Nathan Lambert 称 Claude 在专业领域过度回避问题
This is very needed. Talking to models like Claude about anything that has an overlap with an area like legal, healthcare, etc is mind numbing. They’re so despe
Nathan Lambert 评论 Simon Taylor 关于 Meta Muse 回答风格的帖子，称这种风格“非常必要”。他表示，与 Claude 等模型讨论法律、医疗等领域的交叉问题时令人头疼，模型急于对冲风险、回避灰色地带，往往反而绕开了真正的问题。
查看原帖Meta 的 @Muse 回答问题的方式与 ChatGPT 或 Anthropic 截然不同。 它引用的来源更多，但使用的文字和表格却少得多，而且不会试图追问后续问题。 这种短篇幅内容是为处理任务而设计的，而非为了延续对话，坦白说，读起来远没有那么累人。这体现了一种设计得非常出色的 AI 体验，与基础大语言模型截然不同。 AirOps 团队做了一项很棒的研究 👇 gg @alexandr_wang
查看原文
Meta's @Muse answers questions very differently from ChatGPT or Anthropic. It cites more sources but uses far fewer words and tables, and doesn't try to ask a follow-up. This short-form content is designed for dealing with tasks rather than continuing a conversation, and frankly, it's far less exhausting to read. This speaks to a really well designed AI experience and its so different from the base LLMs. Great study by the AirOps team 👇 gg @alexandr_wang
正文
This is very needed. Talking to models like Claude about anything that has an overlap with an area like legal, healthcare, etc is mind numbing. They’re so desperate to hedge and steer away from grey area that they often are really avoiding the real question.