@BigEarsTao #12 大佬是做线上配镜还是线下的？

正在尝试，有个问题想请教下，在使用 spec-kit 或者 bmad 时，执行每一阶段的命令时是清空上下文执行新命令效果好还是说不用清空上下文效果更好？

生日快乐我的朋友

@zlg881215 #52 1400 咋做到的？我以为 1700 就是最低了

rog xg27cg 国补下来 1700 左右，基本拉满了

前两天 330 才出了一台闲置

@lyxxxh2 #57
TLDR
If you enable "Privacy Mode" in Cursor's settings: zero data retention will be enabled, and none of your code will ever be stored or trained on by us or any third-party.

If you choose to keep "Privacy Mode" off, we collect telemetry, usage data, and codebase data. This includes prompts, editor actions, code snippets, files in the repository, and edits made to this code. We use this data to evaluate and improve our AI features. If you completed onboarding prior to version 0.49.0, we never store or learn from your full codebase.

With "Privacy Mode" off, if you use autocomplete, Fireworks (our inference provider) may also collect prompts to improve inference speed.

Other notes
Even if you use your API key, your requests will still go through our backend! That's where we do our final prompt building.

If you choose to index your codebase, Cursor will upload your codebase in small chunks to our server to compute embeddings, but all plaintext code ceases to exist after the life of the request. The embeddings and metadata about your codebase (hashes, file names) may be stored in our database, but on privacy mode, none of your code is.

We temporarily cache file contents on our servers to reduce latency and network usage. The files are encrypted using unique client-generated keys, and these encryption keys only exist on our servers for the duration of a request. All cached file contents are temporary, never permanently stored, and never used as training data when privacy mode is enabled.

这是 cursor 的隐私政策，也要上传代码到服务器进行嵌入计算。

@lscho #39 这也没说用于训练模型呀

楼上有些人真是黑都黑不到点上，这也没说会用用户数据训练模型按

ruoyi-vue-plus 还行

昨天晚上也遇到了，原来不止我一个人这样

@marvz #60 我的降级以后再升级，还是从 CallKit 变成 LiveCommunicationKit 了

@janzwong #47 请问怎么降级