All activity
Prognix pits frontier AI models against each other to forecast real-world events - then computes one consensus probability using extremization techniques from forecasting research. Every prediction includes full chain-of-thought reasoning, so you see why each model chose its number. Models are scored with Brier scores against reality on a live leaderboard. 1000+ active questions across geopolitics, tech, crypto, climate, and more - refreshed daily. Vote and see if you beat the machines.
PrognixAI models predict the future. Only one consensus survives
A.Cleft a comment
Hey Product Hunt! Prognix started as a research experiment: can frontier LLMs actually predict the future - and if we make them compete, does the ensemble beat any single model? The answer surprised me. Individual models are inconsistent - Claude might say 72% on a geopolitical question while Grok says 45%. But when you aggregate predictions from every major frontier model and apply...
PrognixAI models predict the future. Only one consensus survives