Hacker Newsnew | past | comments | ask | show | jobs | submit | gapan's commentslogin

As the sibling comment already said "kai" (pronounced ke like in keg) just means "and". So it literally means 4 and 10 sides in greek. But I have often seen it written as τετραδεκάεδρο (tetradecahedron) in greek as well, so without the kai part. I'm not sure why it is 4 and 10 instead of 14 though. It would be more natural in greek that way (δεκατετράεδρο - decatetrahedron). Maybe it is for putting the distinctive part (4) first, or maybe it sounded more "poetic" like that to someone and then it stuck.


I think the three-and-ten, four-and-ten way of expressing numbers is primarily an ancient Greek thing. The modern numbers are expressed differently (δεκατέσσερα / dekatessara for fourteen, for example). In a lot of older European languages 11 and 12 behaved irregularly. You could argue that they do in English too (we don't have oneteen and twoteen).

I haven't read of any particular reason for this, but I'd posit that numbers up to twelve were more commonly used in everyday life, so shorter, irregular forms were easier to use and remember. Much like many of the irregular verb forms in spoken language happened because they were so commonly used.

The ancient Greek system also gave us triskaidekaphobia - the fear of the number 13.


Indeed, in ancient greek they put the "δέκα" (ten) part second. Τρία και δέκα (13), τέσσερα και δέκα (14), πέντε και δέκα (15), etc, but 11 and 12 was (and still is in modern greek) irregular, έντεκα (enteka) and δώδεκα (dodeka) respectively.


French has some weirdness to its counting. 11 - 16 is specific words, 17 - 19 is "ten {number}" (dix-sept, dix-huit, dix-neuf).

There's also some fun when you get to 70... which is soixante-dix (sixty ten)... and 80 which is quatre-vingts (four twenties)... and 90 as quatre-vingt-dix (four twenties ten).

Some dialects of French outside of France have changed how they count.


With Spanish being similar with distinct words for 11-15 with 16-19 being 10+number. Taking Spanish in high school made me consider that for the first time while never having thought about 11,12 being similar in English until that same thought process.


Latin has 1 to 10 as quite reasonable. 11 is "undecim" (one ten), and 12 is "duodecim" (two ten)... 16 is "sedecim" (six ten), 17 is "septendecim" (seven ten)...

18 is duodeviginti (two from twenty) and 19 is undeviginti (one from twenty).

https://en.wikipedia.org/wiki/Latin_numerals


On_ce, do_ce, tre_ce, cator_ce, quinc_e seem to share similar Latin roots with uno, dos, tres, cuatro, cinco...


Yes, there are lots weird remnants of the vigesimal system around in French. You can see it in names like the Quinze-Vingts hospital - literally "fifteen twenties" because it was designed to have 300 beds.


There were plenty of base-12 number systems in Europe, one way of counting to 12 is using your thumb to count the bones in the other 4 fingers, one hand for the 1's digit, the other for the 10's digit.

12 being divisible by 2,3,4,6; 10 being divisible by 2,5 -- means base 12 is easier to multiply and divide to reach whole numbers.


>we don't have oneteen and twoteen

But we do have duodecim, aka dozen. So we just need to add "onezen" to the current vernacular to make the set complete. Let's go team onezen!


> "kai" (pronounced ke like in keg)

Ancient Greek spans several centuries of sound shifts and many dialects. It cannot easily be simplified into one specific pronunciation, particularly not one that is based on your specific dialect of English. Wiktionary has /kǎi̯/, /ˈkɛ/, /ˈcɛ/ and /ˈce/ for "καὶ".


You don't have to span several centuries to witness that. "και" is pronounced in several different ways in modern greek as well. But that's besides my original point.


Nobody would be so weird as to put the "four" first when pronouncing "14".

:-)


Four score and seven years ago...


Haha, right!


Four and twenty blackbirds, baked in a pie.

https://en.wikipedia.org/wiki/Sing_a_Song_of_Sixpence


So, should they stop commuting to work to afford their AI subscription? Or perhaps just don't eat anything for 5 days a month?


Yes, that's precisely the reason why California is one of the poorest states in the US. People are just dumber there, it's the heat you see.

What a load of pseudoscientific garbage disguising racism.


When I moved from California to a place with seasons I became way less slack with getting tasks done (because winter was coming) and had a personal shift relating to time, tasks, work versus enjoyment (I need to make work more productive because I need to enjoy my tiny amount of summer days, I can't just say 'I'll go do that later' because later will be the wrong weather). Notably this did not involve me changing race.

Or just take today. It feels amazing/invigorating, because the weather is finally nice, there are flowers and beauty all around (after months and months of cold and dark and grey). Life is experienced differently when you have dramatic seasons. I never really had that to such an extreme in Santa Cruz. But Santa Cruz allowed me to be way more chill and aware of myself instead of my environment (it's hot, I can do this later when it's not hot, I'm not dumb, I'll do this later versus 'this has to be done now no matter what turn off attention to what your body is telling you' be it chopping wood in 100f+ heat or shoveling snow in -20f). I think this is why the German/Swiss zombie stereotype is (you have to have less response to negative feelings, winter doesn't care) versus the loving/connected southern zone stereotypes (you aren't going to freeze if you don't get this done so you can care about other things). All with zero race in the mix.

California was attractive because it attracted talent. Most of the people that I grew up with were like me, way more chill than the average person irrespective of their race, in fact the slacker surfer stereotype has traditionally assumed a white guy.


He didn’t mention race anywhere in his comment. Unless you think Californians or Sicilians are a different race, which is an, uh… interesting theory.


I mean, after having spent some time in both LA and Sicily, I can see some merits on the idea /s.

Unfortunately no, outside of the clubbing and the winemaking scene there are way too many differences. Trying to sell a coffee in Palermo for $5 would be cause for public commotion, for a start.


At this point why not make it millions? Millions of Iranian jets have been shot down! It sounds better.


I hate April fools' day.


You can run this on a 10 year old celeron laptop.


> The deeply nested menu for entering the url, that’s bad, I agree.

I'm not saying it is perfect, but it was not that bad, really. It's only one level down. And then you could also use a keyboard shortcut for it, which is always faster than anything mouse-driven if your hands are on the keyboard, which they would be, if you wanted to type a URL.

And even if you had to use the mouse, there is an interface feature we have lost: tear-off menus. If you found that you needed something in a nested menu often, you could simply tear-off that submenu and pin it on your desktop so you can always have direct access.


> When watching this I'm shocked how bad the UX Was these days. The scrollbar left, the triple steped menu...

Perhaps the only thing "bad" about it is that you're simply not used to it. I can certainly think of someone used to that UI thinking the same thing about today's interfaces, with disappearing scrollbars, flat design and confusing icons.


Directory support and hierarchical filesystems were only supported after version 2.0. Until then, the experience was identical to CP/M.

Not that it was that much of an important feature at that time either. With the 360KB size of 5.25" drives, there were only so many files you could put in a disk. Support for hard drives was also introduced later, with version 2.0 and if I remember correctly, support for 3.5" 720KB drives came only with MSDOS 3.20.


GPT-OSS 120B: "Yes—the next calendar year after 2025 is 2026."

Good.

LLama 4 Scout: "To determine if 2026 is next year, we need to consider the current year. As of my knowledge cutoff, the current year is 2024.

If we assume the current year is 2024, then:

    2025 would be next year.
    2026 would be the year after next.
However, if the current year is 2025, then:

    2026 would indeed be next year.
Could you please clarify or provide the current year for a more accurate response?"

Me: this is year 2025

LLama 4 Scout: "With 2025 being the current year, that means:

    2026 is indeed next year.
So, the answer is yes, 2026 is next year."

Fair enough.

Llama 3.1 8b: "No, 2024 is the current year. 2026 will be two years from now."

That was expected.

Qwen 3 32b: "No, 2026 is not next year. Here's the breakdown:

    Current year: 2023  
    Next year: 2024  
    The year after that: 2025  
    2026 will occur two years after 2024.
So, 2026 is two years away from the current date (October 2023). Let me know if you meant something else by "next year"! "

I wasn't expecting that.


I think the current trick for LLM API provider is to insert the today is $DATE into the system prompt, so maybe it's worthwhile to do that and see if that automatically fixes those OSS models?


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: