Just a “your mileage may vary” caveat: this doesn’t work for all kids - didn’t work for my eldest and isn’t working for my younger. They’re really stubborn kids - no idea where they get it - and they see the pedals on their bike and put them in their mental model for how it all works. Taking them off, they refuse to try the “scoot & glide” and only actually try to learn once I put the pedals back on.
At first I thought this was going to be a puzzle about getting to a specific number using certain rules for navigating the pad, including the operation buttons. For instance, by pressing one or two buttons in each row from top to bottom, can you get the calculator to display 70?
There are so many incredible ideas, projects, inventions, songs, books, movies, video games, etc. that will never see the light of day because the brilliant person or team who could make it can’t afford to stop working for long enough to create them. Find things that excite you and help them become a reality.
LLMs create models, not algorithms. An algorithm is a rote sequence if steps to accomplish a task.
The following is an algorithm:
- plug in input to model
- say yes if result is positive, else say no
LLMs use models, the model is not an algorithm.
> There are patterns in the weights that could be steps in an algorithm.
Sure, but yeah... no..
"Could be steps in an algorithm" does not constitute an algorithm.
Weights are inputs, they are not themselves parts of an algorithm. The algorithm might still try to come up with weights. Still, don't confuse procedure from data.
Don't want to get to pedantic on that response.
The model can contain complex information.
There is already evidence it can form a model of the world.
So why not something like steps to get from A to B.
And, it is clear that LLMs can follow steps.
One didn't place in the Math Olympiad without some ability to follow steps.
"Yes, an LLM model can contain the steps of an algorithm, especially when prompted to "think step-by-step" or use a "chain-of-thought" approach, which allows it to break down a complex problem into smaller, more manageable steps and generate a solution by outlining each stage of the process in a logical sequence; essentially mimicking how a human would approach an algorithm. "
> There is already evidence it can form a model of the world.
Perhaps.
> So why not something like steps to get from A to B.
Why not - because a model and algorithm are different. Simply having a model does not mean you have an algorithm. An algorithm is a deterministic set of steps, a model is typically a function or set of functions for producing results. If the result of that model is to list a set of steps (and also evaluate them too) - that does not make the model an algorithm.
> And, it is clear that LLMs can follow steps
Sure, because that is what the model is set up to do.
> Yes, an LLM model can contain the steps of an algorithm, especially when prompted to "think step-by-step" or use a "chain-of-thought" approach, which allows it to break down a complex problem into smaller
This is the model looking into its training data to find algorithms that seem to match the prompt and then to print out the steps of the algorithm and also execute them. That's not an algorithm in of itself.
I feel I'm on pretty solid ground here. "Algorithmic prompting" has nothing to do with whether a model is an algorithm. I'd ask you google the differences of a model and an algorithm very thoroughly. If something follows an algorithm, I strongly suspect it cannot be a model by definition. It can still be an AI though, as there are non LLM's AI's out there that do follow algorithms. If we are talking about LLM, the M is for "MODEL". Models and algorithms are different. A model that looks for an algorithm to use - is a very sophisicated model, but it's still not an algorithm itself just because it could find, interpret and use one.
If you think so, you should publish your results. It seems like a lot of bright people are going down the road of using LLM for algorithmic tasks. To follow steps.
I think what I'm reaching for, is a little more esoteric, that out of all the data the model is trained on, that it has also started building up algorithms/steps in its 'model', which is part of how it pics the next item.
The whole reason algorithmic prompting started was people started noticing the LLM was already attempting some steps, and that if it was further helped along by prompting the steps, then the results were better.
But, I am using 'algorithm' rather loosely, as just 'steps', and they are a bit fuzzy, so not a purely math algorithm, but more of a fuzzy logic, a first start at reasoning.
edit
also, I should clarify. I am not confusing the algorithm to make the model versus the model, i'm saying in the model it learns to follow steps.
This is meant to show that the housing can be made of wood, but the antennae and electronics still require mounting points via metal or plastic fasteners. The article gives a few reasons why this might be valuable, eg fewer toxins released during burnup, but I see this as an experiment in alternative manufacturing techniques, to see what we might be missing when we assume things like this need to be made out of metal and bolts.
>but I see this as an experiment in alternative manufacturing techniques, to see what we might be missing when we assume things like this need to be made out of metal and bolts.
That's an optimistic view, I suspect it's just done to get people talking about it and to contrast the traditional joinery against the technology. There isn't likely to be any criteria by which wood is the best material to use for something like this.
I’m convinced this is the way to go. Rather than imitating commercial fab techniques, let’s find something that works without the toxic chemistry or vacuum chambers, even if it’s janky at first. 3D printers were janky at first too.
This is excellent work and I adore the result, but I can’t help but feel like the effect could have been achieved with crafted texturing. If you look at Sketchfab as often as I do, there are artists achieving this kind of thing purely with textured polygons[0]. Dynamic lighting is lost with this method, but I feel like with an artist and programmer in close collaboration could find a clever way to solve that.
Hand crafted textures are fine but so’s spending a chunk of time roughly equivalent to hand painting a few models and being able to have any arbitrary geometry rendered in a painterly fashion. You could even figure out a way to combine them, so that the computer can half-ass the parts a master painter would let apprentices handle, and then go back in and do the important parts by hand; I work in Illustrator and figuring out how to make it do half-assed, highly stylized lighting on arbitrary shapes I draw, then doing the rest myself, has been a lot of fun.
reply