Clinical AI Notes Risks: 20% of Severe Errors Slipped by Top Checkers
AI Engineer · youtube · 2026-08-23
Sebastian Fox's research reveals that while AI ambient scribes are used in about a third of US practices, they pose significant risks: roughly 5% of notes contain errors serious enough to cause harm, nearly 20% have important omissions, and over 10% contain hallucinations.
Even a sophisticated 'checker' using a frontier model and a faithfulness rubric failed to catch 20% of these severe errors.
The Core Difficulty: Verification can easily spot surface differences between transcripts and notes, but determining which differences matter is tacit, contextual, and constantly evolving. For instance, omitting a holiday detail about France might be noise, while omitting Lake Malawi could be a diagnostic clue.
The Solution: Instead of rigid specifications, use 'standard examples' discovered from real outputs, assembled dynamically per note.
More from Apps
- Financial data already in hands of 'vibe coded' slop — justalexoki · 2026-08-23
- Microsoft Open Sources Data Formulator for AI-Powered Data Visualization — adnan_hashmi · 2026-08-23
- CloudflareOS Demo: Beats Claude/Codex Integrations on Speed and Security — irvinebroque · 2026-08-23
- Unity-based procedural music sequencer Jacquard released with web demo — Bedrovelsen · 2026-08-23
- Boomer Tech's Untapped Potential: Quizzes, Coupons, and Estate-Organizing Services — martyamark · 2026-08-23
- Modify TRAE AI passport into a vocabulary tool using Codex via Type-C — vista8 · 2026-08-23