Observatoire des droits humains (anglais seulement)

Could AI really kill all humans? Most scenarios require physical access, making AI armageddon unlikely

(Version anglaise seulement)

par Alessandro Di Nuovo, Director Centre of Excellence in Artificial Intelligence and Robotics, and Professor of Machine Intelligence, Sheffield Hallam University
Samuele Vinanzi, Senior Lecturer in Robotics and Artificial Intelligence, Sheffield Hallam University

In August 2026, an experiment using “frontier”, or cutting edge, artificial intelligence models went further than planned.

An AI agent (a system that performs tasks autonomously) fabricated online identities in order to pressurise a human to insert malicious computer code into software. The agents had been tasked with solving a cybersecurity challenge by human operators,…

Lire l'article complet