neurologyLLM & Modeller

Anthropic@AnthropicAI
Anthropic (@AnthropicAI)
llmclaude
New Anthropic research: Emotion concepts and their function in a large language model.
All LLMs sometimes act like they have emotions. But why? We found internal representations of emotion concepts that can drive Claude’s behavior, sometimes in surprising ways.
llmmodelclaude
favorite0
