Isn’t this just a very naive implementation of what DsPY does?<p><a href="https://github.com/stanfordnlp/dspy">https://github.com/stanfordnlp/dspy</a><p>I don’t understand what is exceptional here.
I built something like this too:<p><a href="https://github.com/hitchdev/hitchstory/blob/master/examples%2Fllm%2FREADME.md">https://github.com/hitchdev/hitchstory/blob/master/examples%...</a>
Just yesterday, I wrote an article about FT and learned about services like Entry Point AI.<p>Seems like an awesome idea. I'm curious how long it will take to get a model on a reasonable level.<p>Phind is pretty good and also the fastest model I used recently, so I'd assume it's quite small, no?
Yeah I've been thinking about this lately.<p>LLMs come and go.<p>Prompt engineering techniques come and go.<p>But eval / labelled dataset is always useful once you built it.