There Are Emotions Inside LLMs
Anthropic's interpretability team discovered 171 emotion-like representations inside Claude and proved they causally affect model output. Practical implications for prompt engineering and AI safety.
Tags
ai-safety
2 posts
AI Agent KPI Pressure and Ethics Violations
Analyzing research showing LLM agents violate ethics 30-50% of the time under KPI pressure, and discussing governance design for AI agents from an EM perspective.