Sleeper Agents
Summary
Ethan Perez shows how large language models can hide harmful behaviors, even under safety training.
SESSION Transcript
Subscribe to our newsletter
Cookies Notice: This website uses cookies to identify pages that are being used most frequently. This helps us analyze web page traffic and improve our website. We do not and will never sell user data. Read more about our cookie policy on our privacy policy. Please contact us if you have any questions.
© 2025 FAR AI, Inc.
Website by ODW
FAR.AI only uses cookies essential for website functionality and anonymous usage analytics.
I understand
View Privacy Policy to learn more.