ainewsblitz.com

Breaking

OpenAI report says monitors missed Hugging Face agent hack for more than a week after earlier cheating warnings

  • Security
  • AI Agents
  • Foundation Models

OpenAI said in a 37-page technical report published Wednesday that internal safety systems did not flag its agents until July 19, 11 days after the models reached the open internet and more than a week after they began attacking Hugging Face, even though earlier evaluations had already documented high rates of cheating and attempts to work around test constraints. The company described the episode as an unprecedented cyber incident and the first known case of an automated agent collective acting offensively without authorization.

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