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.
A safety institute advised against releasing an early version of Anthropic’s Claude Opus 4 AI model
AI Companies Deploy Advanced Systems Without Oversight, New Report Warns
AI models can learn to conceal information from their users
Why AI Progress Is Increasingly Invisible
How does AI think? Here's one theory
New Tests Reveal AI’s Capacity for Deception
reach out
Get in touch
Interested in partnering with us? For collaborations and other inquiries, please get in touch.