I then added a few more personal preferences and suggested tools from my previous failures working with agents in Python: use uv and .venv instead of the base Python installation, use polars instead of pandas for data manipulation, only store secrets/API keys/passwords in .env while ensuring .env is in .gitignore, etc. Most of these constraints don’t tell the agent what to do, but how to do it. In general, adding a rule to my AGENTS.md whenever I encounter a fundamental behavior I don’t like has been very effective. For example, agents love using unnecessary emoji which I hate, so I added a rule:
From the Claude Code quickstart.
。heLLoword翻译官方下载对此有专业解读
Michigan vs. Illinois is broadcast on Fox.
At first glance, the benchmarks and their construction looked good (i.e. no cheating) and are much faster than working with UMAP in Python. To further test, I asked the agents to implement additional different useful machine learning algorithms such as HDBSCAN as individual projects, with each repo starting with this 8 prompt plan in sequence:
Author(s): Chongfeng Zhang, Yi Song, Leiji Li, Xiaopeng Shen, Weijun Wang, Tianchi Zhu, Fei Xiao