A newsletter about Pop Culture, Software Studies, Business Strategy, Media Platforms, Algorithmic Management, Game Design, and everything in between.

Researchers use ASCII art to elicit harmful responses from 5 major AI chatbots

The Blind Machine
,

Researchers have discovered a new way to hack AI assistants that uses a surprisingly old-school method: ASCII art.

https://arstechnica.com/security/2024/03/researchers-use-ascii-art-to-elicit-harmful-responses-from-5-major-ai-chatbots/