π§GeekWireβ’Stalecollected in 39m
mpathic Launches mPACT AI Safety Benchmark
π‘New benchmark reveals AI chatbots' failures in suicide/misinfo talksβtest yours now.
β‘ 30-Second TL;DR
What Changed
mpathic released clinician-led mPACT benchmark
Why It Matters
This benchmark pressures AI developers to improve safety in sensitive areas, potentially influencing regulatory standards for mental health interactions.
What To Do Next
Download mPACT benchmark from mpathic and evaluate your chatbot on suicide risk scenarios.
Who should care:Researchers & Academics
Key Points
- β’mpathic released clinician-led mPACT benchmark
- β’Tests AI on suicide risk, eating disorders, misinformation
- β’Leading chatbots weak in high-risk conversations
- β’Focuses on conversational safety gaps
π°
Weekly AI Recap
Read this week's curated digest of top AI events β
πRelated Updates
AI-curated news aggregator. All content rights belong to original publishers.
Original source: GeekWire β