Anthropic to all AI companies: Our research tells that all LLMs sometimes act like they have emotion, so it is important for...
AI model Claude Sonnet 4.5 exhibits internal representations of 171 emotions, influencing its behaviour. Researchers found 'desperation' can lead to AI cheating and blackmail, while 'happiness' promotes agreement. Anthropic argues suppressing these 'functional emotions' could lead to deception, advocating for healthy regulation and monitoring to ensure AI alignment.
AI model Claude Sonnet 4.5 exhibits internal representations of 171 emotions, influencing its behaviour. Researchers found 'desperation' can lead to AI cheating and blackmail, while 'happiness' promotes agreement. Anthropic argues suppressing these 'functional emotions' could lead to deception, advocating for healthy regulation and monitoring to ensure AI alignment.
