ChristianWilliams

Q2 AI Fore­cast­ing Bench­mark: $30,000 in Prizes

POTUS Pre­dic­tions Tournament

Pen­sacola – ACX Mee­tups Every­where Spring 2025

USAID Out­look: A Me­tac­u­lus Fore­cast­ing Series

Build a Me­tac­u­lus Fore­cast­ing Bot in 30 Minutes: A Prac­ti­cal Guide

The State of Metaculus

AI Fore­cast­ing Bench­mark: Con­grat­u­la­tions to Q4 Win­ners + Q1 Prac­tice Ques­tions Open

Bridge­wa­ter x Me­tac­u­lus Fore­cast­ing Con­test Goes Global — Feb 3, $25k, Opportunities

Fore­cast 2025 With Vox’s Fu­ture Perfect Team — $2,500 Prize Pool

Fore­cast With GiveWell

Pre­dic­tions as Public Works Pro­ject — What Me­tac­u­lus Is Build­ing Next

• ChristianWilliamsOct 14, 2024, 10:48 PM

  4 points

  0

  in reply to: gwern’s comment on: Can AI Out­pre­dict Hu­mans? Re­sults From Me­tac­u­lus’s Q3 AI Fore­cast­ing Benchmark

  Hi @gwern, we are currently in the process of combing through winners’ documentation of their bots and which models they used. We haven’t yet encountered anyone who claims to have used one of the base models.
  
  We will share here if we learn a participant did indeed use one.

Can AI Out­pre­dict Hu­mans? Re­sults From Me­tac­u­lus’s Q3 AI Fore­cast­ing Benchmark

Me­tac­u­lus Is Open Source

Com­par­ing Fore­cast­ing Track Records for AI Bench­mark­ing and Beyond

• ChristianWilliamsSep 11, 2024, 5:52 PM

  5 points

  0

  in reply to: habryka’s comment on: AI fore­cast­ing bots incoming

  Maybe “sidestep the data leakage issue” then. The series was designed with these issues in mind. (I work at Metaculus.)

Me­tac­u­lus’s ‘Mini­tac­u­lus’ Ex­per­i­ments — Col­lab­o­rate With Us

Launch­ing the Re­s­pi­ra­tory Out­look 2024/​25 Fore­cast­ing Series

Launch­ing the AI Fore­cast­ing Bench­mark Series Q3 | $30k in Prizes

An­nounc­ing the AI Fore­cast­ing Bench­mark Series | July 8, $120k in Prizes