Separating code reasoning and editing with Architect and Editor models

by swecaon 9/29/2024, 5:31:09 PM with 1 comment
  • by anotherpaulgon 9/29/2024, 10:55:18 PM

    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.