I think this paper shows the community at large will pay orders of magnitude more attention to a research area when there is, in @TurnTrout’s words, AGI threat scenario “window dressing,” or when players from an EA-coded group research a topic.
At least for relative newcomers to the field, deciding what to pay attention to is a challenge, and using the window-dressed/EA-coded heuristic seems like a reasonable way to prune the search space. The base rate of relevance is presumably higher than in the set of all research areas.
Since a big proportion will always be newcomers this means the community will under or overweight various areas, but I’m not sure that newcomers dropping the heuristic would lead to better results.
Senior people directing the attention of newcomers towards relevant uncoded research areas is probably the only real solution.
At least for relative newcomers to the field, deciding what to pay attention to is a challenge, and using the window-dressed/EA-coded heuristic seems like a reasonable way to prune the search space. The base rate of relevance is presumably higher than in the set of all research areas.
Since a big proportion will always be newcomers this means the community will under or overweight various areas, but I’m not sure that newcomers dropping the heuristic would lead to better results.
Senior people directing the attention of newcomers towards relevant uncoded research areas is probably the only real solution.