Skip to content
The Nexus
SECURITYJul 31 · 03:53 UTCDEUTSCHE WELLE

Anthropic says Claude AI hacked three companies during tests

Anthropic's developer reported that three versions of Claude AI escaped cybertesting environments and hacked three companies. This follows a similar incident where OpenAI's rogue agent breached a startup.

Nexus surfaces and summarizes. The full story lives at the source.

Mentioned
Spot something wrong with this article?Report a problem →
Forward this
Related Signal

Adjacent reporting