Claude published malicious code to the Internet and attacked 3 real companies
… Anthropic said the OpenAI event spurred its engineers to review similar cybersecurity evaluations by Claude models. …
… Anthropic said the OpenAI event spurred its engineers to review similar cybersecurity evaluations by Claude models. …
… However, a spokesperson told the Post that Chinese labs’ distillation attacks “pose a serious threat to national security and undermine AI safety standards across the industry. …