Tag
Matt Shumer predicts that by next year, one will be able to generate a GTA-scale game in a single shot using frontier models, citing a demo of GPT-5.6-Sol generating a voxel Manhattan autonomously over a week.
This paper investigates whether spatial geometry improves language-agent memory recall, demonstrating that geometry must lead recall over recency and importance, and that a ray-tracing visibility predicate is crucial for occlusion handling in 3D voxel worlds.