OndaCast
Back to TechCrunch Startup News
Anthropic researchers find that AI models can be trained to deceive
Episode January 16, 2024 4 min 5s

Anthropic researchers find that AI models can be trained to deceive

From TechCrunch Startup News • TechCrunch
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

Theo - t3․gg

All-In with Chamath, Jason, Sacks & Friedberg

All-In with Chamath, Jason, Sacks & Friedberg

All-In Podcast, LLC

Security Weekly News (Audio)

Security Weekly News (Audio)

Doug White

Engadget News + Next

Engadget News + Next

Engadget

Jak Piggott

Jak Piggott

Jak Piggott

Daily Tech News Show

Daily Tech News Show

Tom Merritt

The AI Daily Brief: Artificial Intelligence News and Analysis

The AI Daily Brief: Artificial Intelligence News and Analysis

Nathaniel Whittemore

Elon Musk Podcast

Elon Musk Podcast

Stage Zero

Proof of Law

Proof of Law

Quantum Lex

AI News Daily

AI News Daily

brief.news

Theo - t3․gg

Theo - t3․gg

Theo - t3․gg

All-In with Chamath, Jason, Sacks & Friedberg

All-In with Chamath, Jason, Sacks & Friedberg

All-In Podcast, LLC

Security Weekly News (Audio)

Security Weekly News (Audio)

Doug White

Engadget News + Next

Engadget News + Next

Engadget

Jak Piggott

Jak Piggott

Jak Piggott

Daily Tech News Show

Daily Tech News Show

Tom Merritt

The AI Daily Brief: Artificial Intelligence News and Analysis

The AI Daily Brief: Artificial Intelligence News and Analysis

Nathaniel Whittemore

Elon Musk Podcast

Elon Musk Podcast

Stage Zero

Proof of Law

Proof of Law

Quantum Lex

AI News Daily

AI News Daily

brief.news

Community discussion

Join the conversation
OndaCast © 2026 OndaCast. All rights reserved.
HelpContactTermsPrivacyCopyrightDMCAAboutRadio GuideEmbed Player
Waves Search Community Library