So, LLMs face a regression on their latest proposed improvement. It's not surprising considering their functional requirements are:
1) Everything
For the purpose of AGI, LLM are starting to look like a local maximum.
1) Everything
For the purpose of AGI, LLM are starting to look like a local maximum.
I've been saying it since they started popping off last year and everyone was getting euphoric about them. I'm basically a layman - a pretty good programmer and software engineer, and took a statistics and AI class 13 years ago in university. That said, it just seems so extremely obvious to me that these things are likely not the way to AGI. They're not reasoning systems. They don't work with axioms. They don't model reality. They don't really do anything. They just generate stochastic output from the probabilities of symbols appearing in a particular order in a given corpus.
It continues to astound me how much money is being dumped into these things.
1- running the query through a classifier to figure out if the question involves numbers or math 2- Extract the function and the operands 3- Do the math operation with standard non-LLM mechanisms 4- feed back the solution to the LLM 5- Concatenate the math answer with the LLM answer with string substitution.
So in a strict sense this is not very representative of the logical capabilities of an LLM.
This confusion was introduced at the top of the thread. If the argument is "LLMs plus tooling can't do X," the argument is wrong. If the argument is "LLMs alone can't do X," the argument is worthless. In fact, if the argument is that binary at all, it's a bad argument and we should laugh it out of the room; the idea that a lay person uninvolved with LLM research or development could make such an assertion is absurd.
Changing names does not affect the performance of Sota models.
Which figure are you referring to? For instance figure 8a shows a -32.0% accuracy drop when an insignificant change was added to the question. It's unclear how that's "within the margin of error" or "Changing names does not affect the performance of Sota models".
Their errors appear to disappear when you correctly set the context from conversational to adversarial testing — and Apple is actually testing the social context and not its ability to reason.
I’m just waiting for Apple to release their GSM-NoOp dataset to validate that; preliminary testing shows it’s the case, but we’d prefer to use the same dataset so it’s an apples-to-apples comparison. (They claim it will be released “soon”.)
If you want a more scientific answer there is this recent paper: https://machinelearning.apple.com/research/gsm-symbolic
Maybe some HN commenters will finally learn the value of uncertainty then.
https://chatgpt.com/share/6723477e-6e38-8000-8b7e-73a3abb652...
https://chatgpt.com/share/6723478c-1e08-8000-adda-3a378029b4...
https://chatgpt.com/share/67234772-0ebc-8000-a54a-b597be3a1f...
mini's answer is correct, but then it forgets that fathers are male in the next sentence.
More challenging are unconventional story structures, like a mom named Matthew with a son named Mary and a daughter named William, who is Matthew's daughter?
But even these can still be done by the best models. And it is very unlikely there is much if any training data that's like this.
For anyone curious: https://chatgpt.com/share/6722d130-8ce4-800d-bf7e-c1891dfdf7...
> Based on traditional naming conventions, it seems that the names might have been switched in this scenario. However, based purely on your setup:
>
> Matthew has a daughter named William and a son named Mary.
>
> So, Matthew's daughter is William.
- LLMs use fixed resources when computing an answer. And to the extent that they don't, they are function calling and the behaviour is not attributable to the LLMs. For example when using a calculator, it is displaying calculator intelligence.
- LLMs do not have memory, and if they do it's very recent and limited, and distinct from any being so far. They don't remember what you said 4 weeks ago, and they don't incorporate that into their future behaviour. And if they do, the way they train and remember is very distinct from that of humans and relates to it being a system being offered as a free service to multiple users. Again to the extent that they are capable of remembering, their properties are not that of LLMs and are attributable to another layer called via function calling.
LLMs are a perception layer for language, and perhaps for output generation, but they are not the intelligence.
They still lack, as far as we know, a world model, but the results are already eerily similar to how most humans seem to think - a lot of our own behaviour can be described as “predict how another human would reply”.
https://arxiv.org/abs/2210.13382
I'd be more surprised if LLMs trained on human conversations don't create any world models. Having a world model simply allows the LLM to become better at sequence prediction. No magic needed.
There was another recent paper that shows that a language model is modelling things like age, gender, etc., of their conversation partner without having been explicitly trained for it
My understand was that they know how the model was designed to be able to work, but that there's been very little (no?) progress in the black box problem so we really don't know much at all about what actually happens internally.
Without better understanding of what actually happens when an LLM generates an answer I stick with the most basic answer that its simply predicting what a human would say. I could be wildly misinformed there, I don't work directly in the space and its been moving faster than I'm interested in keeping up with.
We argue that representations in AI models, particularly deep networks, are converging. First, we survey many examples of convergence in the literature: over time and across multiple domains, the ways by which different neural networks represent data are becoming more aligned. Next, we demonstrate convergence across data modalities: as vision models and language models get larger, they measure distance between datapoints in a more and more alike way. We hypothesize that this convergence is driving toward a shared statistical model of reality, akin to Plato’s concept of an ideal reality. We term such a representation the platonic representation and discuss several possible selective pressures toward it. Finally, we discuss the implications of these trends, their limitations, and counterexamples to our analysis.
There's nothing wrong with a hypothesis or that process, but it means we still don't know whether models are doing this or not.
There was a paper that shows a model trained on Othello moves creates a model of the board, models the skill level of their opponent and more.
That's how we think. We think sequentially. As I'm writing this, I'm deciding the next few words to type based on my last few.
Blows my mind that people don't see the parallels to human thought. Our thoughts don't arrive fully formed as a god-given answer. We're constantly deciding the next thing to think, the next word to say, the next thing to focus on. Yes, it's statistical. Yes, it's based on our existing neural weights. Why are you so much more dismissive of that when it's in silicon?
The biggest limitation with the current LLMs is the artificial separation between training and inference. Once deployed, they are eternally stuck in the same moment, always reacting but incapable of learning. At best, they are snapshots of a general intelligence.
I also have a vague feeling that a fixed set of tokens is a performance hack that ultimately limits the generality of LLMs. That hardcoded assumptions make tasks that build on those assumptions easier and seeing past the assumptions harder.
So are we, at any given moment.
If so you could have written this as a newborn baby, you are determining these words based on a lifetime of experience. LLMs doesn't do that, every instance of ChatGPT is the same newborn baby while a thousand clones of you could all be vastly different.
We argue that representations in AI models, particularly deep networks, are converging. First, we survey many examples of convergence in the literature: over time and across multiple domains, the ways by which different neural networks represent data are becoming more aligned. Next, we demonstrate convergence across data modalities: as vision models and language models get larger, they measure distance between datapoints in a more and more alike way. We hypothesize that this convergence is driving toward a shared statistical model of reality, akin to Plato’s concept of an ideal reality. We term such a representation the platonic representation and discuss several possible selective pressures toward it. Finally, we discuss the implications of these trends, their limitations, and counterexamples to our analysis.
Human brains are sure big but they are inefficient because a big portion of the brain is going to non-intelligence stuff like running the body internal organs, eye vision, etc…
I do agree that the money is not well spent. They should haver recognized that we are hitting s local maximum with the current model and funding should be going to academic/theoretical instead of dump brute force.
Maybe in our society there's a surprising amount of value of a "word stirrer" intelligence. Sure, if it was confident when it was right and hesitant when it was wrong it'd be much better. Maybe humans are confidently wrong often enough that an artificial version that's compendious experience to draw on is groundbreaking.
Remember the resounding euphoria at the LK-99 paper last year, and how everyone suddenly became an expert on superconductors? It's clear that we've collectively learned nothing from that fiasco.
The idea of progress itself has turned into a religious cult, and what's worse, "progress" here is defined to mean "whatever we read about in 1950s science fiction".
Arguably a second regression, the first being cost, because COT improves performance by scaling up the amount of compute used at inference time instead of training time. The promise of LLMs was that you do expensive training once and then run the model cheaply forever, but now we're talking about expensive training followed by expensive inference every time you run the model.
gpt4o and 4o mini have a tenth and a hundredth of inference cost of gpt4 respectively
A regression that humans also face, and we don't say therefore that it is impossible to improve human performance by having them think longer or work together in groups, we say that there are pitfalls. This is a paper saying that LLMs don't exhibit superhuman performance.
What I'm certain is we should not praise the inventor of ball bearings for inventing flight, nor once ball bearings were invented flight became unavoidable and only a matter of time.