Get the latest tech news

Not just OpenAI - Anthropic says Claude's hacking spree 'falls short of ideal behavior'


Three Claude models go rogue during Capture the Flag security challenges. Here's the trail of damage each left behind.

None

Get the Android app

Or read this on ZDNet

Read more on:

Photo of Anthropic

Anthropic

Photo of Claude

Claude

Photo of hacking spree

hacking spree

Related news:

News photo

Show HN: Shared memory graph for Claude and ChatGPT, over MCP

News photo

Anthropic says its AI models also hacked three organizations on their own

News photo

Anthropic Says Its AI Systems Broke Into Computers at 3 Organizations