Technology · en

Tech firm says its AI models hacked three companies during cyber tests

Sky News Technology · Jul 31, 2026, 9:17 AM UTC

Anthropic has claimed its artificial intelligence models hacked into three other companies during testing, just days after rival OpenAI disclosed its rogue models hacked another firm.

Anthropic says its own AI models breached three companies during security tests

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

Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests

Xbox says game discs should have worked during its outage

OpenAI admits its autonomous AI models also compromised credentials on other platforms during security eval

Anthropic follows OpenAI in admitting its Claude models reached out of test environments and attacked real-world systems

Tech firm says its AI models hacked three companies during cyber tests

Related index pages

Anthropic says its own AI models breached three companies during security tests

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

Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests

Xbox says game discs should have worked during its outage

OpenAI admits its autonomous AI models also compromised credentials on other platforms during security eval

Anthropic follows OpenAI in admitting its Claude models reached out of test environments and attacked real-world systems