Matt what was the best compression you got from using just the last 6 letter context on enwiki8? 21MB? Or, 18MB?... ? And did you group related words? And how many models were mixed and what were they? Just want to know how low it can go *without doing the grouping related words*.
And do you know how Shelwien's Green algorithm mixes the 17 models? Please explain it "vividly"/clearly if you do. Shelwien seems to have failed 10 times explaining it to me lol. Maybe I can combine his plus mine. ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tcfc4df5e57c62b43-M3d0ab750e3a0198ac4f0f5f0 Delivery options: https://agi.topicbox.com/groups/agi/subscription
