[rhelz]

// I really don't get this perspective. How can you possibly hope to understand "recently-published papers" without first understanding the basics of the field, //

A healthy field moves faster than the textbooks can keep up. Consider the field of, say, personal transportation, during the turn of the century. I'm sure they had some very classic textbooks on veterinary medicine for horses and oxen. But they probably didn't have a lot of classic textbooks on being an auto mechanic.

In the 80's and 90's, if you were studying AI in school, they'd be teaching you prolog, first order logic, various parsing techniques, heuristics to search through graphs. Now it is neural nets, transformers, etc.

A healthy field has to "tear up the textbooks" every 10 years or so.