---
id: "concept-harness-model-coevolution"
type: "concept"
source_timestamps: ["§ The Coupling of Model Training and Harness Design"]
tags: ["model-training", "evolution"]
related: ["claim-harness-overfitting", "contrarian-harness-optimization", "entity-claude-code", "entity-codex-5-3"]
definition: "The feedback loop where models are post-trained within specific harnesses, improving native capabilities but risking overfitting to specific tool logic."
---
# Coupling of Model Training and Harness Design

## The Feedback Cycle

Modern agent products like [[entity-claude-code|Claude Code]] and the [[entity-codex-5-3|Codex]] family are **post-trained with specific models and harnesses in the loop**. This creates a feedback cycle:

1. Useful harness primitives (filesystem ops, bash execution, planning) are discovered.
2. They are added to the harness ([[concept-agent-harness]]).
3. They are then used to train the **next generation of models** to be natively good at those actions.
4. The next harness iteration builds on those native capabilities, and so on.

## The Cost

While this makes models more capable **within their native harness**, it can lead to **overfitting and a loss of generalization** when the model is moved to a different harness — see [[claim-harness-overfitting]].

The contrarian observation [[contrarian-harness-optimization]] shows the operational consequence: the native harness is not always the optimal harness, as evidenced by [[entity-opus-4-6|Opus 4.6]] performance differences on [[entity-terminal-bench-2-0|Terminal Bench 2.0]].

## Practical Implication

When you swap harnesses, expect performance to shift. When you train models for a specific harness, you are also implicitly training out flexibility — a real trade-off between specialization and portability.