A New Trick Uses AI to Jailbreak AI Models—Including GPT-4
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 more about your ad choices. Visit podcastchoices.com/adchoices
Security, Spoken · SpokenLayer
December 11, 20235m 28s
Audio is streamed directly from the publisher (dovetail.prxu.org) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.
Show Notes
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