A rough rule I have for information intake is something I call the information barbell. The best information is either:

Lindy content is usually a good sign that the analysis is correct or relevant over long periods. It’s why we still have “classics” that are required reading for most subjects ranging from computer science to mathematics to literature.

Hyper-recent information is usually immediately relevant — figuring out a new trend, understanding a new development, or arbitraging the information asymmetry in another way. So who better to learn from than the people actually doing the thing?

Anything in-between has a much lower signal-to-noise ratio. Secondary sources usually don’t add new insights (and might hide them) while providing analysis you could have done yourself.

Both ends of the information barbell help us learn from history and synthesize new data from first principles.