[kelseyfrog]

People over-update when they see an em-dash. If you compute the posterior probability, you'll realize that seeing an em-dash hardly shifts the probability that text is AI generated.

[anon84873628]

You might even realize that the AI is using the em-dash precisely because of how often it was used in the training text.

[kelseyfrog]

That's a fair point. I'll admit that LLM em-dash usage likely matches its prevalence in the corpus. However, online message boards and chat is a subset of that corpus that may have a significantly different distribution of em-dash prevalence.

This is necessary nuance that I'll have take into consideration. Thank you.

[anon84873628]

Eh, I wasn't trying to put you on blast or anything. Obviously there is a lot of nuance to how/why the LLM uses them. I just think the whole "em dash == AI" thing is stupid and way overblown. I wish the people who say that would realize it obviously learned them from somewhere.

[kelseyfrog]

You're good, friend. I didn't feel blasted at all. It was a good point

[pimlottc]

“Over-update”? Do you mean “overreact”?

[jdiff]

I'm guessing over-update their opinion/view, but that's the first I've run into that turn of phrase.

[kelseyfrog]

No, I mean over-update in a Bayesian capacity. As in, they are updating their prior probability using evidence to arrive at the posterior probability.

[ggm]

"I don't often jargon, but when I do jargon I jargon like Chuck Norris"

[firesteelrain]

Huh?

[cthor]

See em dash in text

Think text much more likely from robot than first thought

Grug say this change too big from just one em dash