Very good article what it would take for AI to have "agency" and self-preservation goals (w/ a few quotes from me).
& I appreciate the reiterated debunking of the "GPT-4 on its own lied to a TaskRabbit worker to solve a captcha" story.
www.quantamagazine.org/why-do-we-te...
Our tales of AI developing the will to survive, commandeer resources, and manipulate people say more about us than they do about language models.
