Comment by refulgentis
6 hours ago
Thanks for clarifying. I was hoping to clarify the disconnect between you two, looked like on on "bigrams, trigrams, & so on." It reads idiomatically as enumerating fixed-n cases. Parsing "& so on" as "their simultaneous union" asks quite a bit of those two words. Either way, as ChatGPT showed you and you shared, all-ngram comparison brings us to O(N^3), still several exponents short of N^10 that started this thread.
This is getting tiresome. I can make the operations as complicated as necessary by comparing all possible permutations of the input string w/ every other permutation & that will not be reducible to standard attention comparisons. The n-gram was a simple example anyone should be able to understand. You can ask your favorite chatbot to compute the complexity for the permutation version.
No worries! I enjoyed it fwiw, appreciate your time :) (The permutation version would be factorial, fwiw, not polynomial. Different beast entirely.)