Why do AI leaderboards miss the mark? An exclusive dinner for AI leaders
Join Prolific on September 24th in London for an exclusive dinner with AI leaders, where we’ll tackle an urgent question: Why do AI leaderboards miss the mark?
Leaderboards promise to show us the top-performing AI models. But how reliable are they? Some of the most popular leaderboards have been criticized for underrepresenting open-source models, misaligning with real-world ability, and more.
This evening will be an opportunity to share perspectives with peers and engage in candid conversation about where leaderboards are falling short - and what we can do to improve them.
Over the course of the evening, you’ll:
Engage in roundtable discussions: Explore the strengths and limitations of current AI leaderboards, and how they can better align with real-world use cases.
Exchange ideas with peers: Explore new approaches that bring human-centered perspectives into AI evaluation.
Build meaningful connections: Network with fellow leaders who are setting the standards for the next generation of AI.
Connect with peers and help shape the future of AI evaluation - over great food and thought-provoking discussion.