hraness
Theme
Appearance

saved

Artificial intelligence now beats some of the best human forecasters

by The EconomistThe Economistpublished

Hraness wrote this summary from a saved copy of the source. Quotations are taken word for word from the source.

gist

An AI won the Summer 2026 Metaculus Cup for the first time — AIs also took second and fifth, humans third and fourth — per an Economist report citing Forecasting Research Institute analysis. LLM-based forecasters now approach superforecaster parity on evolving question sets, while startups like FutureSearch add multi-model debate, paywalled data, and memory wipe for counterfactuals. Caveats: the cup is four months, the field non-elite, and multi-year horizons may still favor humans. (Read via Hindustan Times syndication; the live Economist page returned 403.)

ideas

  • Metaculus Cup milestone. An AI won the seasonal cup for the first time; AIs also took second and fifth, leaving third and fourth to humans across hundreds of September-resolved questions.
  • LLM forecasters, not narrow models. Unlike weather-style specialized systems, these bots use general LLMs to read news and data broadly and explain reasoning—useful when persuading decision-makers.
  • Startup tricks on top of scale. Multi-model investigation and debate, paywalled esoteric datasets (Mantic), pundit track-record scoring (Preseen), and memory wipe for counterfactual re-runs sit atop frontier LLM scale.
  • Solo tinkerer can still win. Jeffrey Liang’s bot beat better-funded startups with under 150 hours and a couple thousand dollars of compute, and leads an AI-only Metaculus contest.
  • Limits and price collapse. Four-month cups and non-elite human fields bound the claim; multi-year forecasting may still favor humans. Superforecaster work can cost over $10,000 and a week; FutureSearch sells minutes and a few dollars.

quotes

“For the first time an AI won the seasonal Metaculus Cup, a proving ground for forecasters of a wide variety of events.”

The Economist, stating the Metaculus Cup result.

“suggested AI systems have now reached parity with the superforecasters on an evolving set of forecasting questions.”

The Economist, citing Forecasting Research Institute analysis.

“The human forecasters who enter Metaculus’s competitions are not necessarily the world’s best.”

The Economist, bounding the human comparison set.

“A forecast from human superforecasters can cost more than $10,000 and take a week.”

The Economist, contrasting price and latency with AI services.