Pierrad
Changing the AI model for Copilot code completion
Is your feature request related to a problem? Please describe.
I would like to change the AI model used by Copilot to get more accurate code completions.
As mentioned in this documentation:
Changing the AI Model for Copilot Code Completion,
I hope to use a better model.
By default, Copilot code completion uses the GPT-4o Copilot, a fine-tuned GPT-4o mini-based large language model (LLM). This model has been trained on a wide range of high-quality public GitHub repositories, providing coverage of over 30 programming languages. Its knowledge base is more current than the default model, and you may find that it generates completion suggestions more quickly.
Describe the solution you'd like I hope the plugin can provide an option for users to select the AI model. This way, users can choose different AI models based on their needs to obtain more accurate code completions. Thank you.
Hi @Carmel0, when I try to change the completion model in VSCode (and VSCode insiders with copilot plugin preview mode or not), I don't have any choice, I can only select the only model available which is GPT-4o.
Indeed, previously, I have choice between GPT-3.5 Turbo and 4o but it seems they removed the choice to only support 4o.
