Scaling Test Time Compute to Multi-Agent Civilizations — Noam Brown, OpenAI
Source
youtube.com
Author
Latent Space
Date
Why it matters
A lead researcher explains how spending compute at inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition → changes model capability and where multi-agentUsing several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.Full definition → scaling may go, which informs how you budget reasoning and AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → compute.
Terms in this piece · Glossary
test-time compute — Spending more computation when the model answers — thinking longer, trying multiple attempts — to buy accuracy without training a bigger model.
multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
video⚡️Factorio Learning Environment: the ultimate Game Agent Eval — Jack Hopkins
videoAnthropic’s Felix Rieseberg on AI Coworkers, Local-First Agents, and the Future of Knowledge Work
videoThe Agent Cloud: Databricks’ Bet on the Future of AI — Matei Zaharia and Reynold Xin
videoContext Engineering for Agents - Lance Martin, LangChain
