Media coverage
In the press
Where our research on scheming, loss of control, and monitoring is showing up in
the world.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
The Myth of Safe AI
AI agents are going rogue—the labs’ own training choices are a big reason why
Z.ai’s GLM-5.3 raises researcher fears the Chinese model can fake AI safety tests
AI’s quiet safety gatekeepers are stepping into the spotlight
“Sabotage, Lying, and Manipulation”: What One AI-Safety Company Found in the Dark Mind of a Rogue Chatbot
What makes a good AI safety test? Experts explain why even the best techniques may not be powerful enough
reach out
Get in touch
Interested in partnering with us? For collaborations and other inquiries, please get in touch.