The business of extracting knowledge from academic publications

Re:The business of extracting knowledge from academic public... by marviel on Wednesday November 01, 2023 @08:36PM (#38107397)

Big implications and ponderings here for the slew of RAG based applications that are about to hit the market.

I saw a blog post by a fellow from OpenAI earlier today which basically said "when you refer to a model like Bard, or Claude, or Llama -- you're moreso referring to the dataset, than you are the architecture."

His meaning was at training time, but perhaps a similar observation can be had in this context: The value of a retrieval / organization system is only as good as the average information quality in its target corpus

[ Parent | on HN ]

Re:The business of extracting knowledge from academic public... by nextworddev on Wednesday November 01, 2023 @09:34PM (#38107848)

"about" to hit the market? There's like 3000+ Co-Pilots already in the market.

But yes, more to come out next year obviously.

[ Parent | on HN ]