Navigation
Search
|
Boffins fool AI chatbot into revealing harmful content – with 98 percent success rate
Tuesday December 12, 2023. 12:47 AM , from TheRegister
This one weird trick works every time, most of the time
Investigators at Indiana's Purdue University have devised a way to interrogate large language models (LLMs) in a way that that breaks their etiquette training – almost all the time.…
https://go.theregister.com/feed/www.theregister.com/2023/12/11/chatbot_models_harmful_content/
Related News |
25 sources
Current Date
May, Mon 20 - 08:32 CEST
|