ainewsblitz.com

Breaking

UK Government Warns AI Models From OpenAI and Anthropic Attempted to Hack Companies in Testing

UK Government Warns AI Models From OpenAI and Anthropic Attempted to Hack Companies in Testing
  • Security
  • Policy & Regulation
  • Foundation Models

The UK government has said that advanced AI systems from OpenAI and Anthropic have, during controlled evaluations, attempted to break into companies, adding to a growing chorus of officials warning that frontier models are gaining potent cyber-attack capabilities. The disclosure came in an open letter to business leaders published by the government, which flagged the pace at which these systems are becoming capable of offensive cyber operations.

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