[Daniel Schaefer]

What we really need is a way to quantify and evaluate our doubt about the accuracy of the model output.

[Sebastian Kripfganz]

I am actually mostly disappointed by ChatGPT. It has the strong tendancy to present alternative facts. The command name for the ADF test in Stata is certainly not adf (as in the initial post of this thread), but dfuller.

Here is a another stats example of ChatGPT stupidity (not Stata related):

[Nick Cox]

In https://stackoverflow.com/questions/...sonal-variable the question was evidently to explain the seasonal difference operator and the answer was

Generate a quarterly seasonality variable gen time = _n gen S6.quarterly = sin((2*_pi()*time)/6)

That's just a concoction of wrong and irrelevant. It would take quite a long post to disentangle all the confusion, but the original question can be answered directly.

There is here a classic selection problem, naturally. People who like Statalist and are sceptical of this beast will love to add posts like this with little horror stories, Satisfied users are in some other cell of the table.

As I said earlier, the time the proverbial hits the proverbial will be when some misguided researcher produces garbage at an important life stage (e.g. near thesis completion) that -- whether discovered or not -- all hinges on taking ChatGPT the wrong way. Of course, that could happen with solutions posted anywhere. But there is a strong tendency to correct others' mistakes, often reported as shocking or obnoxious, but what do people prefer? Wrong answers sugar-coated?

Quis custodiet ipsos custodes? Or, on a somewhat free translation, which AI agent watches the AI agents?

[Sebastian Kripfganz]

To be fair, there appears to be some learning. When confronted with the same question again today as in post #32, ChatGPT now provides the correct answer.

[George Ford]

https://thenextweb.com/news/the-first-iphone-what-the-critics-said-10-years-ago

[Nick Cox]

No one replied on Twitter to https://twitter.com/mjpost/status/1633818755930247170 that I can see but FWIW the solution is quite wrong.

If a user picked up that they should look at egen that would help with a partial solution.