40,000x40,000=1,600,000,000 40,000x500=20,000,000 x80 more storage With 40,000 word vocab, 16 bits per word if huffman them.
Of course, we can limit what we link.....we can link words ONLY IF they pass a similarity threshold. So cat and hose wouldn't link. Of course in context like at a store they are both 'buyable' shopping items, lol, but if you want to replace a word based on context and not the word, then you just use entailing words....i mean how can you get this related unrelated word 'hose' if they don't even....they only get the same seat in the sentence because of the context, you must get the Next Word from "i [bought a new] cat today" i.e. "bought a new [hose]". ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Ta664aad057469d5c-Ma5ef96ea7c6ecf1c7ce5032c Delivery options: https://agi.topicbox.com/groups/agi/subscription
