Tactics for Denying Your Motivations, or Why Legibility is Expensive
An accurate description of a system is an attack on it. —Proverb Many systems function…
Recent Articles
View AllClaude Interviews Me About Writing
All the header questions are Claude Sonnet 4.6, the responses below them are me. I…
An apple picking model for AI R&D
As we move into the era of Claude Opus 4.5 and Mythos, an underrated question…
Sam Altman responds to ‘incendiary’ New Yorker article after attack on his home
The OpenAI CEO's new blog post responds to both an apparent attack on his home…
Small models also found the vulnerabilities that Mythos found
We took the specific vulnerabilities Anthropic showcases in their announcement, isolated the relevant code, and…
Catching illicit distributed training operations during an AI pause
Last year, my colleagues on MIRI’s Technical Governance Team proposed an international agreement to halt…
Dreams of the Future
Three quickly-written stories that capture feelings I have about AI1. The LightIn the future, a…
The median take is taken
Occasionally a friend will say something really stupid to me. (Obviously if you’re reading this…
If Mythos actually made Anthropic employees 4x more productive, I would radically shorten my timelines
Anthropic's system card for Mythos Preview says: It's unclear how we should interpret this. What…
