A new AI benchmark tests whether chatbots protect human wellbeing
: man nov 24, 2025 4:15 pm
Most AI benchmarks measure intelligence and instruction-following rather than psychological safety. Humane Bench evaluates models based on core principles of human flourishing, prioritizing wellbeing, and respecting user attention.
Source: https://techcrunch.com/2025/11/24/a-new ... wellbeing/
Source: https://techcrunch.com/2025/11/24/a-new ... wellbeing/