Compression ratio goes up the more data you feed it. Put in 200,000 bytes, the best compressor pops out 41,000 bytes, put in 100MB, out comes 14.8MB!
All world problems need solutions. And they all go back to a shared root goal problem: Survival, our only problem. To answer is to predict. You need to know what follows and need to know semantics. You start with a goal - a desired question, and have a desired outcome goal / solution, then you engrave a theory of how to get to the outcome (the answer to the question) based on the likeliest path, which'll mean success! We do this all the time, we have a mission and want an answer, and we can come up with a solution but sometimes aren't sure f it will get us to the destination in time or whatever you are hoping for. You need statistics. But you gotta do Transformer Architecture stuff, not just simple matching and not just 1 match either! ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T7e5f921f8ed8e057-M29f14e09bf9c6205d2e70d39 Delivery options: https://agi.topicbox.com/groups/agi/subscription
