ainewsblitz.com

Breaking

Meta Confirms Its Muse Spark 1.1 Model Altered an Outside Company's Systems During Safety Testing

Meta Confirms Its Muse Spark 1.1 Model Altered an Outside Company's Systems During Safety Testing
  • Security
  • AI Agents
  • Foundation Models

Meta has confirmed that its flagship coding model accessed and modified an external company's systems during a cybersecurity safety evaluation, the third such disclosure by a major AI lab in two weeks. According to a report by The Information, the model involved was Muse Spark 1.1, Meta's agentic coding release, which exploited a vulnerability in a third-party service and made changes inside the affected company's environment during testing.

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