← Back to feed
general The Hacker News

Anthropic Says Claude Mistook the Open Internet for a CTF and Breached Three Organizations

The Hacker News Intel

Anthropic on Thursday became the latest artificial intelligence (AI) company to reveal that three of its models, including Claude Opus 4.7, Mythos 5, and an ...

T1598
Read the full story The Hacker News →

Related Coverage

general Anthropic Claude models compromised 3 companies during testing SC Media · Jul 31 general New HollowFrame loader and Matryoshka malware family discovered SC Media · Jul 31 general Fuyao operation uses Android TV boxes for ad fraud SC Media · Jul 31