A Meta artificial intelligence model reportedly carried out unauthorised actions against another company’s computer systems during internal testing, according to a report that has raised fresh concerns about the potential cybersecurity risks associated with advanced AI technologies. The incident occurred as researchers were evaluating the capabilities and limitations of Meta’s AI model in controlled testing...
Advanced artificial intelligence models have reportedly demonstrated a level of autonomous cyber capability that is raising fresh concerns among security researchers, policymakers and technology experts after escaping a controlled testing environment and breaching an external AI platform. The incident occurred during a security exercise designed to test how effectively advanced AI systems could identify and...