Contra papers claiming superhuman AI forecasting 2024-09-12T18:10:50.582Z

Unit economics of LLM APIs 2024-08-27T16:51:22.692Z

Mirror, Mirror on the Wall: How Do Forecasters Fare by Their Own Call? 2023-11-07T17:39:49.988Z

Comparing Two Forecasters in an Ideal World 2023-10-09T19:52:17.682Z

Predictive Performance on Metaculus vs. Manifold Markets 2023-03-04T08:10:40.941Z

Creating a database for base rates 2022-12-12T10:09:15.778Z

Announcing the Forecasting Wiki 2022-04-15T09:52:33.167Z

Göttingen, Germany – ACX Meetups Everywhere 2021 2021-08-23T08:46:47.850Z

Announcing the UK Covid-19 Crowd Forecasting Challenge 2021-05-17T17:29:26.282Z

Crowd-Forecasting Covid-19 2020-12-31T19:30:37.019Z

Comment by nikos (followtheargument) on Mirror, Mirror on the Wall: How Do Forecasters Fare by Their Own Call? · 2023-11-08T08:24:25.946Z · LW · GW

Agreed. I think a strong reason why this might work at all is that forecasters are primarily judged by some other strictly proper scoring rule - meaning that they wouldn't have an incentive to fake calibration if it makes them come out worse in terms of e.g. Brier or log score. 

Comment by nikos (followtheargument) on Mirror, Mirror on the Wall: How Do Forecasters Fare by Their Own Call? · 2023-11-08T08:22:29.473Z · LW · GW

Thanks, yeah that list looks interesting!

Comment by nikos (followtheargument) on Project Lawful Audiobook: An Unofficial Fan Production with ElevenLabs AI · 2023-11-04T20:07:33.256Z · LW · GW

The audio quality is incredible! How automated is the process vs. how much manual work are you putting in? Really appreciate what you're doing, thanks a lot!

Comment by nikos (followtheargument) on Is Metaculus Slow to Update? · 2022-05-24T15:41:05.307Z · LW · GW

This looks really cool! And it would be nice to get some version of this (or at least a link to it) on the Forecasting Wiki.