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.
AI models that lie, cheat and plot murder: how dangerous are LLMs really?
Is AI Capable of 'Scheming'? What OpenAI Found When Testing for Tricky Behavior
AI models are schemers that could cause 'serious harm' in the future. Here's the solution.
Research on AI models deliberately lying is wild
AI Is Scheming, and Stopping It Won’t Be Easy, Study Finds
AI models know when they're being tested - and change their behavior, research shows
reach out
Get in touch
Interested in partnering with us? For collaborations and other inquiries, please get in touch.