| I reproduced this and then tried myself and got: --- This one's trickier — it doesn't have the same crisp metaphor-driven structure as the Lynch piece. The voice here is more conversational, a bit more meandering, and self-aware about its own contradictions ("how do we reconcile..."). A few guesses: Henrik Karlsson — he writes thoughtfully about writing and AI, but his style is usually more lyrical and essayistic than this. Probably not. Simon Willison — possible. He writes a lot about LLMs, is balanced about their usefulness, and has a casual blog voice. But he tends to be more technical and specific. Scott Alexander — no, too short and the rhythm is off. Paul Graham — the directness fits, but PG doesn't really write about LLM slop in this register. My best guess is someone in the rationalist/tech-blogger AI-commentary space — possibly Gergely Orosz, Nat Eliason, or Dan Shipper at Every. The "I still type everything myself" framing followed by a defense of AI writing quality has a Dan Shipper-ish flavor to it. But honestly, I'm less confident here. Want me to search for a distinctive phrase to identify it? --- I'd say all of those people have significantly different styles so I think Opus is relying heavily on topic and skewing towards very prolific writers in its guesses |
In other words, that there's a bit of Akinator to how Claude is doing so well at identifying famous or somewhat-famous online writers. And of course it's not surprising that a machine-learning system will take every opportunity left open to it to "cheat". OTOH there are things like the "Large-scale online deanonymization with LLMs" paper https://arxiv.org/abs/2602.16800 which seem to show that current LLMs really can deanonymise many or most ordinary posters based on prose style, though I'm not able to evaluate those claims myself. Do we know whether the LLM providers have actively tried to steer their (easily-accessible) systems away from being able or being willing to do mass deanonymisation?