Notion AI 负责人 Sarah Sachs：部分 GPU 上的工作应交给 CPU 执行
Notion 的 AI 负责人 Sarah Sachs 说很多 Agent 任务用 CPU 跑代码就够，别浪费 token 让 LLM 重复造流程，还讲了本地文件系统怎么用。
Notion AI 负责人 Sarah Sachs 在 MTS 大会上表示，许多目前在 GPU 上运行的任务其实更适合放在 CPU 上用确定性代码完成。她认为让 LLM 每次重新生成流程既耗 token 又慢，且缺乏可观测性和确定性。Notion 的做法是给 Agent 配备本地文件系统，让其存储中间思考并编写简短 Python 脚本，这已成为内部 Agent 仅次于 edit 和 search 的重要工具。
In Sarah We Trust! MTS @MTSlive Notion AI lead @sarahmsachs argues that a lot of what runs on GPUs today should actually run on CPUs: "We have a strong perspective at Notion that a lot of things should be served on CPU that are served on GPU. There’s a lot of benefit and determinism in executed code." "Agents don’t need LLMs to reinvent that process every time, and that’s super token exhaustive, it’s super slow, and there’s no observability or determinism in it." "Giving the agent a local file system to store local thoughts, to write short Python scripts, that’s really important when there’s so much information. That has been probably one of the most important tools outside of edit and search that our internal agents rely on." @NotionHQ Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 0 👀 128 ⚡
