Hacker News Reader

Comment by sosull | Hacker News Reader

I really love this. It’s comprehensive, it consolidates the data to the point where the argument effectively ‘makes itself’, and the way it’s presented respects the reader’s time. It also makes for an interesting challenge (for me at least) to try to characterise the subject matter of a language problem so narrowly.

No ream of slides. No narrative. Just a lovely big painful conclusion.

View on HN

Thank you so much! The presentation was really my goal here, more than the model itself.

> the argument effectively ‘makes itself’

What argument? I don't know what to take away other than "Claude likes certain words". Some of them are kind of amusing, but I'm not convinced the vocabulary is bad or that this is a problem, just from looking at this.

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).

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.

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.

Reply on news.ycombinator.com