i'm heartened to see ai companies agree *that* we need embedded evaluations; now the question becomes *how.* answering this question requires many voices. today 100+ respond, calling for five minimum requirements to make embedded evaluations credible. we have a lot of work to do. to meet this demand, @aievalforum -- where i act as senior advisor -- is embarking on an ambitious path ahead to: (1) develop standards for embedded evaluation; (2) create independence-preserving funding mechanisms; and (3) establish a talent pipeline for independent evaluation. we are actively expanding our membership. we also welcome conversations on support and funding. please reach out if you would like to collaborate with us on any of these initiatives.