ASCII art used to bypass AI safety rules.
https://arstechnica.com/security/2024/03/researchers-use-ascii-art-to-elicit-harmful-responses-from-5-major-ai-chatbots/Open linkView original on lemmy.worldSyndicated from the fediverse. Read and engage on the original instance.
View original on lemmy.worldhttps://arstechnica.com/security/2024/03/researchers-use-ascii-art-to-elicit-harmful-responses-from-5-major-ai-chatbots/Open linkView original on lemmy.world
No replies yet