[seqfan] Re: Sequence from ChatGPT

[Brendan McKay]

Neil, That idea won't work because ChatGPT is inconsistent.  In the same 
chat I asked the same question again:
Q: what are the prime factors of 10028741430768001?
ChatGPT: 10028741430768001 = 199 × 503 × 683 × 6131 × 1046803 (NOPE!)


Here is an example with elementary logic.

Q: If A equals B, and B equals C, and A equals D, does D equal C? 
ChatGPT: (correct answer with correct explanation) Q: If A equals B, and 
B is not equal to C, and A equals D, does D equal C? ChatGPT: No, it 
cannot be concluded that D equals C based on the given information. Even 
though A equals B and B is not equal to C, we cannot determine the 
relationship between A and C. Similarly, A equals D does not allow us to 
determine the relationship between D and C. Therefore, we cannot deduce 
that D equals C from the given statements. Note that the second answer 
contains only correct statements, but it doesn't answer the question. 
The correct answer is "D does not equal C". So this seems to indicate a 
problem with negation, which is a standard problem in theorem proving 
but this example is very elementary. B/
On 3/4/2023 11:20 am, Neil Sloane wrote:
> Brendan,  That's hilarious!  I suppose one could write a shell script 
> to produce the sequence of numbers that ChatGPT of April 2, 2023, at 
> 9:18pm  NY Time  gives the wrong factorization for.
> Not Of General Interest, of course, just a curiosity.
>
> Best regards
> Neil
>
> Neil J. A. Sloane, Chairman, OEIS Foundation.
> Also Visiting Scientist, Math. Dept., Rutgers University,
> Email: njasloane at gmail.com
>
>
>
> On Sun, Apr 2, 2023 at 8:42 PM Brendan McKay via SeqFan 
> <seqfan at list.seqfan.eu> wrote:
>
>     Q: what is 10007^4?
>     ChatGPT:  10007^4 is equal to 10,028,741,430,768,001.  (WRONG)
>
>     Q: what are the prime factors of 10028741430768001? ChatGPT:
>     10028741430768001 = 101 * 99041335663409. (WRONG) Moral: Don't even
>     think about using ChatGPT to do arithmetic, let alone more complex
>     mathematics. Brendan.
>     On 3/4/2023 3:48 am, Alonso Del Arte wrote:
>     > Proofreading might be a more productive use of ChatGPT here,
>     e.g., "how
>     > would you explain that numbers with property *P* also have
>     property *Q*?"
>     > Such a prompt might generate more useful content than asking it
>     to come up
>     > with an entire new entry from scratch.
>     >
>     > By the way, has anyone tried looking up something on the OEIS
>     using a
>     > mobile device rather than a desktop computer, e.g., a Samsung
>     Galaxy S8+?
>     > If you don't know how to fix that problem, ChatGPT might be able
>     to help
>     > you.
>     >
>     > Al
>     >
>     >
>     >
>     >
>     >
>     > On Sun, Apr 2, 2023 at 12:37 PM 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
>     >> <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/
>     >>
>
>     --
>     Seqfan Mailing list - http://list.seqfan.eu/
>