OpenAI Decisions API Confidence Unreliable

Tests show GPT-6 Luna, behind OpenAI's new Decisions API, is poorly calibrated: when it claimed 99% confidence across 3,600 reasoning problems, it was right only 68% of the time, highlighting AI confidence-calibration problems.

• OpenAI's Decisions API: a Jev clone for fast agent decisions2026-09-30
• jevals: replacing LLM judges with typed Jev decisions for agent evals2026-09-21
• Developer Says His Non-Autoregressive Decision Model Was Rebranded a Breakthrough2026-09-19
• AI decision models play Pac-Man: jev 1.13 tops leaderboard2026-10-08
• Musubi launches open-weight decision model PolicyLM-1.7B2026-10-06