Separating code reasoning and editing with Architect and Editor models

Separating code reasoning and editing with Architect and Editor models(aider.chat)

5 points by sweca 1 year ago | 1 comment

The article describes experiments with aider that show the benefits of using a pair of LLMs to make changes in an existing code base:

  - An Architect model solves the coding task.
  - An Editor model edits the source code.

This approach set a new SOTA on the aider code editing benchmark, using o1-preview as the Architect and either DeepSeek V2.5 or o1-mini as the Editor.