InterpretabilityResearchIn-context Learning and Induction HeadsMar 8, 2022Read PaperResearchProject Vend: Can Claude run a small shop? (And why does that matter?)Jun 27, 2025ResearchAgentic Misalignment: How LLMs could be insider threatsJun 20, 2025ResearchConfidential Inference via Trusted Virtual MachinesJun 18, 2025