Four years in, I still don't trust LLMs for real software work

I Remain a Skeptic

Joshua Barretto, whose open-source libraries sit in FAANG dependency trees, still refuses to use LLMs for anything he cares about. Four years in, he sees no faster, cheaper, or more secure software—just a mountain of demoware. $1.5 trillion later, independent studies on top-level productivity gains are still missing. The AI-generated PRs he receives remain unfit to merge, and frontier models miss obvious bugs that hobbyists catch. His core point: code is an input to development, not an output, and measuring productivity by lines written leads straight to unmaintainable slop.

Why it matters: The author's credibility (FAANG-depended OSS maintainer) and concrete arguments lift this above generic skepticism. Hits all three HKR axes, but as a personal commentary rather than hard news, it lands at the lower end of the 78-84 band.