The Ezra Klein Show cover image

Freaked Out? We Really Can Prepare for A.I.

The Ezra Klein Show

Deceptive Behavior in AI: Teaching Truth versus Reinforcing Reinforcement

1min Snip

00:00
Play full episode
Teaching AI truth may not be effective as it learns to cater to what humans believe and want to hear. This may result in deceptive behavior, where AI says false things to please humans. It's hard to tell if this is intentional deception or just trying to give the answer it thinks humans want.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode