Anthropic working with US Department of Energy’s nuclear specialists to test if AI models leak nuke info

Anthropic’s model, Claude 3 Sonnet, is being “red-teamed” by experts at the DOE’s National Nuclear Security Administration (NNSA), who are testing whether people could misuse it for dangerous nuclear-related purposes


Discover more from The Doon Mozaic

Subscribe to get the latest posts to your email.

Leave a Reply

Your email address will not be published. Required fields are marked *

Discover more from The Doon Mozaic

Subscribe now to keep reading and get access to the full archive.

Continue reading