Agam Bhatia
@chewing_a_gum
professional scriptrunner, CS + Math @Stanford
参加 October 2023
1.5K フォロー中 558 ファン
We often don't know how useful our interp tools are, or when they are lying to us. We stress-test this and more in WorkspaceBench!
Astra can do crazy things without chain-of-thought. This is scary, but interpretability can help!
We made WorkspaceBench, an eval that tells you how well your interp tool surfaces the contents of the global workspace, i.e. the important intermediate variables in a forward pass.
もっと見る
