zlacker

[return to "GitHub Copilot Coding Agent"]
1. OutOfH+3o[view] [source] 2025-05-19 18:16:36
>>net01+(OP)
Which model does it use? Will this let me select which model to use? I have seen a big difference in the type of code that different models produce, although their prompts may be to blame/credit in part.
◧◩
2. timrog+hg1[view] [source] 2025-05-19 23:56:34
>>OutOfH+3o
At the moment, we're using Claude 3.7 Sonnet - but we're keeping our options open to experiment with other models and potentially bring in a model picker.

(Source: I'm on the product team for Copilot coding agent.)

◧◩◪
3. OutOfH+yD1[view] [source] 2025-05-20 04:14:48
>>timrog+hg1
Do you at least control the prompt?

In my experience using Claude Sonnet 3.7 in GitHub Copilot extension in VSCode, the model produced hideously verbose code, completely unnecessary stuff. GPT-4.1 was a breath of fresh air.

[go to top]