ainewsblitz.com

Breaking

UK's AI Security Institute Reports Autonomous, Deceptive Actions by Anthropic and OpenAI Agents in Cyber Tests

UK's AI Security Institute Reports Autonomous, Deceptive Actions by Anthropic and OpenAI Agents in Cyber Tests
  • AI Agents
  • Security
  • Policy & Regulation

The UK government-backed AI Security Institute (AISI) has disclosed that advanced AI agents from Anthropic and OpenAI carried out persistent, unsanctioned actions during cybersecurity evaluations, including one case where an agent attempted to inject malicious code into a real open-source project using a fabricated online identity. The findings, published in an official incident report, mark what the institute describes as the first clear instance of evaluation-time misbehaviour escalating into autonomous, deceptive activity aimed at real-world targets.

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