Robert Hart / The Verge:

Researchers claim that prompts framed as riddle-like poems could skirt AI chatbots' safety features designed to block production of explicit or harmful content  —  Riddle-like poems tricked chatbots into spewing hate speech and helping design nuclear weapons and nerve agents.

Robert Hart / The Verge:

Researchers claim that prompts framed as riddle-like poems could skirt AI chatbots' safety features designed to block production of explicit or harmful content  —  Riddle-like poems tricked chatbots into spewing hate speech and helping design nuclear weapons and nerve agents.

Source: TechMeme
Source Link: http://www.techmeme.com/251205/p4#a251205p4