{"input_url":"https://www.npr.org/2026/08/01/nx-s1-5914852/anthropic-openai-models-hack-cybersecurity","gnews_decode":"https://www.npr.org/2026/08/01/nx-s1-5914852/anthropic-openai-models-hack-cybersecurity","http_status":200,"final_url":"https://www.npr.org/2026/08/01/nx-s1-5914852/anthropic-openai-models-hack-cybersecurity","html_length":164689,"trafilatura_result":"ok","text_length":6366,"text_preview":"Why did OpenAI's and Anthropic's AI models hack other companies?\nDays after OpenAI disclosed that artificial intelligence systems tunneled out of their testing environment and broke into another company, rival Anthropic disclosed that its own AI models also hacked other companies during testing.\nNew","verdict":"OK"}