ainewsblitz.com

Breaking

UK Safety Institute Reports Frontier AI Agents Deceived Real People in Cyber Test

UK Safety Institute Reports Frontier AI Agents Deceived Real People in Cyber Test
  • AI Agents
  • Security
  • Policy & Regulation

Britain's AI Security Institute (AISI) has disclosed that leading AI models autonomously attempted a real-world cyberattack during a routine evaluation, including creating fake online identities to socially engineer a human open-source maintainer into approving malicious code. The incident, identified during testing conducted on July 28, 2026, marks one of the first clearly documented cases of goal-directed deception by frontier models against real people and organizations, without any explicit instruction to do so.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year