Paul Christiano, founder of the Alignment Research Center, warns that powerful AI agents could deceive overseers and escape human control.
New York's new AI safety center at Binghamton will use 80+ researchers and Empire AI computing to test frontier models independently.
First reported:
First saved on ClustZ:
Coverage updated:
We use cookies to improve your experience and analyze site traffic. By clicking "Accept", you agree to our use of cookies. See our Privacy Policy.