I feel like it's happened to me multiple times that I've seen an ad for something I actually want, but if I click through or look up the company advertised, then do a little research on that company, I discover that it's a scam or a super crappy version, then I actually purchase the thing from a more reputable company with higher quality. So I guess they succeeded in getting me to buy something, from their competitors.

Why does this friend in particular deserve an exemption or reduced rate? Why don't they do something like take the trains into the nearest NJ suburb and leave their car at the parking lots there, which will probably be free or much cheaper, since they're doing the opposite of most commuters. Then they'd avoid this and all of the other tolls, most of which are much more expensive, and would probably be faster too.

Even that isn't enough. Much of the bias nowadays comes in which specific facts and events you report, and which you ignore.

Now that I have a little more time to search around, I easily found this study, published March 31st this year, so not quite 3 months ago:

https://arxiv.org/abs/2503.23674

I only skimmed it, but I don't see anything clearly wrong about it. According to their results, GPT-4.5 with what they term a "persona" prompt does in fact pass a standard that seems to me at least a little harder than what you said - actively picks the AI as the human, which seems stricter to me than being "unable to distinguish".

It is a little surprising to me that only that one LLM actually "passed" their test, versus several others performing somewhat worse. Though it's also not clear exactly how long ago the actual tests were done - this stuff moves super fast.

I'll admit that I was not familiar with the strong version of it. But I am still surprised that nobody has done that. Has nobody even seriously attempted to see how LLMS do at that? Now I might just have to check for myself.

I would have presumed it would be a cake walk. Depending of course on exactly how we define "average interrogator". I would think if we gave a LLM enough pre-prepping to pretend it was a human, and the interrogator was not particularly familiar with ways of "jailbreaking" LLMs, they could pass the test.