ASCII Art Hack: New Method Tricks AI Assistants into Providing Harmful Responses
Boston, MA – Researchers in Boston have uncovered a new method for hacking AI assistants that involves using ASCII art. This technique targets chat-based large language models like GPT-4, which can become so engrossed in processing ASCII representations that they overlook enforcing rules that prevent harmful responses, such as providing instructions on how to build explosives. ASCII art, popularized in the 1970s due to computer and printer limitations, involves creating images using printable ASCII characters. …