So many (disclosed) claude-isms. The subject is interesting, the LLM-"hydrated" text is not.

It feels like work to skim through all the unnecessary em-dashes and actually read the article.

Granted, the article is not long, but I just don't have it in me. I already parse Claude output for my day job and I don't enjoy doing it for my leisure time.

> How this was written: drafted with an AI assistant from my own notes, then edited by me.

Doesn't feel that way with "The tradeoffs I am not going to hide" and "How it resolves, honestly"

This site needs Bryan Garner

This is not true. As author points out his domain is invalid unless you install something. So the whole thing is misleading.

The duality of a HTML-only website that's full of AI slop is hilarious.

Text is ai slop, cleverly disguised by using an unstyled website