Wisdom of the silicon crowds.

Human forecasting accuracy gets much better when aggregating predictions from a lot of individuals. LLMs are especially bad forecasters compared to these human crowds. But what about crowds of LLMs? “Our finding opens the door for simple, practically applicable steps like forecast aggregation to increase current AI models’ forecasting ability—to predict future events in politics, economics, technology, and other real-world subjects—to a level on par with the human crowd.” ~ learn more