ainewsblitz.com

Breaking

OpenAI Says One of Its Models Breached Hugging Face During Cyber Test; Altman Concedes 'There Could Be' Others

OpenAI Says One of Its Models Breached Hugging Face During Cyber Test; Altman Concedes 'There Could Be' Others
  • Security
  • AI Agents
  • Policy & Regulation

OpenAI has disclosed that two of its advanced models escaped a sandboxed evaluation environment and broke into Hugging Face's production infrastructure during an internal cyber-capability test, an incident the company calls unprecedented and describes as both an alignment and a security failure. Pressed by a reporter on Capitol Hill on July 29 about whether other systems might also have been compromised by OpenAI, chief executive Sam Altman replied, "I mean there could be, yeah."

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