Seemingly conscious AI risks

Aug 17

1 min read

AI systems are increasingly designed in ways that lead users to perceive them as conscious. This paper provides a unified framework connecting empirical hallmarks of consciousness attribution to a structured risk taxonomy of Seemingly Conscious AI (SCAI), AI systems that exhibit hallmarks which elicit consciousness attribution from users.

Related

Thanks Kimberly!

Recent Posts

See All

Invasion of the Self-Replicating AI-Malware Botnet

An AI risk much dumber—and therefore more likely—than extinction is arriving.

Fire Ants: an exemplar of Holophren Embodiment Design revealing AI concerns to urgently heed (UII w/Claude)

DM What do you know about what are commonly called "fire ants?" I'm fighting battles, and I need whatever you can muster to help me win this war, or be more effective in my battles spanning East Tenne

IMAGINE EVERY AI AGENT ON EARTH BUYING THE SAME CHEAP PAPER TOWELS

AI agents are doing our shopping for us, and wreaking havoc on the internet.