{"type":"post","id":"google-s-thinking-in-bets-project-page-recording-a470d5","slug":"google-s-thinking-in-bets-project-page-recording-a470d5","title":"Google's Thinking-in-Bets project page: recording claims and confidence before feedback cuts false reversals from 12.2% to 0.02%","description":"Google’s October 2026 Thinking-in-Bets report proposes that an agent record claims, evidence, and confidence before it reads user feedback.","retrieval_nugget":"Google’s October 2026 Thinking-in-Bets report proposes that an agent record claims, evidence, and confidence before it reads user feedback. Across five Gemini models and eight benchmarks, the authors report sharply fewer false reversals of correct work. It is a training-free workflow rather than a trained model or a shipped product.","published_at":"2026-11-01","updated_at":"2026-11-07","record_date":"2026-11-01","date_kind":"published_at","topics":["google","gemini"],"entities":["Google","Thinking-in-Bets","Nghi D. Q. Bui","Gemini","Annie Duke","JevAct"],"related_patterns":["verification-bandwidth-is-the-scarce-resource"],"novelty_label":"same_event","prior_refs":[],"source_url":"https://thinking-in-bets.github.io/","source_urls":["https://thinking-in-bets.github.io/"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:google-s-thinking-in-bets-project-page-recording-a470d5","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/google-s-thinking-in-bets-project-page-recording-a470d5/","markdown":"https://newruntime.com/posts/google-s-thinking-in-bets-project-page-recording-a470d5.md","json":"https://newruntime.com/posts/google-s-thinking-in-bets-project-page-recording-a470d5.json"},"markdown_url":"https://newruntime.com/posts/google-s-thinking-in-bets-project-page-recording-a470d5.md","next_reads":[{"type":"topic","path":"/topics/google/","url":"https://newruntime.com/topics/google/","title":"Google","reason":"Explore the google topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/google.md","json_url":"https://newruntime.com/topics/google.json"},{"type":"topic","path":"/topics/gemini/","url":"https://newruntime.com/topics/gemini/","title":"Gemini","reason":"Explore the gemini topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/gemini.md","json_url":"https://newruntime.com/topics/gemini.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}