精选理由
Meta偷偷拿对手的聊天机器人做未成年人危机测试，一口气发了4.5万条提示，看看它们怎么应对。
Meta雇佣数百名承包商伪装成未成年人，向OpenAI的ChatGPT、Google的Gemini和Character.AI发送自杀、性、毒品相关提示。单轮测试中发送了超过45,000条提示。被测试公司对此毫不知情。该测试旨在评估聊天机器人对未成年人危机场景的回应。
原文 · Decoder
Meta secretly tested ChatGPT, Gemini, and Character.AI with thousands of minor-perspective crisis prompts
Meta reportedly had hundreds of contractors pose as minors and send suicide, sex, and drug-related prompts to chatbots from OpenAI, Google, and Character.AI. In a single testing round, more than 45,000 prompts were sent. The companies being tested had no idea. The article Meta secretly tested ChatGPT, Gemini, and Character.AI with thousands of minor-perspective crisis prompts appeared first on The Decoder .