News for hackers. Stuff that matters.
Re:Finetuning Large Language Models by furyofantares on Saturday April 22, 2023 @10:16AM (#35666829)
As long as the search part of search + prompt is good, the prompt part will emit accurate results or will say it couldn't find the answer. You can also cite the sources this way.

It seems pretty expensive because you may be pasting a lot of context into each query. If you allow the user to have follow up queries and you want to retain context of the conversation that seems expensive too. But it does seem like it should give the best results for Q&A as long as question is directly answered in your data somewhere.

There are no comments on this comment yet.