CONNECTED THINKING
Knowledge atlas
Follow people, viewpoints and their original evidence.
1 people · 1 sources · 1 viewpoints
IN CONTEXT
AI deployment architecture
Choose a viewpoint. Follow it back to the conversation.
Harnesses orchestrate model execution beyond raw intelligence
Equal sectors are reading positions, not rankings.
Showing 1–1 of 1 viewpoints · Newest sources first
Selected viewpoint
Harnesses orchestrate model execution beyond raw intelligence
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.
These are individual perspectives, not a measure of consensus. Source material stays in its original language.
Supporting evidence
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.
Publication dates describe the sources, not changes in belief.