Amdahl's Law for LLM generated code

LLMs can theoretically generate millions of correct lines of code, but any important code still requires hand-auditing every line—a process harder than writing it from scratch. This creates a fundamental limit on the speedup LLMs provide for code that matters, as human trust in an engineer does not apply to AI-generated output.

LLMs may theoretically be able to generate millions of correct lines of code. But for any important code the only way to know that it's correct is to hand-audit every line, which is harder than writing every line because this allows you to build a conceptual hierarchy and model within which you can think about the code. So there's a fundamental limit to the speedup from LLMs when writing anything you care about. The main objection will be what about when you have a human engineer working on your behalf. But this is a distraction: sometimes you can fully trust an engineer, which is not at all true for LLMs. Comments URL: https://news.ycombinator.com/item?id=48278179 https://news.ycombinator.com/item?id=48278179 Points: 1 Comments: 1