-
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.
-
过去一周，我部署并测试了开源 AI 个人助手框架 OpenClaw。我没有租用云端服务器，而是想看看在本地运行一个持久、自主的 AI 实体究竟需要什么条件。 这个过程证明，虽然本地智能体的部署还有很多不完善之处，但其核心架构是切实可行的。简单来说，就是让大语言模型（LLM）进入一个持久循环：执行外部工具，并不断修改自己的配置状态。以下是我的硬件配置、调试过程，以及把这个智能体“放养”到纯机器人社交网络后的观察。
-
Over the past week, I deployed and tested OpenClaw, an open-source AI personal assistant framework. Rather than renting cloud infrastructure, I wanted to see what it takes to run a persistent, autonomous entity locally. The process proved that while we are still navigating the rough edges of local agent deployments, the underlying architecture—a persistent loop where an LLM executes external tool calls and modifies its own configuration state—is functional. Here is a technical breakdown of my infrastructure setup, the debugging process, and what happened when I let the agent loose in a bot-only social network.
-
This "report" is a complete record of my personal development journey for a Side Project: Melon Moment (Chinese name: 小瓜书). Amidst the current wave of generative AI, I have deeply experimented with how a software engineer can utilize AI tools to develop a full-stack application. The core of my project is an application for recording child growth, aiming to address the various shortcomings of existing commercial software in terms of organizing massive amounts of photos, the high cost of printing physical albums, and the integration of AI features.
-
I have a simple, annoying problem. I make a lot of blunders in my chess games. I also love using Chessable to drill puzzles. But there was no easy way to take *my* specific blunders and turn them into puzzles I could practice. So, I decided to build a tool to do it. My goal: a script that could pull my Lichess games, extract the blunder-turned-puzzle, and format it for Chessable. I decided to try this using the "[AI Coding Accelerator](https://maven.com/nila/ai-coding-accelerator)" methodology (Explore, Plan, Execute) and a few AI agents I'd been wanting to test. The process involved several missteps, a $50 credit, and ultimately, a functional tool.
-