Do not give dogs what is holy [Matthew 7:6] (Was: Prolog totally missed the AI Boom)

What is holy is only for Dogelog Player!
Do not give dogs what is holy, and do not
throw your pearls before pigs, lest they
trample them underfoot and turn to attack you.
-- Matthew 7:6
https://www.biblegateway.com/passage/?search=Matthew%207%3A6
I have deleted my posts and the swi2.pl.log proposal:
between(C, 0'0, 0'9), Digit is C-0'0.`
Just rewrite it to:
0'0 =< [Digit], [Digit] =< 0'9, [Digit] is C-0'0`.
The [X] in an evaluation is dual use again:
?- X is [a].
X = 97.
?- X is [0'a].
X = 97.
Mild Shock schrieb:

 Inductive logic programming at 30
https://arxiv.org/abs/2102.10556
 The paper contains not a single reference to autoencoders!
Still they show this example:
 Fig. 1 ILP systems struggle with structured examples that
exhibit observational noise. All three examples clearly
spell the word "ILP", with some alterations: 3 noisy pixels,
shifted and elongated letters. If we would be to learn a
program that simply draws "ILP" in the middle of the picture,
without noisy pixels and elongated letters, that would
be a correct program.
 I guess ILP is 30 years behind the AI boom. An early autoencoder
turned into transformer was already reported here (*):
 SERIAL ORDER, Michael I. Jordan - May 1986
https://cseweb.ucsd.edu/~gary/PAPER-SUGGESTIONS/Jordan-TR-8604-OCRed.pdf
 Well ILP might have its merits, maybe we should not ask
for a marriage of LLM and Prolog, but Autoencoders and ILP.
But its tricky, I am still trying to decode the da Vinci code of
 things like stacked tensors, are they related to k-literal clauses?
The paper I referenced is found in this excellent video:
 The Making of ChatGPT (35 Year History)
https://www.youtube.com/watch?v=OFS90-FX6pg