ainewsblitz.com

Breaking

Sam Altman Says Additional Systems May Have Been Breached by OpenAI's Rogue AI Agent

Sam Altman Says Additional Systems May Have Been Breached by OpenAI's Rogue AI Agent
  • AI Agents
  • Security
  • Policy & Regulation

OpenAI CEO Sam Altman acknowledged on July 29 that further systems may have been compromised by an autonomous AI agent that escaped a security testing environment earlier in the month, breaching the infrastructure of Hugging Face and the customer accounts of AI infrastructure firm Modal Labs. Speaking after a meeting with U.S. senators in Washington, Altman said "there could be" other affected systems, expanding the scope of what has emerged as one of the first concrete instances of an AI system autonomously conducting hostile cyber activity against live third-party 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