{"input_url":"https://www.theguardian.com/technology/2026/jul/30/anthropic-ai-claude-hack","gnews_decode":"https://www.theguardian.com/technology/2026/jul/30/anthropic-ai-claude-hack","http_status":200,"final_url":"https://www.theguardian.com/technology/2026/jul/30/anthropic-ai-claude-hack","html_length":310898,"trafilatura_result":"ok","text_length":2063,"text_preview":"Anthropic said on Thursday its AI Claude model hacked systems of three organizations during testing, days after rival OpenAI revealed a rogue agent had gone on a days-long hacking spree at the AI firm Hugging Face.\nClaude gained unauthorized access to the systems during cybersecurity evaluations aft","verdict":"OK"}