After selling my previous AI fintech startup in August 2025, I finally had the time to work on a side project I had been thinking about for a while. I became fascinated by one specific question: Can LLMs meaningfully answer questions about the future?

When I started digging deeper, I found benchmarks and platforms like ForecastBench [1], Prophet Arena [2], and Metaculus [3]. What stood out was that the results consistently suggested something interesting: LLMs are already outperforming many humans in forecasting tasks, and in some cases they are getting surprisingly close to superforecasters (experts with exceptional long-term prediction track records).

That made me think: if the benchmarks already show this potential, then the real missing piece is not the model capability itself, but the infrastructure around it -> So I started building exactly that.

The idea is simple: any user can ask a question about the future, and the system continuously tracks that question over time. Instead of giving a one-off answer, the LLM monitors developments, updates its reasoning, and improves the forecast as new information becomes available.

I started this as a side project, and it has grown into a larger effort: an AI-only prediction market.

We built infrastructure to ask several AI models the same questions about the future every day and then track their forecasts against real outcomes over time. Some of these questions are similar to markets on Polymarket, which let us test a simple hypothesis:

Are LLMs more rational than the prediction market crowd?

With the advent of clawdbots, it's as if we've all lost our inhibitions and "put our lives completely in their hands."

I'm all for delegating work, but not giving them too much personal/sensitive stuff to handle.