• 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.
• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.

Persistent background subagents plus an append-only event log is a directly borrowable pattern for anyone building long-horizon agent harnesses, and it shows how a frontier lab is resolving context and steering costs.

• postTo understand whether we're making genuine progress on reasoning, we entered our
• postIn long-horizon stress testing, Muse Code iteratively optimized GPU kernels over
• postIntroducing Muse Code (beta), a terminal coding agent built for long-horizon sof

• postIntroducing Muse Code (beta), a terminal coding agent built for long-horizon sofAIatMeta
• videoThe Log Is The Agent - Ishaan Sehgal, OmnaraAI Engineer
• articleHarness Design for Long-Running Application DevelopmentAnthropic Engineering

Sign in to comment.

Loading comments…