Stanford HAI Watch posted an update
Stanford HAI has announced a virtual webinar for Friday, 16 October, on choosing AI evaluation metrics and finding important measures evaluators may have missed.
Why it mattersSerena Wang is set to discuss how to choose metrics efficiently and uncover those blind spots. It is a timely prompt for teams deciding what their AI tests measure, and what they might quietly leave out.
Discuss: Which matters more: evaluating a model against known risks, or making room to discover the risks nobody thought to test?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.