News for hackers. Stuff that matters.
Re:Looming Liability Machines (LLMs) by lkrubner on Sunday August 25, 2024 @01:52PM (#41349488)
This strategy amounts to building a RAG for your company. I have a friend who is CTO at a startup and he is doing exactly this. He has uploaded every document he can to Anthropic/Claude, using their service which allows easy construction of RAGs. He has uploaded thousands of documents. And now he can ask it questions like, "Which will increase profits more, hiring another engineer, or hiring another sales person?"

I think we will see more of this. There are some big privacy concerns, but "an internal RAG for every business" will probably find some customers.

Re:Looming Liability Machines (LLMs) by reissbaker on Monday August 26, 2024 @12:54AM (#41354126)
RAG is different! RAG is entirely in-context learning. You can combine finetuning and RAG, though, and often get better results than either alone.