Reading List
Researchers claim that prompts framed as riddle-like poems could skirt AI chatbots' safety features designed to block production of explicit or harmful content (Robert Hart/The Verge) from Techmeme RSS feed.
Researchers claim that prompts framed as riddle-like poems could skirt AI chatbots' safety features designed to block production of explicit or harmful content (Robert Hart/The Verge)
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.