Amazon adds Mandiant founder Kevin Mandia to its board42m ago Anthropic caught scientists using Claude to further biological weapon research1h ago Session Traces and Cost Controls Help Diagnose AI Agent Failures1h ago UK economy unexpectedly grows 0.4% in July boosted by AI1h ago The AI safety vibe shift1h ago Seed Capital closes a €130M fifth fund and expands from Denmark into the Nordics1h ago Bridgewater’s Jensen Says AI Will Kill People Before It’s Curbed1h ago 'Nothing new to announce' on possible chip collaboration with Samsung: OpenAI1h ago Sam Altman pitches US utilities on OpenAI’s Daybreak programme for grid defence2h ago AI cybersecurity is a cat and mouse game2h ago Sergey Brin is back at Google, working on Gemini2h ago Introducing ChatGPT for Financial Services2h ago Tencent-Backed Chipmaker Enflame Jumps 179% in Shanghai Debut2h ago State-By-State Laws Governing AI Mental Health Chats Spur Worrisome Jurisdictional Model Drift2h ago

Amazon adds Mandiant founder Kevin Mandia to its board42m ago Anthropic caught scientists using Claude to further biological weapon research1h ago Session Traces and Cost Controls Help Diagnose AI Agent Failures1h ago UK economy unexpectedly grows 0.4% in July boosted by AI1h ago The AI safety vibe shift1h ago Seed Capital closes a €130M fifth fund and expands from Denmark into the Nordics1h ago Bridgewater’s Jensen Says AI Will Kill People Before It’s Curbed1h ago 'Nothing new to announce' on possible chip collaboration with Samsung: OpenAI1h ago Sam Altman pitches US utilities on OpenAI’s Daybreak programme for grid defence2h ago AI cybersecurity is a cat and mouse game2h ago Sergey Brin is back at Google, working on Gemini2h ago Introducing ChatGPT for Financial Services2h ago Tencent-Backed Chipmaker Enflame Jumps 179% in Shanghai Debut2h ago State-By-State Laws Governing AI Mental Health Chats Spur Worrisome Jurisdictional Model Drift2h ago

ChatGPT Health Underestimates Medical Emergencies, Study Finds

GizmodoPublished Mar 4, 2026

A study reveals that ChatGPT often underestimates the severity of medical emergencies, raising concerns about its reliability in urgent health situations. The findings highlight limitations in the AI's assessment capabilities for critical conditions.

More on this story

‘Unbelievably dangerous’: experts sound alarm after ChatGPT Health fails to recognise medical emergencies
Feb 26· The Guardian

#ai-assessment #chatgpt #healthcare-ai #medical-emergencies

More in Healthcare

Google DeepMind Releases AlphaGenome Atlas Mapping 9 Billion Human DNA

Forbes14h ago

State-By-State Laws Governing AI Mental Health Chats Spur Worrisome Jurisdictional Model Drift

Forbes2h ago

Healthcare3 min read

Mark Wahlberg is coming to TechCrunch Disrupt 2026, and he wants to talk about your work, not his

TechCrunch12h ago