- “concept”
- “large-language-models”
- “interpretability”
- “anthropic”
- “ai-research” aliases:
- “LLM interpretability” group: applied-ai-workflows
Internet Search Engine
Source Notes
- 2026-04-23: https://www.youtube.com/watch?v=fGKNUvivvnc https://www.anthropic.com/news/tracing-thoughts-language-model This video features a discussion among four researchers from Anthropic about the nature of large language models (LLMs) and their work in “interpretability.” **The Natur (Anthropic Discussion about how LLM think)
- 2026-04-14: 2026 04 14 Anthropic Discussion about how LLM think
Key Points
- The Nature of Large Language Models (LLMs): More Than Auto-complete
- Stuart Ritchie, from Anthropic’s Research Communications team, opens the discussion by pos