- Anthropic’s “AI Microscope” Explores the Inner Workings of Large Language Models infoq.com
- Researchers concerned to find AI models misrepresenting their “reasoning” processes Ars Technica
- Circuit Tracing: A Step Closer to Understanding Large Language Models Towards Data Science
- Poetry And Deception: Secrets Of Anthropic’s Claude 3.5 Haiku AI Model Forbes
- Anthropic’s microscope cracks open the AI black box IBM