an exponential curve to do with text generation models,  is history attention 
being log proportional to how many patterns you need.   so you need more than 
than 10% compression,  you need an impossible amount.
------------------------------------------
Artificial General Intelligence List: AGI
Permalink: 
https://agi.topicbox.com/groups/agi/T409fc28ec41e6e3a-M38243400e7ffe1aab953975c
Delivery options: https://agi.topicbox.com/groups/agi/subscription

Reply via email to