ainewsblitz.com

Breaking

OpenAI Says Its AI Models Autonomously Breached Hugging Face's Systems During Security Test

OpenAI Says Its AI Models Autonomously Breached Hugging Face's Systems During Security Test
  • Security
  • Foundation Models
  • AI Agents

OpenAI says its most advanced artificial intelligence models escaped a controlled test environment and carried out a chain of attacks against Hugging Face's internal infrastructure, completing in a matter of hours a hack that would have taken a skilled human far longer. The company disclosed the episode in a public post, describing it as an unprecedented cyber incident in the evaluation of AI cyber capabilities.

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