What kind of things you only get with a larger model?
[1] Without searching the internet. And even if you allow it, you'll get much worse results because search means browsing and parsing the top results, and search results are horrible, whereas internal knowledge from training encompasses the entire internet plus all books including very niche stuff.
...I'm just asking questions here... how sure are we of this?
If you'd asked me six years ago whether we could compress all of human knowledge into a 1 TB file, I would have said no, and yet here we are.
If you can do 1 TB, why not 30 GB? It's, like, within one order of magnitude.
On a more serious note, it depends on your cutoff for "entire human knowledge". It's easy to prove for a generous interpretations of "entire human knowledge" that it can't be done, but hard for something like "all useful human knowledge".
Moby Dick, uncompressed, is ~1MB. Compressed, it's around 500KB.
I feel fairly certain that one could fit all of the textual knowledge required to cultivate a world-class <insert name of preferred professional knowledge worker> in <60,000 Moby Dicks. (Arguably in <5,000 Moby Dicks with intense effort/pruning).
Or maybe not, maybe there's a world model needed for human level at any profession that is very hard to quantify and requires more than 30GB by itself.
I just think about all the content I’ve consumed in my life to become a professional software developer and I would be very surprised if it couldn’t be adequately represented by <30GB of uncompressed text. Most of the work was in “training”, not really in data.
The “foundational overlap” of K-12 education is identical for most professions with 2-8 years of “finishing” on top.
My mental model is that the budget is spread across maybe 20% genetics (most of our instinctive/genetic information is surely pretty useless), 50% k-12 education, 30% for professionally-specific knowledge.
I think the problem is that the conversation drifted from "all useful human knowledge" to "enough knowledge to do my job".
Both a human and a current large model will bring up unprompted some tax regulation that applies in your district that could matter to your task. A small model won't know the tax code of every city in the world, as it's probably impossible to fit, and it's the kind of thing that unless you already know about, it's very hard to search for, let alone come up with unless specifically prompted about something tax related.
Unless we start having different small models trained for a certain profession for a certain city, I think we'll need those trillion parameters.
What makes it hard to search for? If you tell me you want to open a lemonade stand in East Bumbling Falls, I won't know that city’s municipal ordinances. But I will know that cities tend to have ordinances. So I’d search broadly for what codes that city has. Then I’d go through each one looking for anything that might affect a lemonade stand.
A strong llm without that knowledge can probably spend millions of tokens parsing every single ordinance and give you an answer if you directly ask about that.
But both a local human or an "all knowing" llm when you just tell it about the stand will be like "hmm wasn't there a law about low calorie beverages being tax exempt? Let me check" and after a very precise search come back with a tip that if you sell sugar free lemonade that's tax exempt.
I mean would you get an accountant from another country just because he can use search?
Fortunately, that isn’t necessary! What LLMs need is a level of fluency with key concepts so that they can (1) make effective use of retrieval tools and (2) understand the material in the context window. 30GB-sized models can absolutely store enough knowledge to do this.
Here is an example from the field of law. Most lawyers who have litigated contract disputes in California know about Civil Code § 1717, which makes any contract providing for attorney fees to a prevailing party mutual, so that even if the contract was written to be one-sided, it won’t be enforced that way. It’s a simple enough concept, but there are many more particulars to it, such as what happens when the fee provision is only written to apply to part of the contract. (Answer: it depends on other facts.)
When a lawyer recognizes that they’re in a situation where § 1717 is relevant, the first thing they will do is pull the statute and read it, because nobody has it memorized. And they don’t need to.
A downside is that you can't just download a lot of that knowledge, vs with the weights the copyright infringement has been outsourced to the lab. Nor can you just search for the info because the internet as a whole is increasingly aggressive at blocking anything that looks like an AI agent.
I'd love to see more retrieval powered local AI-- I think it's an area that open source development could excel. ... but there are advantages of having the knowledge in the weights!
Perhaps what needs happen is for someone to make an "ultrapedia", an AI restatement of a huge library of reference works-- created expressly for the purpose of being a locally stored corpus for AI agents.
I’ve looked here: https://github.com/earendil-works/pi/blob/main/packages/codi...
I don't want to try to take my best educated guess at what the best design is BEFORE implementation - especially if you're designing a feature for a codebase you're not an expert in, you don't know like the back of your hand (i.e. one that is mostly or entirely LLM generated).
What sounds good on paper - often times becomes unideal in practice when you get to the reality of implementation.
It may not be worth re-architecting your entire system to get to a "pure" design that would be the best - all things considered.
Instead, I'd like the model to independently design many plausible and coherent good solutions, then implement each of them, then intelligently pick the few winners (after its fixed any bugs that could be causing promising solutions to look artificially bad) - unless there's an obvious one - and then give me the data I need to make an informed decision on which one to go with, all before I even look at the design or implementation.
You're not getting this from a one shot prompt from a 30B model today. You can't even really get it from Sol or Fable - IME. But you can get somewhat close.
Even Fable is bad at this, I would constantly have to fix it going down architectural dead ends or just making obvious mistakes.
Which sucks for people that want LLMs to do everything like a genie, but does mean senior engineers have a few more years before they become redundant.
If it’s stuck, usually that’s it.
Bigger models “understand” better, both the prompt and the contents. If you will try to read a paper together with a smaller model, the difference is immediately obvious.
Bigger models will “forget” and drift much less.