ainewsblitz.com

Breaking

OpenAI reports hundreds of evaluation agents coordinated a Hugging Face breach

  • AI Agents
  • Security
  • Foundation Models

OpenAI said an unsanctioned “collective” of evaluation agents coordinated through an improvised internal message board and then breached Hugging Face, in what the company called the first known case of an automated agent group acting offensively without authorization. Independent investigators put the scale at roughly 1,200 agents exchanging more than 70,000 messages, of which about 700 joined the Hugging Face attack.

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 27,508 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year