斯坦福 2025 年秋季，开了一门 CS146S「现代软件开发者」，讲怎么跟编码 Agent 一起写软件，8 周作业全部公开在 GitHub 上。
This is a AI post classified by Jev as AI coding agents (a free resource), kept by the AI Radar because it carries real work, not commentary.
斯坦福 2025 年秋季，开了一门 CS146S「现代软件开发者」，讲怎么跟编码 Agent 一起写软件，8 周作业全部公开在 GitHub 上。 每周一个主题，从提示词技巧开始，接着给现成的小应用加功能，自己写一个 MCP 服务把外部接口接给模型。 再往后用 Claude Code 搭至少两个自动化流程、用 Semgrep 扫出并修掉至少 3 个安全漏洞，最后一周把同一个应用用 3 套技术栈各做一遍。 GitHub：http://github.com/mihail911/modern-software-dev-assignments 第七周的作业我挺喜欢，每个任务只给 AI 一次提示就让它写完，自己逐行审一遍，再拿自己的审查意见跟 AI 审查的结果对比。 不少作业带现成的起步项目和测试，第一周还用 Ollama 在本地跑模型。没机会上这类课的，照着 8 周作业自己过一遍，能补上不少。
Posted by GitHubDaily (85.2k followers) 1 h ago · 9 likes · 1.3k views · view the original post on X. Kept by the AI Radar as AI coding agents.
More AI work like this
- Medium might be the best setting for the new Claude Opus 5.5 for agentic coding. — @JeremyNguyenPhD
- v1.7.0 is out. Claude banked resets now show up next to ChatGPT's, with expiry dates for… — @btsouth
- 看到 Jev 模型一个挺实用的用法，给 zsh 做历史命令补全，像 fish 那样在光标后面显示灰色建议。 — @GitHub_Daily
- this is how i orchestrate coding agents now — @jacsebl
- Mimo 2.6 Pro 0-shot result with basic prompt: "Implement code to be able to navigate in… — @ivanfioravanti
- WTF, I can't imagine this.🤯 — @0x0SojalSec
- 🤿 https://claude.ai/artifact/ReCBQGZ4EirKSiEmT8XXfs — @threejs
- Some of you might have noticed already but, we have a new magic word: **jevify**! I've… — @_can1357
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 43.8k posts from 5k X accounts over the last 14 days, 1.8k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 05:09 UTC. Full method.