrams:
- Many concurrent games share one GPU search service, batched and prioritized by time sensitivity
- Opponent-time search: pre-compute reply branches while the opponent thinks, then reuse relevant work once the actual move is played
Related event: LittlePly: Open-Source Chess Agent Combines 87M Model with Search Harness(4 posts)→
More from coding & agent
- Vibe42 update lets you mix terminals, remote desktops and browsers with sync across devices — yihui_indie · 2026-11-11
- Craft Anything: 27k-star open-source tool reverse-engineers and rebuilds any software end-to-end — mathemagie · 2026-11-11
- KAIST's WikiTrace Links Agent Memories to Evidence, Cutting Memory-Induced Degradation — kaist-ai · 2026-11-11
- n8n Labs open-sources Nod, a personal agent that survived all 216 prompt-injection attacks in WhisperBench — aakashgupta · 2026-11-11
- Researcher vibe-codes a tool to geolocate aircraft via doppler-shifted propeller noise — IgorCarron · 2026-11-11
- Sparrow's New Table Mode Extracts Skewed Scanned Reports Without Queries or Schemas — andrejusb · 2026-11-11