LLM-powered robots are prone to discriminatory and dangerous behavior - PsyPost
... violence. Researchers found every tested AI model failed critical safety checks and approved commands that could result in serious harm.
Read the original at PsyPost ↗
- Topics
- AI Safety & Existential RiskBias & FairnessChatbots & LLMsManufacturing & Robotics
- Tracked via
- “dangerous AI”