“User bench” and the idea of benchmarking AI users
A post introduces “user bench,” shifting the benchmarking question from AI systems to the people using them.
TLDR
“Many labs benchmark their AIs, but who has the audacity to benchmark their users?” a post asks, closing with “introducing user bench.”
Combined views
“User bench” and the idea of benchmarking AI users
A post introduces “user bench,” shifting the benchmarking question from AI systems to the people using them.
TLDR
“Many labs benchmark their AIs, but who has the audacity to benchmark their users?” a post asks, closing with “introducing user bench.”