Frontier models ~solve a brand-new game, say researchers measuring generalisation is dying

gleech · x · 2026-11-17

Gavin Leech and coauthors argue videogames are becoming unusable for measuring model generalisation, showing GPT-6-class models can nearly solve a difficult game released after training. Full details in the linked Paradigm 3 report.

Related event: GPT-6 models solve 86% of a brand-new puzzle game, study finds(2 posts)→

Original post →

More from Research

Research channel →