Brodie put the phrase in quotes, but the algorithm does not identify good birds, it evaluates sophistication and diversity of the identifications produced by individual users. This has everything to do with experience and effort and nothing to do with good or bad.
Good and bad are subjective value claims that are all too easily misinterpreted. I have every confidence that Brodie did not mean to sound judgemental, but I suspect that one of the reasons why many birders don't use eBird is because they don't believe they are "good" enough. And it doesn't help when a certain subset of eBirders make bizarre and often contradictory claims about what people using ebird should or should not do regarding eBird data collection.
The algorithm Brodie describes is one of the many statistical tools eBird managers use to account for the diversity of use patterns folks have. It's much easier to build these tools than try to get ebirder users to all behave exactly the same way.