timelets

Three times a year, the forecasting platform Metaculus hosts a tournament that is known to have especially difficult questions. It generally attracts the more serious forecasters, Ben Shindel, a materials scientist who ranked third among participants in a recent competition, told me. Last year, at its Summer Cup, a London-based start-up called Mantic entered an AI prediction engine.

A few months later, the guesses from Mantic’s prediction engine and the other tournament participants were scored against the real-life outcomes and one another. The AI placed eighth out of more than 500 entrants, a new record for a bot.

Mantic’s prediction engine combines a bunch of LLMs and assigns each one different tasks. One might serve as an expert on a database of election results. Another might be asked to scan weather data, economic outcomes, or box-office receipts, depending on the question that it’s attacking. The models work together as a team to generate a final prediction.

On Metaculus, a group of forecasters has taken to estimating when AIs will have the chops to out-predict an elite team of humans. Last January, they said there was about a 75 percent chance this would happen by 2030. Now they think it’s more like 95 percent.

https://www.theatlantic.com/technology/2026/02/ai-prediction-human-forecasters/685955/

The feedback cycle is long, but the approach seems to be working nevertheless.