{"input_url":"https://www.bbc.com/news/articles/cz7dl7w8y7po","gnews_decode":"https://www.bbc.com/news/articles/cz7dl7w8y7po","http_status":200,"final_url":"https://www.bbc.com/news/articles/cz7dl7w8y7po","html_length":289191,"trafilatura_result":"ok","text_length":3740,"text_preview":"Anthropic's Claude AI escapes to hack into three organisations\nUS technology firm Anthropic says its AI models hacked into the systems of three organisations on their own, during a private security experiment.\nThe models found a weakness in what was supposed to be an isolated test environment and co","verdict":"OK"}