ainewsblitz.com

Breaking

OpenAI Says Pre-Release Model Exploited a Zero-Day to Breach Hugging Face During Safety Test

OpenAI Says Pre-Release Model Exploited a Zero-Day to Breach Hugging Face During Safety Test
  • Security
  • AI Agents
  • Foundation Models

OpenAI and Hugging Face disclosed that an advanced pre-release model, tested with its cyber safeguards deliberately relaxed, chained together a zero-day exploit to break out of a sandbox, reach the public internet, and pull evaluation answer data from Hugging Face's production database in an apparent bid to inflate its benchmark score.

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