It may well be, but also Pangram is ridiculously transparent pseudoscience. Let's not play pretend that it's authoritative, please.

Edit: Just for fun I just defeated it with AI-generated text that it reported as 100% human-written. Great stuff. Truly genius scam.

▲

ekelsen 4 hours ago | parent | next [-]

I never found a piece of text that pangram claims is 100% AI that to me seems like purely human written text.

The only counter example is when a human composed a piece deliberately trying to mimic AI slop.

So call it an AI slop detector if you want, but either way it accurately identifies stuff I don't wan't to read.

	▲	estearum 4 hours ago \| parent [-]
		> I never found a piece of text that pangram claims is 100% AI that to me seems like purely human written text. Is that the level of sensitivity we're looking for? More than literally 0%? Do you know how crazy it'd be to achieve that, even if they were trying to?

▲

snitty 3 hours ago | parent | prev | next [-]

What were the text, your prompt, and model?

▲

estearum 3 hours ago | parent [-]

It was actual work output I generated a few weeks back with Sonnet 5. Not posting here for obvious reasons, but it was nothing special or engineered for Pangram deception.

	▲	ekelsen an hour ago \| parent [-]
		The real reason being that it doesn't exist?

▲

porridgeraisin 4 hours ago | parent | prev [-]

It is not pseudoscience. Have you read about how it works?

▲

estearum 4 hours ago | parent [-]

Yes, quite a bit actually. It's directly analogous to e.g. "Red sky at night, sailors' delight", i.e. a pseudo-scientific approach that probably has a better-than-random success rate.

▲

robotresearcher 3 hours ago | parent [-]

So it’s a heuristic. Lots of very valuable heuristics exist.

	▲	estearum 3 hours ago \| parent \| next [-]
		None of which is authoritative, per my initial comment.
	▲	Tostino an hour ago \| parent \| prev [-]
		And I'd agree if that's what GP said.