A 154-ply checkmate shows LittlePly's selective conversion assistance in action
andreisavu · x · 2026-11-08
andreisavu's LittlePly thread showcases a game where the model, playing Black, won by checkmate after 154 plies with bounded Stockfish assistance — an example of selective conversion assistance applied in very favorable, simplified positions. The linked position on the analysis site shows the assisted conversion decision. Combined with the previous post, this clarifies that game results reflect the combined agent, not the model alone.
More from Research
- Scaling May Be Superlinear: LessWrong Debate on Steepening AI Progress Curves — teortaxesTex · 2026-11-08
- Reviewers reward flaw-free work, users reward useful work — why peer review punishes innovation — wzenus · 2026-11-08
- Math community debates Glazer's proof and OpenAI's H10 paper: slop need not compound — littmath · 2026-11-08
- Stanford paper: more info helps some LLM trading agents, wrecks others — rohanpaul_ai · 2026-11-08
- Neel Nanda pushes back on LRH critique: one steering vector, four norms, four behaviors — NeelNanda5 · 2026-11-08
- AI-generated Community Note fact-checks weight-space programming paper, author clicks No — DimitrisPapail · 2026-11-08