"does Diff A fix Vuln B" is not the ranking solution proposed by the author. the ranking set-up is the same as the embedding case.
I'm curious - why is LLM ranking preferred over cosine similarity from an embedding model (in the context of this specific problem)?
This is awesome! What is your most common use case? Have you thought of competing with https://scribehow.com/ in the documentation space?
I enjoyed writing this one!
"does Diff A fix Vuln B" is not the ranking solution proposed by the author. the ranking set-up is the same as the embedding case.
I'm curious - why is LLM ranking preferred over cosine similarity from an embedding model (in the context of this specific problem)?
This is awesome! What is your most common use case? Have you thought of competing with https://scribehow.com/ in the documentation space?
I enjoyed writing this one!