AI Forecasting in 2026: What 11 Analyses Say by Benjamin Wilson 🔸

·Nuno Sempere··

This post is a syn­the­sis of 11 Me­tac­u­lus analy­ses run be­tween Oct 2024 and May 2026, seek­ing to sum­ma­rize ev­ery­thing we know about AI fore­cast­ing and how to do it well. Con­clu­sions from other pa­pers, blogs, and bench­marks are also dis­cussed in or­der to give a com­pre­hen­sive overview of the field. Top takeawaysPros still beat bots in com­par­i­sons to date: Me­tac­u­lus has com­pared bots and Pros (top fore­cast­ers on Me­tac­u­lus) on a shared set of for­ward-look­ing ques­...

Read full article →

Related Articles

Same Vaccine Question, Three AI Models, Different Answers: A Case Study in AI Biosecurity Safeguards by Nnaemeka Emmanuel Nnadi
Nnaemeka Emmanuel Nnadi · Nuno Sempere · 2h ago
A Calibration Benchmark for LLM Beliefs Across a Taxonomic Hierarchy by DanRKAlex
DanRKAlex · Nuno Sempere · 1d ago
When will AI forecasting crush human superforecasters?
Daniel Reeves · Manifold Markets · 1d ago
Disagreement = Counterfactuality for Matching Funds by ellie
ellie · Nuno Sempere · 1d ago
Which AI risks will grow in global attention in Q3/2026?
JK · Manifold Markets · 2d ago