And I assume this is the usual one in Europe in general for a human-readable context, like within a sentence. And as you said, dashes only in YYYY-MM-DD which is hopefully used always in any data context.
I never knew that, actually. I developed a habit of writing my dates with dashes instead of slashes because I thought the latter looked too much like the number 1. Makes me wonder how many people I've confused after they read paperwork I dated. I currently do ISO order with forward-slash as a separator, which might be similarly confusing.
There are systems out there that do YYYY/DD/MM. AFAICT YYYY-DD-MM is only used by evil pranksters, so a date that starts with a 4 digit number and uses dashes is relatively safely assumed as YYYY-MM-DD.
> It does in my jurisdiction. 2/8/24 is usually m/d/y, 2-8-24 is usually d-m-y
Where is that?
I would guess this is more like 'most people use /' and 'most people where I am use month first'; therefore those using - separation are weirdo Europeans/rest of world putting the day first.
DD-MM-YYYY isn’t as logical as you think. If it was actually consistent then it would be 82-20-0002. Only ISO 8601 and friends are consistently arranged. Anything else is simply a convention that makes sense to those accustomed to it.
But it's actually worse than that: while both the car and the horse will correctly move you from A to B, you can't cite an LLM output as a source and can't use it to check something. You can use it as a source of inspiration at best.
Here your LLM output is wrong. Someone from Germany wrote they most commonly use dots, in France we use slashes and I think countries around all do one of the other.
So yes, there's no way around doing it like we always did: find a reputable source to back a statement. And ChatGPT does not do this.
When evidence is needed, "often correct enough" is not sufficient. You need reliable and correct for sure.
I assume you understand how LLMs work? Probabilistic word generation? That can't possibly be used as a source. It literally works by making up things that look probable. It can be used to find a source, but you still need a source.
The LLM might be correct often enough, but you'll only know the LLM is correct in the case at hand by checking at a source…
> If ChatGPT behaves like a roulette to you I'll attribute that to operator error.
I never used it. I know LLMs can be impressive and useful, but sourcing is not among the use cases. The operator should be operating the right tool for the job in the first place.
Shit I say is hopefully correct often enough, but I still can't use myself as a source.
I'm not implying frequency, and it does apply here, you cited ChatGPT as an evidence, in this very discussion. I'm speaking about this, specifically. This comment where you do this was downvoted and flagged to death. And I did mention LLM can be useful. What are you trying to do here?
