To get good mutations I’m pageranking the AST nodes of all the covered sources files similar to aider chat and using that as context for Sonnet 3.5 to allow it to generate good code mutations.
I’m not too experienced with using Sonnet 3.5 for Codegen like this and wanted to know if I was missing some best practices or if there is some additional context I can pass to Sonnet 3.5 to further increase the quality of code mutations it creates.
[Question] I’m using Sonnet 3.5 to power language agnostic mutation testing
Hey so I’m using Sonnet 3.5 to power our open-source mutation testing tool here- github.com/codeintegrity-ai/mutahunter
To get good mutations I’m pageranking the AST nodes of all the covered sources files similar to aider chat and using that as context for Sonnet 3.5 to allow it to generate good code mutations.
I’m not too experienced with using Sonnet 3.5 for Codegen like this and wanted to know if I was missing some best practices or if there is some additional context I can pass to Sonnet 3.5 to further increase the quality of code mutations it creates.
Appreciate the help, thanks!