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)→
More from Research
- Probing activations restores diversity in distilled image and video generators — _akhaliq · 2026-11-17
- Perturbing inputs improves LM pretraining distillation, new paper shows — DimitrisPapail · 2026-11-17
- ReDiverse restores output diversity in few-step distilled diffusion models — anand_bhattad · 2026-11-17
- Inkling 2 Small hits 81.7% on ARC-AGI-2, beating DeepSeek V4.1 Flash but trailing on ARC-AGI-3 — teortaxesTex · 2026-11-17
- AI-formalized math spans Galois's 1832 last letter, fixing errors in a dozen published papers — stevenstrogatz · 2026-11-17
- FLUX 3 trains on images, video and sound: BFL on visual intelligence — Latent Space · 2026-11-17