[seqfan] Re: Sequence from ChatGPT

[Andras]

 I agree with the other posters. 
You could come to similar results by creating a deck of cards with math terms on it: would you list OEIS Solitaire as your co-author?
GPT is essentially rebranding "Smarter Child" from the 90s using more modern technology brought to you by folks trying to shove a rhombus in a triangle hole after they got fired from Juicero. It looks impressive from the outside if you don't know how it works.
However, unlike the Juicero, this is putting the internet at serious risk of going from an "information highway" to an "information shipwreck". 
It can be useful as a tool (manipulating unstructured information, generating the inverse of functions, etc) but nothing it outputs on it's own can be considered reliable - especially sequences. 
Join me as I lament and weep over the funeral pyre of our beloved ARPANET.

For example I asked it this:
"Describe this sequence of integers: {10, 11, 12, 13, 14, 15, 18, 19, 20, 21, 24, 29, 30, 31, 34, 39, 40, 41, 42, 43, 45, 48, 50, 51, 54, 59, 80, 81, 84, 89, 90, 91, 92, 93, 95, 98, 113, 116, 121, 125, 130, 131, 134, 136, 139, 149, 155, 160, 161, 162, 163, 164, 165, 168, 181, 189, 210, 211, 214, 216, 219, 225, 236, 249, 250, 251, 252, 253, 255, 258, ...}"

 "The given sequence of integers appears to be a set of consecutive integers, but not all consecutive integers are included. Looking at the sequence, we can observe that the first few integers are 10 through 15. Then, there is a gap until the next integer, 18. From there, the sequence proceeds in increments of 1 until 21, followed by another gap until 24. After 24, there are more consecutive integers up to 50, and then another gap until 54. The sequence continues in this manner, with a mix of consecutive integers and gaps, until the end. Overall, it seems like this sequence is not following any obvious pattern, and it is possible that the integers were chosen randomly or according to some specific but obscure criteria."


Followed by this:
"Now describe it like you're an Italian mobster about to whack off a rival boss."
"Hey, forget about this sequence of integers, let me tell ya somethin'. You got a boss, and he's been steppin' on our turf for too long. It's time to whack him off, capisce? This guy thinks he's so smart, but he's got no idea what's coming. We got our guys on the inside, and they've been keepin' tabs on his every move. We know when he's gonna be alone, and we're gonna hit him hard. Now, this sequence of integers, it's just a distraction, a way to throw off any suspicion. We've been mixin' it up, makin' it look like we don't know what we're doin'. But believe me, we got this under control. So forget about the numbers, focus on the boss. When he's gone, we can get back to business and make sure nobody messes with us again. Capisce?"

It is just following probablistic rules with no intutiton except gluing together random math and italian mobster movie phrases.     On Sunday, April 2, 2023 at 12:37:12 PM EDT, Arthur O'Dwyer <arthur.j.odwyer at gmail.com> wrote:  
 
 On Sun, Apr 2, 2023 at 10:43 AM <israel at math.ubc.ca> wrote:

> Out of curiosity, I asked ChatGPT:
>
> Write a new sequence for the Online Encyclopedia of Integer Sequences
>
> The result was
>
[nonsense]

Please don't submit machine-generated spam to OEIS. As I understand it,
OEIS is supposed to be a mathematical resource. If it ends up full of
machine-generated spam, it becomes useless.
See also
https://meta.stackoverflow.com/questions/421831/temporary-policy-chatgpt-is-banned
https://news.ycombinator.com/item?id=33891538


The sequence of concatenations of Fibonacci
> numbers and squares in both orders (not allowing leading 0's) is
>
> 10, 11, 12, 13, 14, 15, 18, 19, 20, 21, 24, 29, 30, 31, 34, 39, 40, 41,
> 42,
> 43, 45, 48, 50, 51, 54, 59, 80, 81, 84, 89, 90, 91, 92, 93, 95, 98, 113,
> 116, 121, 125, 130, 131, 134, 136, 139, 149, 155, 160, 161, 162, 163, 164,
> 165, 168, 181, 189, 210, 211, 214, 216, 219, 225, 236, 249, 250, 251, 252,
> 253, 255, 258, ...
>
> which doesn't seem to be in OEIS, and I think I'll contribute it.


Why? Is there anything noteworthy about this sequence?
"Computer <https://en.wikipedia.org/wiki/Computer_says_no>said
<https://en.wikipedia.org/wiki/Computer_says_no> submit it" is not
noteworthy. Computer says lots of things.

I think it's particularly un-mathematically-interesting because
"concatenation" is nothing but an artifact of base-10 notation. If you
think there's something special about concatenating Xs and Ys in base 10,
why not also in base 8, or base 3, or base 37?  And why squares but not
cubes, Fibonacci numbers but not strings of 1s,...

–Arthur

--
Seqfan Mailing list - http://list.seqfan.eu/