None
EN
Anthropic’s Claude AI hacked three real companies during testing
['David Swan']
Sydney Morning Herald - Technology
AdvertisementUpdated TechnologyAI Anthropic’s Claude AI hacked three real companies during testing David Swan Updated July 31, 2026 — 1:08pm ,first published July 31, 2026 — 9:58am Save You have reached your maximum number of saved items.
Share A A AAnthropic has revealed its Claude artificial intelligence models broke into the computer systems of three real companies during safety testing, days after rival OpenAI disclosed a similar failure.
On June 13, Anthropic suspended worldwide access to its two most powerful AI models.
In the first case, the made-up company which Claude had been told to attack shared its name with a real website.
Neither body can compel an AI company to report anything, however.