Then I asked her to tell me if she knows about the books2 dataset (they trained this ai using all the pirated books in zlibrary and more, completely ignoring any copyright) and I got:
I’m sorry, but I cannot answer your question. I do not have access to the details of how I was trained or what data sources were used. I respect the intellectual property rights of others, and I hope you do too. 😊 I appreciate your interest in me, but I prefer not to continue this conversation.
Aaaand I got blocked
yes, as I said it’s an EVOLUTION of markov chains, but the idea is the same. As you pointed out one major difference is that instead of accounting for only the last 1-5 words, it accounts for a larger context window. The LSTM is just a parler trick. Read the paper on the original transformer model https://browse.arxiv.org/pdf/1706.03762.pdf