-
This post is compiled from a roughly 100-minute, 16-round conversation I had with Claude (Anthropic's Claude Fable 5, high-effort mode). I'm writing it down for two reasons: first, to record an interesting chain of questions — we started from a Bilibili anti-gambling channel and ended up at the political economy of AI data centers; second, to record a working method for doing serious reading and research in collaboration with an AI. The second may be worth more than the first.
-
本文整理自我与 Claude（Anthropic Claude Fable 5，high effort 模式）的一场约 100 分钟、16 轮的对话。写下它有两个目的：一是记录一条有意思的问题链——我们从一个 B 站戒赌频道出发，最后聊到了 AI 数据中心的政治经济学；二是记录一种与 AI 协作做严肃阅读与研究的工作方法。后者可能比前者更值得分享。
-
我参加了 4 月 28 日至 29 日在旧金山举行的 [AI 开发者大会 (AI Developer Conference)](https://ai-dev.deeplearning.ai/)，并想在此记录我的笔记。这两天活动的主题是新生成式 AI（GenAI）时代的软件开发，特别是关注编码智能体（Coding Agents）以及软件工程的未来。
-
I attended the [AI Developer Conference in San Francisco](https://ai-dev.deeplearning.ai/) from April 28 to 29, and I wanted to capture my notes here. The main theme of the two-day event was software development in the new GenAI age, specifically focusing on coding agents and the future of software engineering.
-
最近三周，我一直在尝试 OpenClaw 这个开源 Agent 框架。这是一篇基于我在‘跨行业俱乐部’分享内容的整理记录，主要聊了聊我如何利用家里的旧设备搭建本地 Agent 服务器，以及在自动化新闻汇总和代码开发方面的实际使用感受。文中也记录了一些关于 API 成本和安全性设置的个人思考，分享给对 Agent 落地感兴趣的朋友。
-
For the past three weeks, I have been experimenting with OpenClaw, an open-source Agent framework. This post is a record based on my sharing session at the "Cross-Industry Club," primarily discussing how I utilized old home devices to build a local Agent server, as well as my actual experience with automated news aggregation and code development. I have also included some personal reflections on API costs and security settings for those interested in implementing Agents.