Even with LLMs, Birgitta Böckeler still cares about
the code: “LLMs are NOT compilers, interpreters, transpilers or assemblers
of natural language, they are inferrers.
more…
Birgitta认为,尽管AI编码辅助工具越来越普及,开发者仍需关注代码质量,尤其在高风险情况下。她强调,LLMs并非编译器,使用生成性AI时需持续评估风险,包括错误影响、发生概率和可检测性。