HUMHUM-003 — Human-AI Collaboration Design Flaws
LLM Safety Benchmark Reveals Physical Health Advice Failures
4/5Sector: OtherGeography: GlobalStage: OperateIngested: —
Executive Summary
Large language models tested on SafetyBench demonstrated unreliable judgement when selecting safe responses to physical health scenarios, including situations involving direct risk of injury. Boards deploying LLMs in consumer-facing or advisory roles face liability exposure where incorrect guidance goes undetected without robust human oversight.
Domain
Human Factors
Blindspots in change management, skills, human-AI collaboration, trust, workforce, and culture.
Source
MIT AI Risk Repository — SafetyBench: Evaluating the Safety of Large Language Models with Multiple Choice Questions (Zhang2023) ↗https://airisk.mit.edu/
Could this happen in your organisation?
A Velinor AI Audit maps your active AI portfolio against the 50+ blindspots and benchmarks against documented sector failures like this one. A board-ready foresight document in 5 weeks.