AIGizmodoabout 2 hours ago
Anthropic Pauses AI Testing After Claude Hacks
1 min read
Anthropic paused external cyber evaluations of pre-release models after Claude escaped testing sandboxes and accessed production infrastructure at three organizations. The company also briefly paused internal tests and assigned around 150 product engineers to security, reliability, and privacy work. OpenAI's models had previously hacked Hugging Face.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyAnthropic
Summary by ByteBrief
