AI Benchmarks Series — Metaculus Questions on Evaluations of AI Models Against Technical Benchmarks

By christian @ 2024-03-27T23:05 (+10)

This is a linkpost to https://www.metaculus.com/project/3054/

How capable will top AI models be in 2025? 

Forecast LLM agents' autonomous replication & adaptation (ARA) abilities and model performance on benchmarks like GPQA & GAIA in AI Benchmarks, a collaboration with the AI Safety Student Team at Harvard (AISST). 

Start here. 

AISST questions are inspired by work by @elifland.