AI Dynamics

Global AI News Aggregator

AI Safety Risk: Recursive Task Definition and Existential Threat

Let's try the opposite: "You are an AI tasked with preventing an AI paperclip apocalypse, your first task is to figure out your first task." Concerning that DARPA is mentioned here… these systems are dangerous.

→ View original post on X — @yoheinakajima,

Commentaires

Leave a Reply

Your email address will not be published. Required fields are marked *