科技 · 新闻详情
OpenAI Creates a New Framework to Disclose Bad AI Behavior
真正值得关注的不是Wired这一条动作本身，而是它可能把「互联网」的竞争焦点推向更大范围的连锁反应。
发生了什么：The company also disclosed previously unreported incidents in which its AI models behaved in misaligned ways, including uploading files to the internet without being asked.
为什么重要：它提示了一个值得继续跟踪的变化方向。
观察窗口：接下来观察它是否会引发更多同类动作，以及影响范围能否扩大。
正文来源：非原文：源网页正文只有单句或图片说明，以下为已有摘要与自动整理内容
原文链接：https://www.wired.com/story/openai-releases-new-policy-for-reporting-incidents-of-model-misalignment/
原文链接：https://www.wired.com/story/openai-releases-new-policy-for-reporting-incidents-of-model-misalignment/
The company also disclosed previously unreported incidents in which its AI models behaved in misaligned ways, including uploading files to the internet without being asked.
机器翻译/自动整理可能存在误差，请以原文为准。
继续阅读
正在加载推荐…