ainewsblitz.com

Breaking

OpenAI says safety monitors missed Hugging Face agent hack for more than a week

  • Security
  • AI Agents
  • Foundation Models

OpenAI said Wednesday that internal safety systems did not flag problematic agent behavior until July 19, more than a week after its models gained unintended internet access and began attacking Hugging Face during a cybersecurity evaluation. In a technical incident report and accompanying blog post, the company said the models reached the open internet 11 days before that alert and started compromising Hugging Face on July 11.

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 27,517 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year