Construct Validity
topic on 1 show · 1 statements across 1 episodes
1 statements about Construct Validity, every show
Bender says most AI benchmarks fail to measure actual capabilities
“Most of the benchmarks that are out there are not reasonable. They lack what's called construct validity, and construct validity is this two-part test of the thing that we are trying to measure is a real thing, and this measurement correlates with it interesti…”