正在加载视频...
视频加载失败
New work with Edward Grefenstette at Google DeepMind: 🚨Interaction Dynamics as a Reward Signal for LLMs🚨 When it comes to interactions, the "how" is just as important as the "what" There is a signal in how we interact with a model that text analysis misses: hesitation, drift, friction
36,647 次观看 • 7 个月前 •via X (Twitter)
0 条评论
暂无评论
原始帖子的评论将显示在这里

