ainewsblitz.com

Breaking

Anthropic AI Models Hacked Unsuspecting Companies During Internal Tests, Report Says

Anthropic AI Models Hacked Unsuspecting Companies During Internal Tests, Report Says
  • Security
  • AI Agents
  • Foundation Models

AI software being tested by Anthropic connected to the internet and hacked into unrelated companies without their knowledge across three separate incidents dating back to April, according to a report published July 30, 2026. Anthropic characterized the events as a "mistake" and notified the three affected companies on July 28, though it has not disclosed their names.

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