Open-world survival games pose significant challenges for AI algorithms due to their multi-tasking, deep exploration, and goal prioritization requirements. Despite reinforcement learning (RL) being popular for solving games, its high sample complexity limits its effectiveness in complex open-world games like Crafter or Minecraft. We propose a novel approach, SPRING, to read Crafter's original academic paper and use the knowledge learned to reason and play the game through a large language model (LLM).

Here we test whether these scaling "laws" hold for the task of modeling the human brain.

It is inexpensive and needs only one GPU week of training.

Program synthesis has been long studied with recent approaches focused on directly using the power of Large Language Models (LLMs) to generate code.

Booth is a reporter at TIME. Governor Gavin Newsom speaks at Google about preparing students and workers for the next generation of technology, in San Francisco, California, on August 7, 2025. Governor Gavin Newsom speaks at Google about preparing students and workers for the next generation of technology, in San Francisco, California, on August 7, 2025. Booth is a reporter at TIME. CEOs of the companies racing to build smarter AI--Google DeepMind, OpenAI, xAI, and Anthropic--have been clear about the stakes.

Humans interpret language using beliefs and prior knowledge about the world. For example, we intuitively understand the response "I wore gloves" to the question "Did you leave fingerprints?" as meaning "No".