Microsoft can use OpenAI models but it's not the model that's the problem, it's the application of them. Anthropic simply knows how to execute better.
they should just acquire one of the many agent code harnesses. Something like opencode works just as well as claude-code and has only been around half of the time.
As evidenced by Anthropic models not performing well in github presents copilot.
they should just acquire one of the many agent code harnesses. Something like opencode works just as well as claude-code and has only been around half of the time.