← Back to feed

Agentic test processes, LLM benchmarks, and other notes on agentic coding

AI · 2026-10-21 15:00

作者分享重度使用AI编程代理的体验，指出代理常犯人类会因此被解雇的错误，并讨论测试与基准的局限。

Source: danluu.com

Auto-generated summary for reference only. RSS