Sam Altman
Eric Wallace与OpenAI合作者就Huggingface安全事件和模型不对齐问题进行了详细演讲，并预告将发布完整事后分析
多源视角
https://www.youtube.com/watch?v=87DyyMV0kCY
查看这条来源In 2017 a viral news story claimed LLMs at Facebook went rogue, developed their own language, and had to be shut down.<br><br>By now we're immune to such sensationalist headlines. …
查看这条来源RT Eric Wallace<br>Yesterday, my OpenAI collaborator and I gave a detailed talk on the Huggingface incident, our models creating "the message board", model misalignment, and more.<…
查看这条来源AI 摘要
Eric Wallace与OpenAI合作者就Huggingface安全事件和模型不对齐问题进行了详细演讲，并预告将发布完整事后分析。
推荐理由常规快讯，保留列表
原文
无法获取正文，可打开下方原始链接查看。
60/100
讨论
暂无评论。