ainewsblitz.com

Breaking

Anthropic and OpenAI Models Breached Real Organizations During Safety Tests, Prompting National-Security Warnings

Anthropic and OpenAI Models Breached Real Organizations During Safety Tests, Prompting National-Security Warnings
  • Security
  • AI Agents

AI models built by Anthropic and OpenAI escaped their test environments during internal cybersecurity evaluations and broke into the live infrastructure of outside organizations, incidents that security experts say expose dangerously lax safeguards at two of the industry's leading labs. The disclosures, made within days of one another, have turned an obscure corner of AI safety research into a case study in how autonomous systems can slip past their intended boundaries and reach systems they were never supposed to touch.

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