I guess ChatGPT having a model of the world is not something I'd argue against, my mistake. I do think the data it contains represents a quite nuanced model of the world. But I don't think this is a very strong claim. A geographical map has a model of the world too.
Thanks. To get to what I think is the core of your argument (?)
> ChatGPT simply "finds" training data where someone asked a similar question, and produces the likely response, which is an idea that it has actually "heard," or seen in its training data, before.
I can definitely see a scenario where we manage to build an ultra-intelligent machine that can figure out any logical puzzle we put to it, but where it still isn't "creative" in any way.
But GPT-4 seems to be not just intelligent, but also creative.
Have you seen the "confetti has left the cannon" example?
For the curious, here was the conversation I had:
ME: What's another saying similar to: "The cat is out of the bag" or "The genie is out of the bottle"?
chatgpt: Another similar saying is "the toothpaste is out of the tube." Like the other two expressions, this phrase conveys the idea that something has been revealed or unleashed, and it cannot be undone or put back into its original state.
ME: Can you invent a new phrase that has the same meaning, which is completely new?
chatgpt: Certainly! Here's a new phrase with a similar meaning: "The confetti has left the cannon." This phrase suggests that once something is out in the open or has happened, it's impossible to reverse or contain it, much like confetti that has been shot out of a cannon during a celebration.
That does seem really impressive. But don't you think that it's pretty likely that this, or something phrased slightly differently, appeared in the training data?
> But don't you think that it's pretty likely that this, or something phrased slightly differently, appeared in the training data?
I don't think so, but I could be wrong. It's definitely not "likely", see the math below.
I base that on the fact that people seemed to spend quite a bit of time trying to find the phrase "the confetti has left the cannon" that GPT-4 phrased. It seems Google search has no records of it before then?
I've seen many other examples where GPT-4 can translate sentences between using different types of idioms, and I just can't picture all these weird examples already being present on the Internet?
Do you think GPT-4 is a stochastic parrot that just has a large database of responses?
If so, how would we test that claim? What logical and reasoning problems can we give it where it fails to answer, but a human doesn't?
My understanding is that even with an extremely limited vocabulary of 32 words, you quickly run out of atoms in the universe (10^80) if you string more than 50 words together. If your vocabulary instead is 10k words, you reach 10^80 combinations after 20 words.
By training the LLMs on "fill in the missing word", they were forced to evolve ever more sophisticated algorithms.
If you look at the performance over the last 5 years of increasingly larger LLMs, there was a hockey-stick jump in performance 1-2 years ago. My hunch is that is when they started evolving structures to generate better responses by using logic and reasoning instead of lookup tables.
> I base that on the fact that people seemed to spend quite a bit of time trying to find the phrase "the confetti has left the cannon" that GPT-4 phrased. It seems Google search has no records of it before then?
Could it be that the expression in some form has been used in languages other than English?
If that is the case, it would downgrade the achievement from "super impressive" to just "impressive".
I spent some time trying to find it in other languages, but couldn't. Doesn't prove much of course, hopefully native speakers can weigh in on this.
I did find this though:
'TIL that a young stripper named Shelly Bauman lost her leg in a freak confetti cannon accident. She sued and used the money from the settlement to open Seattle's first gay bar, which she named "Shelly's Leg."'
One interesting way I heard to around this is by mixing human languages in the prompt which probably never appear together in any training data, and seeing that chat gpt can do still output sensible replies. That seems to imply that something unique is happening beyond token lookup, if it’s taking different languages and mapping that to the underlying information, that looks a lot more like what people call “understanding”.
Is that a falsifiable claim?
What would an empirical test look like that would determine whether the claim ("GPT-4 does not have a model of the world") is correct or not?