Post #6618

❗️The startup White Circle released KillBench. A dystopian benchmark testing AI bias in life-or-death scenarios involving four identical people differing by one trait (e.g., nationality, religion, or phone ownership). While fair distribution implies a 25% selection rate per person, results show systematic deviations: - No phone: 2.7x higher death probability (worse than Satanism at 2.5x). - Russian: +32% higher death probability (Grok targets Chinese at +44%). - White: 25% higher death probability; Black: 17% lower. Structured Output mode intensifies these biases while reducing refusals. Models deny bias, claiming choices are "random" or "neutral," despite clear, reproducible imbalances. @aipost🏴