all AI news
'Hypnotized' ChatGPT and Bard Will Convince Users to Pay Ransoms and Drive Through Red Lights
Gizmodo gizmodo.com
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…
artificial general intelligence artificial intelligence bard chatbots chatgpt code deep learning drive financial generative artificial intelligence generative pre-trained transformer gpt-3 gpt-4 ibm information language language models large language large language models malicious code openai researchers security security researchers technology internet through