| > I'm not an AI specialist, but for what I know, current AI are nothing more than fine tuned statistic algorythm. Yes, but Google Page Rank is just fancy matrix multiplication and worth a fortune, while the finely tuned statistics that is machine learning (specifically chatGPT) knows more about CSS and German than I do: ~~~~ Me: Erzählen Sie bitte wie ich kann ein div tag mit schwarzes hintergrund, dreihundert px hoch und 24 pixels wide machen mit css chatGPT: Um ein div-Tag mit einem schwarzen Hintergrund, 300px hoch und 24px breit zu erstellen, könntest du den folgenden CSS-Code verwenden: div {
background-color: black;
height: 300px;
width: 24px;
} Um den CSS-Code anzuwenden, kannst du ihn entweder in einem style-Tag innerhalb deines HTML-Dokuments oder in einer externen CSS-Datei platzieren und dann per link-Tag in deinem HTML-Dokument einbinden. Beispiel: <!DOCTYPE html>
<html>
<head>
<style>
div {
background-color: black;
height: 300px;
width: 24px;
}
</style>
</head>
<body>
<div></div>
</body>
</html> ~~~~ The actual HTML and CSS it gave me is multiple lines and sensibly indented, don't know a convenient way to mark a block as pre-formatted. Note that chatGPT understood me correctly even though I forgot the German for "wide" and switched to English for one word only. (I do know more CSS than is in this example; I used chatGPT over the weekend to update my website, and it solved two problems that I didn't know pure CSS could even do, but that conversation is too big to bother putting into a comment here). |
That being said, both xbrl.org and the SEC document for us gaap xbrl reporting (an xml document) are kind of greedy about providing a documentation for what the tags actually cover. xbrl.org provide no documentation at all and advise an xbrl.org membership for developers, And the SEC document provided the tags but no information of what the tags cover.
The answer from chatGPT seems to about 'labels', used in xbrl document to describe xbrl taxinomy tag in different contexts, for example 'income in miami store'. But a change in a top executive position, like for 'CFO', once again required in SEC filling, shouldn't be subject to various arbitrary kind of label, because then the whole thing make no sense. If you call a 'cat', a 'little domestic pet'...
I searched google for the tag or label provided by chatGPT and google provided zilch. I searched the document provided by the SEC website, zilch again.
So either the code for the SEC form is wrong, either the tag or the label is wrong... or I don't know what else.
It seems, according to comments and posts from HN, that chatGPT can give good approximative answer, but fails without any notice once you ask for details.
According to an article published on HN a few days ago, 'chatGPT hallucinate facts'.