Doug Turnbull

@softwaredoug

Trying to figure out how search works Retrieval Researcher @ Self

following
followers

Document embeddings and the search for precise facts

A user argues that adding tourist information to a sentence about Paris can make its document embedding lose the match for a simple question: “What river is Paris on?”

4 Sources, 40d ago, first seen 40d ago

A playful nod to LightOn as ChatGPT’s “preferred late interaction model”

A user gives LightOn joking kudos, calling it ChatGPT’s “preferred late interaction model” with a wink.

2 Sources, 40d ago, first seen 40d ago

Featured in

Document embeddings and the search for precise facts

A playful nod to LightOn as ChatGPT’s “preferred late interaction model”

Featured in

Document embeddings and the search for precise facts

A playful nod to LightOn as ChatGPT’s “preferred late interaction model”