Sign up to save your podcasts
Or
Share FutureSim: Replaying Real-World Events to Evaluate AI Forecasting Agents
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
FutureSim: Replaying Real-World Events to Evaluate AI Forecasting Agents
A benchmark designed to test AI models' capabilities in making accurate 3-month future predictions.
View all episodes
By Shaoqing TanA benchmark designed to test AI models' capabilities in making accurate 3-month future predictions.