Is it possible to do the inverse, then? (Tranforming weights back to code)
Executing programs inside transformers with exponentially faster inference
41–50 of 139 posts
Re: Executing programs inside transformers with exponentially faster inference
#42This seems like it has some potential, but is pretty much useless as it is. Shame there are no weights released - let alone the "compiler" tool they used to actually synthesize computational primitives into model weights. It seems like a "small model" system that's amenable to low budget experiments, and I would love to see what this approach can be pushed towards. I disagree with the core premise, it's basically the…
If you want to experiment with hardcoding small programs into transformer weights, maybe try ALTA: https://arxiv.org/abs/2410.18077v2
I'm less interested in turning programs into transformers and more interested in turning programs into subnetworks within large language models.
Which the blog post brings up as a research direction, but never actually elaborates upon. And the interface between the two is a hard problem.
I'll check out the link though, thanks.
Re: Executing programs inside transformers with exponentially faster inference
#43LLMs are not deterministic per my understanding. A program always produces the same output for the same input and instructions (ignore FP accuracy for now). How is determinism achieved here?
Re: Executing programs inside transformers with exponentially faster inference
#44LLMs are not deterministic per my understanding. A program always produces the same output for the same input and instructions (ignore FP accuracy for now). How is determinism achieved here?
LLMs may be deterministic for a subset of inputs, if one output (or intermediate layer) neuron-state probability is significantly higher than the rest. My understanding is, when probabilities are close they diverge.
Re: Executing programs inside transformers with exponentially faster inference
#45If this works, we might be able to have a special ISA for LLM and forget about high level computer language for humans.
I am talking strictly about computing, not garbage in garbage out IO.
Re: Executing programs inside transformers with exponentially faster inference
#46> the whole process remains differentiable: we can even propagate gradients through the computation itself. That makes this fundamentally different from an external tool. It becomes a trainable computational substrate that can be integrated directly into a larger model.
IMHO the key point at which this technique has an unfair advantage vs a traditional interpreter is here.
How disruptive is it to have differentiability? To me it would mean that some tweaking-around can happen in an LLM-program at train-time; like changing a constant, or switching from a function call to another function. Can we gradient-descent effectively inside this huge space? How different is it from tool-calling from a pool of learned programs (think github but for LLM programs written in classic languages)?
Re: Executing programs inside transformers with exponentially faster inference
#47The Percepta stuff would seem to demonstrate a mechanism for implementing "thinking". I don't understand how foundation models implement "thinking", but my intuition is that models are specifically trained for matching on and following procedural patterns. A task in a given domain can be performed through an associated and encoded procedure. The model holds all the linkages, as weights, that allows a procedure to be conditionally incrementally generated and performed. Does anyone have any insights about how LLM "thinking" is trained and coded?
Re: Executing programs inside transformers with exponentially faster inference
#48This shows the downside of using AI to write up your project. I see the eloquent sentences, but don't get the message. > This works, but the actual execution happened outside the model. The model specified the computation, then waited for an external system to carry it out. > Our transformer also emits a program, but instead of pausing for an external tool, it executes that program itself, step by step, within the sa…
> Is it speed? > Is it that you can backprop through this computation? Do you do so? With respect, I feel that you may not have read the article. > Because the execution trace is part of the forward pass, the whole process remains differentiable: we can even propagate gradients through the computation itself. That makes this fundamentally different from an external tool. It becomes a trainable computational substrate…
I read the article and had the same question. It's written in such a way that it feels like it's answering these questions without actually doing so.
The right thing to benchmark against isn't a regular transformer, it's a transformer that writes programs that are then interpreted. They have a little visual demo where it looks faster but only because they make Python absurdly slow, and it's clearly not meant to be a real benchmark.
I spent the whole article thinking, wow, cool, but also ... how is this better than an LLM steering a regular computer? The closest we get is a statement about the need to "internalize what computation is" which doesn't say anything to me.
Fundamentally, running actual instructions on a real CPU is always going to be faster than running them via a neural network. So the interesting part is where they say you can backprop through it, but, ok, backprop is for cases where we don't know how to encode a function using strict logic. Why would you try and backprop through a Sudoku solver? It's probably my imagination is just limited but I could have used more on that.
Re: Executing programs inside transformers with exponentially faster inference
#49The Percepta stuff would seem to demonstrate a mechanism for implementing "thinking". I don't understand how foundation models implement "thinking", but my intuition is that models are specifically trained for matching on and following procedural patterns. A task in a given domain can be performed through an associated and encoded procedure. The model holds all the linkages, as weights, that allows a procedure to be…
Basically just madlibs - the models generate intermediate tokens that help predict a better answer based on training (RLHF & otherwise). They tend to look like "reasoning" because those tokens correlated with accepted answers during training.
Extended thinking passes are just more of the same. The entire methodology exists merely to provide additional context for the autoregression process. There is no traditional computation occurring
Re: Executing programs inside transformers with exponentially faster inference
#50Earlier quoted context omitted.
Why must models be analogous to humans using tools? Or to take the analogy route further wouldn't it be better if humans had calculators built into their brains, provided they are determisitic and reduce latency
Because it is directly analogous. Neural nets (whether biological or artificial) are not the best way to execute lots of deterministic computations quickly and reliably. That's why we invented computers. I'm not convinced at all that this is the best way to reduce latency; there are many other ways of doing that. Having a calculator in our brains would be handy of course, but a gigahertz multi core computer is still…
Exactly. They've implemented a VM inside a transformer, turned an O(1) memory access call into O(n), optimized it down to O(log n) and wrote a post about how smart they are.
It's a nice bit of engineering, if you don't subscribe to YAGNI. If you do, you must ask the obvious question of what capability this delivers that wasn't available before. The only answer I've got is that someone must have been a bit chilly and couldn't figure out the thermostat