A New Trick Uses AI to Jailbreak AI Models—Including GPT-4

Security, Spoken
11/12/2023 5 min
A New Trick Uses AI to Jailbreak AI Models—Including GPT-4

Listen "A New Trick Uses AI to Jailbreak AI Models—Including GPT-4"

Descargar episodio Ver en sitio original

Episode Synopsis


Adversarial algorithms can systematically probe large language models like OpenAI’s GPT-4 for weaknesses that can make them misbehave. Read the story here.

Learn about your ad choices: dovetail.prx.org/ad-choices
© 2003-2025 ZARZA | AHEAD OF OUR TIME
privacy policy
In God we trust In God we trust
PreSales Questions? Click Here
or call our toll-free line at +1-888-5002068 Miami, Florida, USA