Hacker News Reader

I think the point was that Claude’s output can be somewhat easily and compellingly measured using this technique and its kind of massive (and human attributed).

It shows that about 40% of supposedly human-authored PRs are actually authored by Claude, and that these PRs clearly stand out from the others even without prior knowledge of Claude’s writing style.

Probably not what the author intended, but to me, this represents a great argument against the somewhat frequent claim that "AI writing patterns reflect human writing patterns". Rather, AI writing is distinctly not human, and is drifting further from human writing with every new model release.

LLMs were not taught to say the phrase "load-bearing seam" from humans saying it, because humans have never said it. It's almost definitely an artifact of post-training and nothing more.