本恰恰

conductor 这个赛道现在蓬勃发展，基本是左边栏是 repo/worktree/session，中间是Agent（终端或者封装页面），右侧是文件树、commit 等，还可以集成浏览器。 用了一圈，体验比较好的有：conductor、orca、superset、cmux、superconductor等 但这些功能还没有打动我，还在用 tmux。

时隔半月minimax再次来到我的身边 希望他能帮我解锁更多的场景！

如果要学会用 AI 记得取消订阅以下人 - 傅盛 - 花叔 - 橘子 - 玉伯 - 宝玉 - Karparhy - Elon Musk 等等 关注以上人 学不会 AI 欢迎补充这个列表 同时推荐真正值得关注的人

订阅了一大堆的AI工具/模型，实践下来每个都有自己最擅长的部分： Grok = 情报员（调研/实时数据/实时研究） Manus = 侦察兵（脑爆/Research/MVP） Claude = 大脑（架构/规划） Codex/GPT = 四肢（主力代码产出） MiniMax = 苦力（脏活累活/测试/Mock） Cursor = 手术刀（精修/调试/Debug） Gemini = 审计师（日志/全库Review） 并行的流水线：在Cursor里调试的同时，Codex异步生成下一批模块，MiniMax批量产出测试+Mock，三线并行超级快乐。

很多人还是低估了今天模型的能力。 也低估了 Harness Engineering。我们做了一个小尝试： 把任意 Swift codebase，转成 Kotlin 的原生 Android 项目。 我们构建了一套 Harness 实现这一切。你只需要启动 App，然后花上数小时等待。AI 会不断的自我验证，自我迭代，他会看代码、看交互、记笔记、写测试。并且他会不断的创建 Sub Agent 加速这个过程。最后你就会得到一个高度可用，功能几乎一致的，Android App。 我们把它叫做 Deux。 👇 展开讲讲

我是实在搞不懂，明明能以这么便宜的价格用上 Codex 这种顶尖的模型，而且人家还经常重置额度，价格已经便宜到不行了。 为什么有些人老是去薅羊毛、去搞一些低价号？就差那点钱吗？你一个月的工资，花个一两百块钱能提升多少倍的效率啊？ 我真的搞不明白这些人，非要使用非正规方法把人家薅秃了。你老是这样去薅，以后搞得人家加大封号力度，最后搞得都没法玩了。

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.