AI model testing
1 statements across 1 episodes · 1 bullish · 0 bearish · 1 people on the record · first statement May 23, 2025 by Scott Clark · across every show →
Everything said about AI model testing, oldest first
May 23, 2025 positive
Clark: AI testing should use many weak estimators to detect behavioral differences
“Instead of trying to come up with a small number of strong estimators for performance, where we want to be able to conclusively say A is better than B, Instead, what we want is a large number of potentially weak estimators to be able to determine whether or no…”