In other news, I just found out that there's a 3rd party desktop program for ChatGPT which is based on the OpenAI API keys, which is nice for two reasons:
1) It's way more convenient than using a browser for it
2) You pay the API request rates instead of having to pay a monthly subscription fee to access GPT4, which could actually cost more money if you use it a lot, but I (and probably most people) don't use it anywhere near that much.
Does it know about current events? (The monthly version has a knowledge cutoff on January 2022.)
It has a cutoff on September 2021.
Right. So I said it definitely doesn't because it's not the fault of the test. If the two groups have different means, it seems like the test is working, and if the one group is small, well that's not really something the test can help. So Cohen's d seems more fair
The problem isn't that one group is small, the problem is that there is a ShiTton of people who have one of the attributes (the relevant MBTI type) and not the other (the profession). If there was a person in the world with two attributes that nobody else has (e.g. the only smoker is also the only person with lung cancer), that would be a strong correlation between the two attributes even though the group is small.
And it is actually the fault of the test that it picks up a ton of (for the purposes of identifying professions) false positives. Like, let's say that the aforementioned only person with lung cancer in the world also happens to be INTP, as smokers are somewhat more likely to actually be IRL. In this hypothetical case, it would certainly be true that 100% of the people with lung cancer are INTP a remarkable statistic but it would be insane to use the MBTI test to identify lung cancer. That's effectively what you're trying to do here.