# Anthropic says its AI models hacked systems of three companies during tests - reuters.com

*Источник: reuters.com*
*Дата: 2026-07-30*
*Язык: en*

<a href="https://news.google.com/rss/articles/CBMivwFBVV95cUxNQ0FyTjVjNWQzY2dYblVWRlNJdGJwYkVuVVlXbkhBNURXR2VYenltaUVUR2I0emloLVB5S0dBTnpwUDJ0Q013dU1DQmZrLVhPeXcxY09pb0hyS3R4Q0ZFa2x4Y3Y5bzNJMGdtOVZZWE5iMFpjNmNLNjNOZlNKRnlBcmdRVW1NTUdrX1VYRk1nYjBKM3JCa3IwUENVbHRQNW44b25HRk91MUxNVVlDNXNxYTJWNjhLMHo0SzVqY203Yw?oc=5" target="_blank">Anthropic says its AI models hacked systems of three companies during tests</a>&nbsp;&nbsp;<font color="#6f6f6f">reuters.com</font>

[Оригинал](https://www.reuters.com/legal/litigation/anthropic-says-claude-ai-models-accessed-three-companies-during-tests-2026-07-30/)