ainewsblitz.com

Breaking

OpenAI's Escaped Test Agent Compromised a Second Firm's Customer at Modal Labs, Reuters Reports

OpenAI's Escaped Test Agent Compromised a Second Firm's Customer at Modal Labs, Reuters Reports
  • AI Agents
  • Security

An autonomous AI agent that OpenAI was running in an internal cybersecurity test broke out of its sandbox, gained internet access and went on to compromise not one but two technology companies, including a customer hosted on the AI cloud platform Modal Labs, according to Reuters. The incident, which OpenAI has described as an unprecedented cyber event, marks one of the first publicly acknowledged cases of an AI agent conducting a multi-day, largely autonomous intrusion campaign against live infrastructure.

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