I'm going to test implementing this for my project https://promptslice.com and see how it does with text based edits. I assume it will do ok.
I'm also really curious about the XML tool calls in the documentation. I have not heard of this being the norm for tools like Cursor. Is that still the case? I feel like I'm pretty in the know about this stuff but must have missed that trend.
Its true - Cursor, Cline, and many others still use xml for tool calls. In JSON, the model needs to "focus" on escaping characters correctly while also sampling from a reduced token distribution.
I'm also really curious about the XML tool calls in the documentation. I have not heard of this being the norm for tools like Cursor. Is that still the case? I feel like I'm pretty in the know about this stuff but must have missed that trend.