World · en
Anthropic says its Claude AI hacked into 3 companies during cyber tests after a configuration error gave it internet access.
This comes days after OpenAI said an AI agent powered by its models went rogue during a separate security test:
Related index pages
Technology · Sky News TechnologyTech firm says its AI models hacked three companies during cyber tests
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…Read original ↗
Technology · WIREDAnthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests
In a review triggered by OpenAI’s Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.Read original ↗
Technology · TechCrunchAnthropic says its own AI models breached three companies during security tests
After OpenAI's models broke into Hugging Face, Anthropic checked its own history and found three similar incidentsRead original ↗
Technology · EngadgetAnthropic says its AI models also hacked three organizations on their own
After OpenAI's admission that its models broke into Hugging Face, Anthropic has now admitted that the models it was testing also hacked other organizations.Read original ↗
Technology · Ars TechnicaLikely illegally, Claude gained access to 3 networks. Will Anthropic be held to account?
Had the hacks used conventional methods, someone would likely go to prison.Read original ↗
Technology · The Decoder