{"input_url":"https://edition.cnn.com/2026/07/30/tech/anthropic-ai-models-break-out-hack","gnews_decode":"https://edition.cnn.com/2026/07/30/tech/anthropic-ai-models-break-out-hack","http_status":200,"final_url":"https://edition.cnn.com/2026/07/30/tech/anthropic-ai-models-break-out-hack","html_length":5443278,"trafilatura_result":"ok","text_length":3026,"text_preview":"AI company Anthropic says that during routine testing some of its models accessed the internet and hacked into three separate organizations’ systems – and that it didn’t notice the models had done so until an internal review prompted by rival OpenAI disclosing its models did the same.\nAnthropic said","verdict":"OK"}