The Decoder:"But marinade" and leaked passwords are what researchers found in ChatGPT's hidden reasoning
原文摘要:Security researchers found a vulnerability in the APIs of OpenAI, Anthropic, and Google that lets them extract encrypted reasoning traces and move them between models. A s 来源:The Decoder。建议继续查看原文,重点核对它影响的工具入口、成本、风险和真实使用场景。