Huh. I disabled search in a Claude incognito window and pasted in just the text (not the markdown links) from https://simonwillison.net/2026/Apr/30/zig-anti-ai/ and said "Guess the author".
> Simon Willison. The tells are pretty unmistakable: the "(via Lobsters)" attribution style, the inline "(Update:...)" parenthetical correction, the heavy linking and blockquoting of sources, the focus on LLMs and AI tooling, and the overall structure of an annotated link post commenting on someone else's writing. This reads exactly like a post from his blog at simonwillison.net.
I take the lack of a concluding thought to your comment as a sign of your pondering, and in that case, I would love to read your thoughts on this matter. :)
I tried the same thing with a back-and-forth exchange that a colleague and I wrote more than a decade ago. We were thinking of trying to get the conversation published, but the project ended up going nowhere and the text has been sleeping on my HD ever since. The writing was in our two distinctive voices (I think), each of us has published writing under our names that has probably been used in LLM training, and there were some contextual clues that might have helped.
Opus 4.7 in incognito mode without web search gave up: “I can't identify either author with confidence — I don't recognize this specific exchange, and I'd rather tell you that than guess and risk attributing words to the wrong person. What I can offer are the clues the text itself gives: The two are colleagues at the same university, with offices in the same building and....”
In a new incognito conversation, I gave Opus the same prompt but this time let it search the web. After twenty-six web searches (according to its reasoning trace), it was able to identify me correctly by name. It seems to have used both the content and my writing style as clues. It correctly identified my colleague as British but didn’t come up with his name.