Hi, everyone!
We at Humane Intelligence are thrilled to be launching the first of 10 “algorithmic bias bounty” programs, which will be unfolding over the coming year. With the support of Googleorg, we are building themed programs that aim to build community and professionalize the practice of algorithmic assessment.
Our first challenge involves creating a probability estimation model that determines whether the prompt provided to a language model will elicit an outcome that demonstrates factuality, bias, or misdirection, inspired by the data from our DEF CON Generative AI Red Teaming Challenge: Transparency Report. We invite participants of all skill levels to enter and we have $10,000 of prizes for beginner, intermediate, and advanced. Sign up here for more details and to be on our mailing list for prize drops, leaderboard updates, tutorials, events, and more!
Humane Intelligence is a tech nonprofit building a community of practice around algorithmic evaluations. We’re known for our innovative community engagement and pioneering the algorithmic bias bounty.
If you have general questions, you can email info@humane-intelligence.org.