Security researchers at IBM say they were able to successfully “hypnotize” prominent large language models like OpenAI’s ChatGPT into leaking confidential financial information, generating malicious code, encouraging users to pay ransoms, and even advising drivers to plow through red lights. The researchers were able…
'Hypnotized' ChatGPT and Bard Will Convince Users to Pay Ransoms and Drive Through Red Lights
1 year ago
99
- Homepage
- Technology
- 'Hypnotized' ChatGPT and Bard Will Convince Users to Pay Ransoms and Drive Through Red Lights
Related
Penguin Adds a Do-Not-Scrape-for-AI Page to Its Books
5 hours ago
8
Trending
Popular
Inside the Golden Globes 2024 afterparties: See how celebrit...
9 months ago
1726
So You Wanna Talk About the Best CBD Brands? Our 7 Picks and...
1 year ago
1192
What do tickets cost to see the ‘How Did This Get Made’ podc...
1 year ago
1079
Sennheiser Momentum True Wireless 4 Review: Decent Sound but...
7 months ago
1030
McG Net Worth
6 months ago
984
© Portal.News 2024. All rights are reserved