Hacker News new | ask | show | jobs
by w1nst0nsm1th 1261 days ago
AI seems to be the next financial buzzword, after crypto, gig economy, CDO, dotcom, and so on.

I have seen a video a few days ago saying we are coming out of data era and entering the 'Knowledge Era' thank to AI where knowledge is following a logarythmic path. A 'revolution', a 'paradigm shift', and other bubblebabble.

Who was telling that ? A 30 years old startup CEO wearing... a t-shirt and a jeans... You see the pattern.

I'm not an AI specialist, but for what I know, current AI are nothing more than fine tuned statistic algorythm.

Here a is a short french video with english subtitles from arte, the german-french public cultural television, about a painting coming from Midjourney : https://www.arte.tv/en/videos/110342-003-A/the-world-in-imag...

The video explain very well what AI are able to do (and consequently what they can't do) if you listen (read) carefully what the art historian say about the painting, which received the first price of 2022 collorado art festival.

In short, the painting is nothing new by itself but a patchwork of elements from different period of art history. In other word a statistic average of previous painting, photography, drawing, etc... based on the artist prompts in midjourney.

Not to say the painting is aweful, I personnaly find it's beautiful and could happily put it in my living room, but it definitively shows how current AI works, commented by an historian art specialist which has no ball in AI game.
1 comments
ben_w 1261 days ago
> 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).

link
w1nst0nsm1th 1261 days ago
I asked it what was the xbrl taxinomy tag on us gaap for change in executive management of a SEC registered company in SEC filling and the answer doesn't fit compared to the whole xbrl taxinomy published on the SEC website. It also answered me 2 different kind of SEC form for it. It also gave me the correct url for the us gaap xbrl taxinomy on sec website.

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'.

link
ben_w 1261 days ago
It absolutely does indeed hallucinate[0] on occasion.

Despite how remarkable and useful it already is, don't make the mistake of putting it unsupervised in charge of anything, as it's going to mess up at least as often as a self driving car.

[0] or whatever we want to call the behaviour; also seen it called BSing (because it doesn't really know what truth is) and "mansplaining as a service"

link
w1nst0nsm1th 1260 days ago
It seems accurate for domains where it has large dataset (major programming langages like python, html, ...) to build model from.

xbrl is probably not the case as it is a very specialized domain, that is business reporting in standardized electronic format, according to specific local accounting standard, for example US GAAP in the us.

Only banks, (possibly) investment funds and accounting department in publicly traded companies, and financial regulation organisations (at least in the US) have invested that field.

This explains may be that.

link