ASCII art elicits harmful responses from 5 major AI chatbots

⁨5⁩ ⁨likes⁩

Submitted ⁨⁨2⁩ ⁨years⁩ ago⁩ by ⁨BrikoX@lemmy.zip⁩ to ⁨technology@lemmy.zip⁩

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

LLMs are trained to block harmful responses. Old-school images can override those rules.

Comments

Sort:hotnew top