How an artificial intelligence (as in large language model based generative AI) could be better for information access and retrieval than an encyclopedia with a clean classification model and a search engine?
If we add a step of processing – where a genAI “digests” perfectly structured data and tries, as bad as it can, to regurgitate things it doesn’t understand – aren’t we just adding noise?
I’m talking about the specific use-case of “draw me a picture explaining how a pressure regulator works”, or “can you explain to me how to code a recursive pattern matching algorithm, please”.
I also understand how it can help people who do not want or cannot make the effort to learn an encyclopedia’s classification plan, or how a search engine’s syntax work.
But on a fundamental level, aren’t we just adding an incontrolable step of noise injection in a decent time-tested information flow?
The problem will always be that you have to use an llm to ask questions in natural language. Which means it gets training data from outside whatever database you’re trying to get information from. There isn’t enough training data in an encyclopedia to make an llm.
So it can’t be better because if it doesn’t find anything it will still respond to your questions in a way that makes it seem it did what you ask. It just isn’t as reliable as you yourself checking and going through the data. It can make you faster and find connections you wouldn’t make yourself easily. But you can just never trust it as you can trust an encyclopedia.