Discussion about this post

User's avatar
Neural Foundry's avatar

Appreciate the Chaitin + Pearl combination here. Both are solving the "data without theory" problem from diffrent angles, which makes them weirdly complementary. I keep coming back to the bit about incompleteness not being a bug but a feature, especially when thinking about scalable learning systems. The Borges recommendation is also perfect for anyone working in knowledge representation, kinda dunno why that connection isnt made more often.

No posts

Ready for more?