EPISODE · Dec 11, 2023 · 7 MIN
A New Trick Uses AI to Jailbreak AI Models—Including GPT-4
from Security, Spoken · host WIRED
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
Embed this episode
NOW PLAYING
A New Trick Uses AI to Jailbreak AI Models—Including GPT-4
0:00
7:43
1×
No transcript for this episode yet
Similar Episodes
No similar episodes found.
Similar Podcasts
No similar podcasts found.
Frequently Asked Questions
How long is this episode of Security, Spoken?
This episode is 7 minutes long.
When was this Security, Spoken episode published?
This episode was published on December 11, 2023.
Can I download this Security, Spoken episode?
Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!