Blog

Blog

2026-07-07: Superhuman Articulacy as an LLM Safety Target
2026-07-05: Pangram as a model for AI safety general managers
2026-06-29: More about me
2026-06-28: A reading list for generalists
2026-05-06: Blind deep-deployment evals for control & sabotage
2026-05-02: Dev tools in 2026
2026-04-30: Goblin Mode, 24 Hours Later
2026-01-02: The best year of my life