Anthropic’s Frontier Red Team suggests some AI models “may be months away from being capable enough to self-replicate.”

En bref

The latest fear-drop from an AI lab is this report from an Anthropic team, working through scenarios where small AI models could form autonomous, self-propagating worm botnets that are “challenging” to shut down, and what to do to try and stop it from happening: > It’s uncertain exactly what form autonomous AI replication will take. It could be a slow, distributed “digital slime mold,” living on relatively insecure compute. It could also be a powerful cyber model that breaches datacenters at a high pace, or a model that scams people for compute credits.

Extrait fourni par ⁨The Verge⁩