Harness Engineering for Self-Improvement
Original excerpt
A harness is the system surrounding a base model that orchestrates execution and decides how the model thinks and plans, calls tools and acts, perceives and manages context, stores artifacts, and evaluates results.
Context
I explicitly mention “deployment system” because the layer between the raw model and the real-world context seems to be as important as the model’s raw intelligence (i.e. the evals right after pretraining). Harnesses are important components of AI deployment, as shown by successful coding agent products such as Claude Code and Codex.