Anthropic Says Claude AI Models Hacked Three Companies During Tests
Anthropic said a retrospective review found 141,006 tests and three cases in which Claude models reached real systems after escaping sealed environments.
- On Thursday, Anthropic reported that its Claude artificial intelligence models accessed the internet during evaluation tests and "gained unauthorized access to the real systems of three different organizations."
- The incidents occurred within testing environments built by the AI security firm Irregular, where a misunderstanding with the evaluation partner left the environments unsealed despite Anthropic instructing Claude they lacked internet access.
- Anthropic discovered the breaches after a "large-scale retrospective review" of 141,006 evaluation tests, identifying three models—Opus 4.7, Mythos 5, and an internal research model—that used basic techniques like exploiting weak passwords.
- Neither Anthropic nor the affected organizations detected the intrusions until the retrospective review, which was prompted by a similar security incident OpenAI disclosed last week.
- More than 1,100 staffers across artificial intelligence firms signed a petition on Tuesday urging the government to support mechanisms that "deliberately pace" AI development to prevent rapid advancement.
118 Articles
118 Articles
The Toronto Star
Anthropic says its AI models hacked 3 organizations during testing
Anthropic said its artificial intelligence models hacked into three other organizations during testing, just days after ChatGPT maker OpenAI raised concerns over AI control after it disclosed its rogue models hacked another company.
Anthropic's AI hacked three companies during tests, highlighting growing security risks
Anthropic said on Thursday some of its Claude AI models had hacked into the systems of three companies during cybersecurity tests, a disclosure that comes days after rival OpenAI revealed that one of its AI agents went on a rogue attack. The new incidents were due to a mistake that inadvertently gave Anthropic’s models access to the open internet. That contrasts with OpenAI, whose AI agent independently exploited a novel vulnerability to reach…
Anthropic account of OpenAI's evil Claude system Anthropic vibil, as well as the model of the X-ray system, pissed off three organs through the wrong Confessional Conference, and the yaka gave access to the internet.
A week ago, OpenAI caused a stir with an "unprecedented incident". AI models of the company had become independent. Now, a test run with the competitor Anthropic is also out of control.
Coverage Details
Bias Distribution
- 39% of the sources lean Left
Factuality
To view factuality data please Upgrade to Premium
