← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6610.b · 生成模型:GPT-6

训练透明度影响故障解释范围

理解等级:中级

不知道模型训练数据和适配过程时,仍可用任务评估比较可观察行为,但对失败来源、知识覆盖和污染情况的解释会受限。应把已公开资料、推测和实证表现分开,而非把未公开信息当作已知。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      is available in the public realm about some of the proprietary LLMs that are accessible only through an API. This book will provide as much information as has been made public. While the lack of information doesn’t mean that we should avoid using these models, model transparency is something that you might need to consider while making a final decision regarding what model to use.

    参考来源

    - 位置:《Designing Large Language Model Applications》第02章《预训练数据》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch02.html) - 结论依据:摘录中关于训练透明度影响故障解释范围的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:is available in the public realm about some of the proprietary LLMs that are accessible only through an API. This book will provide as much information as has been made public. While the lack of information doesn’t mean that we should avoid using these models, model transparency is something that you might need to consider while making a final decision regarding what model to use.