One of the things I often wonder is "what will be the minimally viable LLM" that can work from just enough information that if it googles the rest it can provide reasonable answers? I'm surprised something like Encyclopedia Britanica hasn't yet (afaik) tried to capitalize on AI by selling their data to LLMs and validating outputs for LLM companies, it would make a night and day difference in some areas I would think. Wikipedia is nice, but there's so much room for human error and bias there.

▲

embedding-shape 3 hours ago | parent | next [-]

Your worry about Wikipedia is that there is "much room for human error and bias", yet earlier you seem to imply that a LLM that has access to the www somehow would have less human error and bias? Personally, I'd see it the other way around.

	▲	giancarlostoro 2 hours ago \| parent [-]
		When GPT 3.5 became a thing, it had crawled a very nuanced set of websites, this is what I mean. You basically curate where it sources data from.

▲

intrasight 3 hours ago | parent | prev | next [-]

It's not so much a "minimally viable LLM" but rather an LLM that knows natural language well but knows nothing else. Like me - as an engineer who knows how to troubleshoot in general but doesn't know about a specific device like my furnace (recent example).

And I don't think that LLM could just Google or check Wikipedia.

But I do agree that this architecture makes a lot of sense. I assume it will become the norm to use such edge LLMs.

	▲	giancarlostoro 2 hours ago \| parent [-]
		Correct! I know RAG is a thing, but I wish we could have "DLCs" for LLMs like image generation has LoRa's which are cheaper to train for than retraining the entire model, and provide more output like what you want. I would love to pop in the CS "LoRa or DLC" and ask it about functional programming in Elixir, or whatever. Maybe not crawl the web, but hit a service with pre-hosted, precurated content it can digest (and cache) that doesn't necessarily change often enough. You aren't using it for the latest news necessarily, but programming is mostly static knowledge a a good example.

▲

utopiah 3 hours ago | parent | prev | next [-]

> validating outputs for LLM companies

How? They can validate thousands if not millions of queries but nothing prevent the millions-th-and-one from being a hallucination. People who would then pay extra for a "Encyclopedia Britanica validated LLM" would then, rightfully so IMHO, complain that "it" suggested them to cook with a dangerous mushroom.

▲

bee_rider 2 hours ago | parent | prev | next [-]

Isn’t that sort of what a RAG is? You’d need an LLM “smart” enough to turn natural-user prompts into searches, then some kind of search, then an LLM “smart” though to summarize the results.

	▲	giancarlostoro 2 hours ago \| parent [-]
		Yeah, I think RAG is the idea that will lead us there, though its a little complicated, because for some subjects, say Computer Science, you need a little more than just "This is Hello World in Go" you might need to understand not just Go syntax on the fly, but more CS nuances that are not covered in one single simple document. The idea being having a model that runs fully locally on a phone or laptop with minimal resources. On the other hand, I can also see smaller models talking to larger models that are cheaper to run in the cloud. I am wondering if this is the approach Apple might take with Siri, specifically in order to retain user privacy as much as possible.

▲

uniq7 3 hours ago | parent | prev | next [-]

Since Google Search already includes an AI summary, your minimally viable "LLM" can be just an HTTP GET call

▲

thinkingtoilet 2 hours ago | parent | prev [-]

Wikipedia has proven to be as accurate as encyclopedias for decades now. Also, I'm betting AI companies have illegally trained their models on the Encyclopedia Britanica's data by now.