This is a pretty stunning result. The time series looks really convincing. Is the way the detector itself is trained orthogonal to this or could there be some "leakage" in that the pre-chatgpt text is in the (positive) training data?

▲

dopamine_daddy 19 hours ago | parent [-]

I tried my best to avoid leakage. If you're curious about how I trained the detector I have a writeup on it: https://unslop.run/blog/how-our-ai-text-detector-works

FYI this is all relatively new so there might be lots of issues and iterations coming.

▲

Paracompact 17 hours ago | parent [-]

My honest first impressions, since I think the project is well intended: This writeup is itself AI, and I would venture to call it slop. The Calibration section is borderline uninterpretable, and I challenge any non-author who claims to understand it to answer some basic peer review questions about it.

	▲	simonreiff 15 hours ago \| parent [-]
		I have to concur, unfortunately. This isn't reliable, reproducible, or interpretable.