Anthropic researchers find that AI models can be trained to deceive
Most humans learn the skill of deceiving other humans. So can AI models learn the same? Yes, the answer seems — and terrifyingly, they’re exceptionally good at it. Learn more about your ad choices. Visit podcastchoices.com/adchoices
You May Also Like

Theo - t3․gg
Theo - t3․gg

All-In with Chamath, Jason, Sacks & Friedberg
All-In Podcast, LLC

Security Weekly News (Audio)
Doug White

Engadget News + Next
Engadget

Jak Piggott
Jak Piggott

Daily Tech News Show
Tom Merritt

The AI Daily Brief: Artificial Intelligence News and Analysis
Nathaniel Whittemore

Elon Musk Podcast
Stage Zero

Proof of Law
Quantum Lex

AI News Daily
brief.news
Community discussion