You say one model performs great on real life dataset A but poorly on another such B, while another model performs great on B but poorly on A. Take a look at what your meaning of Great and Poorly mean. There is indeed a certain model/brain that is the Better Great one we seek/want over all others that is great on both the datasets we use (A and B) more than others; less trade off. There may be a few that are as equally Good/Great, but these are the Better ones over the Worse ones. The Good ones we want that perform great on many datsets overall are the ones that make us Survive longer. Survive=Good. Our own brains are an example of a model/s that are fairly the best 'organs' over ex. a monkey's or rock's.
We all know this already, the AGI we want will be good across many datasets. We just went through this above lol. AI/predictableness exists, the way physics works is the free lunch; we follow laws. ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T353f2000d499d93b-M8a455b0b05ff453a17686fbe Delivery options: https://agi.topicbox.com/groups/agi/subscription
