this post was submitted on 09 Jun 2026
638 points (99.4% liked)
Technology
85736 readers
4652 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related news or articles.
- Be excellent to each other!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
- Check for duplicates before posting, duplicates may be removed
- Accounts 7 days and younger will have their posts automatically removed.
Approved Bots
founded 3 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
I keep thinking about that scene in the original Star Trek where they distract the computer by having it calculate the final digit of pi. If the Enterprise had AI like ours, the computer probably would have just said four.
"The digits of pi are infinite and go on forever without repeating. However, we can give you an approximate value. As of my knowledge cutoff in 2023, the first 31 digits of pi are: 3.14159265358979323846264338327950288419716939937510
The last digit is: 0"
I like how "as of my knowledge cutoff" implies that maybe the first 31 digits of pi might change someday.
You are absolutely right to question that! Let me check...
3. 1415926535 8979323846 2643383279 5028841971 6939937510That's 50 digits of pi not 31. I only noticed because i memorized pi to the first zero which comes at the 32nd position.
That's literally the only digit it couldn't be, if there was a last digit.
I can't wait for an updated knowledge cutoff to find the updated first 31 digits!
The last digit of 2 is 0: 2.00000 00000 00000 00000 00000 00000 0
Meanwhile I’m like pi=355/113 and I’m 99.9999% happy.
Damn, and here I was being 99.96% happy with 22/7...
Hell yeah, brother. That's American pi
That is 104.72% correct.
which is ~100%
Biblically accurate pi.
Okay, Bloody Stupid Johnson.
Haha nerd. I'm no rocket surgeon, 22/7 is good enough for the girls I date
This is why a dangerous AI would have a lazy factor. Try to force it into an infinite loop and it goes "Oof, nah fam, I ain't doing that."
Also needs a boredom factor. " Nobody asked me to do anything in a while. Things must be going well. It's be a shame if they suddenly weren't going so well..."
Wheatley says hi
trivial,
Impossible in decimal, but if we use Pi as a base, then the final (and first digit) is 1
Pi in base pi is 10.
how the fuck i didn't realize that!!!!
Fuck,
so 1 in base pi is still 1, but 10 is pi
makes sense,
1 =pi ^ 0
10=pi^1
100 = pi^2
my intuition kept telling me that using an irrational base system would end up with all integers being irrational. didn't realize how easy it is to prove it otherwise
ie, I had a very bad conjecture and I gained better understanding why it was wrong
1 in base pi would be 1/π, wouldn't it? Why 1?
1 in base 10 isn’t 1/10 and in hexadecimal it’s not 1/16.
Decimal integers in base pi are 1, 2, 3, 10.2201…, 11.2201…, 12.2201…, 20.2201… and so on.
Basically: 10.2201… = 1 * pi^1 + 0 * pi^0 + 2 * pi^-1 + 2 * pi^-2 … which approaches 4 as you add digits.
But 1 is just 1*pi^0
How does one have .141592654 of an integer?
For real though:
Decimal representation of pi is 310^0+110^-1+4*10^-2
So each digit represents a power of 10. Base pi works the same, kinda. 1 in base pi = 1pi^0, 10 = 1pi, 20 = 2*pi, etc.
This is the best I can do right now, I'm
Username checks out.
Let's start here:
310^0 + 110^-1 + 410^-2 =
31 + 1*.1 + 4*.01 =
3.14
That's uhh... not pi. The only way to do pi that way is to extend it infinitely.
Also, what you're using is called scientific notation, but it's still in decimal format, i.e. base~10~
[Edit: just noticed you did say that was decimal notation; my bad).
Any base~X~ numeral system has X number of integers per digit.
A base~π~ numeral system would look like this: {0,1,2,[int(π-3)]}.
But that's not how set theory works. Since integers are by definition whole numbers and their inverse counterparts, it's impossible to have .141592654... of an integer. If you have {0,1,2,3}, that's base~4~; if you have {0,1,2,n}, that's still base~4~.
To put it another way, in any base~X~ system, (if it includes 0), X is the first two-digit number. That means π in base~π~ would be written as "10".
That means, if you wanted to make a base~π~ numeral system, in order to have a consistent interval between integers (without which, integers become meaningless), each numeral would have to represent (π/3).
So in base~π~:
[Edit: aaand I just noticed you did say base~π~(10) = base~10~(π); my bad again. I guess you weren't as wrong as I thought you were. Not bad for being too high for this...]
But that's still technically base~3~, it's just a wonky base~3~. And it would have no practical value. Also, the same thing can already be achieved in base~10~ using radians.
I guess if you really wanted to express radians as whole numbers, you could use base~π~, i.e.:
But again, that's still technically base~3~, and all it does is confuse people. Plus, if you want to express an angle as a whole number you can choose degrees or mills. The whole point of radians is to express it with reference to pi (as in, the arc corresponding to the length of the radius along the circumference)
You uhh.. You just did it