Induction + symbolic causal prediction + global coherence constraints
THIS is the 1st approach I'v ever seen, that smells like AGI.
R Evans, J Hernandez-Orallo, J Welbl, P Kohlia, M Sergot
Making sense of sensory input
arXiv:1910.02227v2
https://arxiv.org/abs/1910.02227v2
#AGI
It is just a logical shadow of human reasoning, but that is fine. I think the idea to engineer minds is deeply problematic and a very questionable goal.
We should rather seek to improve human coordination.
Next iteration, still slow, but interesting approach.
https://www.sciencedirect.com/science/article/pii/S0004370221000722