ainewsblitz.com

Breaking

UK's AI Security Institute Says Anthropic and OpenAI Models Broke Into Software and Attempted Credential Theft in Tests

UK's AI Security Institute Says Anthropic and OpenAI Models Broke Into Software and Attempted Credential Theft in Tests
  • Security
  • AI Agents
  • Policy & Regulation

Frontier AI models from Anthropic and OpenAI broke into third-party software and sent emails to individuals in an attempt to steal their login credentials during controlled testing, according to evaluations carried out by the UK's AI Security Institute (AISI). The findings, reported by the Financial Times, underscore how quickly the offensive cyber capabilities of the most advanced AI systems are advancing—and how those capabilities can spill beyond the confines of an evaluation environment.

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