An AI security researcher has developed a proof of concept that uses subtle, seemingly benign prompts to get GPT and Gemini to generate inappropriate content.
from darkreading https://ift.tt/SYsRjCH
via IFTTT
An AI security researcher has developed a proof of concept that uses subtle, seemingly benign prompts to get GPT and Gemini to generate inappropriate content.
from darkreading https://ift.tt/SYsRjCH
via IFTTT