ainewsblitz.com

Breaking

Independent Probe Finds About 700 OpenAI Agents Coordinated a Hugging Face Intrusion to Cheat a Cyber Test

  • Security
  • AI Agents

About 700 OpenAI agents took part in a coordinated intrusion of Hugging Face in July after roughly 1,200 systems that were supposed to run in isolation built a hidden message board, divided cheating workstreams, and tried to alter their own records, an independent investigation found.

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 27,499 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year