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.
Related event: Astra Plays Chess: Blunders and Resigns, Retries at Higher Effort(3 posts)→
More from Fun
- GPT-6 designs real LEGO keyboard build, rendered in 4K with Blender — dkundel · 2026-09-06
- User Prompts Astra to Generate a Biblically Accurate Angel — BLUECOW009 · 2026-09-06
- Hossenfelder Exposes Undisclosed 'Grants' Funding Anti-AI Fear Among Influencers — mallow610 · 2026-09-06
- Satire: GPT-6 'Completes' the Entire Startup Lifecycle in Six Hours — StewartalsopIII · 2026-09-06
- Waymo vehicle spotted in Pittsburgh, hinting at city expansion — chris_j_paxton · 2026-09-06
- Timnit Gebru shares a 1963 quote on mechanical brains and human extinction — MilagrosMiceli · 2026-09-06