Astra blunders its way to resignation in chess test, rerun at Extra High reasoning
MikePFrank · x · 2026-09-06
MikePFrank tested Astra playing chess directly (no engine cheating) against an intermediate-level bot: the model stayed tied for much of the game but made multiple blunders and eventually resigned. He is rerunning the match with reasoning turned up to Extra High to see if more thinking budget fixes the play.
More from Fun
- rez0 claims he may have submitted nearly a third of all Google BugSwat bugs — rez0__ · 2026-10-23
- First-ever in-body prime editing treatment injected into a human — basedjensen · 2026-10-23
- AI Twitter drama: DeepSeek superfan blocked by scaling01 over model lore spat — teortaxesTex · 2026-10-23
- Run Lola Run director Tom Tykwer uses Seedance in hybrid AI filmmaking experiment — Uncanny_Harry · 2026-10-23
- "Still Worth Something" S01E01: a Pixar-style fully AI-animated comedy short — LPGroves · 2026-10-23
- Halloween AI short: "Careful who you bring home" — glagolef · 2026-10-23