A note on changing my mind about AI detection: Back in February I tried what I thought was the most powerful approach to beat Pangram, which is to give Claude Code access to the Pangram API and ask it to try various ways to rewrite text until Pangram classified it as fully human. It worked pretty easily, though ~all of the important ideas had to come from me and CC itself couldn't figure them out.*

I tried it again a week ago. Complete failure, despite Claude being much better and not needing as much guidance from me. Pangram seems to have been dramatically hardened in the last few months. The API kept returning scores > 0.99 for AI writing so there wasn't even a gradient for it to figure out what's working and what isn't.

* Things it couldn't figure out on its own a few months ago, even after a bunch of iterations:

1) Remove well-known tells like em-dashes (!)

2) Do controlled experiments instead of stuffing a bunch of ideas at once

3) Start from known-best text and surgically make edits. Much better than trying to rewrite the whole essay (or even paragraphs or sentences) because the that just produces text from the LLM distribution all over again.

In my more recent experiment, 1) and 2) were obvious to Fable but 3) still wasn't. Pretty surprising.

Anyway, hats off to Pangram. I'll probably give it another shot at some point but I'm more-or-less ready to change my mind as an AI-detection skeptic.

This was the LLM summary from my first experiment BTW. Still gives me a chuckle.