{"input_url":"https://www.dw.com/en/anthropic-says-claude-ai-hacked-three-companies-during-tests/a-78184070","gnews_decode":"https://www.dw.com/en/anthropic-says-claude-ai-hacked-three-companies-during-tests/a-78184070","http_status":200,"final_url":"https://www.dw.com/en/anthropic-says-claude-ai-hacked-three-companies-during-tests/a-78184070","html_length":150904,"trafilatura_result":"ok","text_length":2724,"text_preview":"Anthropic said on Thursday that its artificial intelligence (AI) models \"gained unauthorized access\" to three outside organizations during testing that was supposed to be isolated from \"real-world\" systems.\nThe company reviewed 141,006 test sessions to find that three different versions of Claude, i","verdict":"OK"}