from Hacker News

Separating code reasoning and editing with Architect and Editor models

by sweca on 9/29/24, 5:31 PM with 1 comments

• by anotherpaulg on 9/29/24, 10:55 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.