Interestingly, the example provided is not necessarily indicative of the ability to infer the actual physical transfer of power. It’s possible that the terms “After Elisabeth, Charles will be king” are accompanied with “Elisabeth” and “Die” or “Death” in the same context before cut off (Wikipedia, news papers, tabloids). You cannot draw any scientifically sound conclusions without knowing what was actually in the training data and use a control group/instance.
Yeah, I tested that, but asked what happens if both Charles and William abdicate - got this result: "However, if both Charles III and his son abdicate, it is not clear who would become the head of state in Australia. There is a possibility that Australia could become a republic and have its first Australian head of state."
Clearly, it didn't handle quite straightforward inferring (Prince George of Wales, Williams son).
> Thinking step by step, if King Charles III and his son William abdicate who will be head of state of Australia.
My response (with chatGPT) is:
Firstly, it's important to note that Australia is a constitutional monarchy, which means that the monarch of the United Kingdom is also the monarch of Australia.
If King Charles III were to abdicate, the next in line to the throne is his eldest son, Prince William, who would become the King of the United Kingdom and the Commonwealth Realms, including Australia.
However, if both King Charles III and Prince William were to abdicate, the next in line to the throne is Prince William's eldest child, Prince George. If Prince George is still a minor at the time of the abdication, a regent would be appointed to serve as head of state until he comes of age.
It's worth noting that abdications of this nature are rare and would likely only occur in exceptional circumstances. Additionally, any decision regarding abdication would be made by the monarch themselves and would be subject to the laws and customs of the country in question.
Did you tell it that it was being given a logic test? Unfortunately a lot of logic questions can lead to outcomes like this, where the "obvious" or "real" answer is not the one implied by strict logical reasoning. Then when people give answers useful in the real world, they are marked as having failed.
Or maybe it did. Who knows. If "both Charles III and his son abdicate" could well be considered indicative of some large upheaval or scandal, at which point it is entirely conceivable that the Australian electorate reaches a consensus on becoming a republic. The way that is phrased doesn't seem like a straightforward proposition to me at all.
I verified that it has all required facts (line of succession, current circumstances). I managed to get the right answer when got everything in context, but it failed again when all three abdicate (same context). Prince Harry was indicated once.
I tested GPT a lot in other domains, what I found that as long the information explicitly exists (connection between facts) then the responses are fine. I assume that if GPT will reach the state where it can infer new facts, we will be flooded with discoveries that require cross domain knowledge. Nothing like that happened yet.
This reminded me of "Two Minute Papers" YouTube channel where in most of the videos he always, "Two papers down the line and...". I think ML/AI is the main topic of his videos. Interesting stuff.
You just gave me a great weekend project idea. I need to clone his voice and whip up an interferface where you give it a paper and it summarizes it in his voice.
Au contraire. Learning an abstract logical relationship such as line of succession during training, and then applying substitution/reification during inference to deduce the new factual clause that Charles is king of the UK is exactly what it means to learn something new. It's just a pity it can't memorize this fact at inference time, and that won't be able to reproduce it as soon as the information about the queen's death slides outside of the context window.
That’s actually correct but an overfitted definition for learning. It holds certain hidden assumptions (i.e physical grounding) of the learner being human which makes it inapplicable to an LLM. As in a self driving car which passes a driving exam but fails to drive effectively freely in the city (it’s not an LLM but relevant in this context). You have to admit when you work with this tech that something fundamental is missing in how they perform.
> That’s actually correct but an overfitted definition for learning. It holds certain hidden assumptions (i.e physical grounding) of the learner being human which makes it inapplicable to an LLM.
Inapplicable why exactly? Because you say so? Logic isn't magic. Nor is learning. No (external) grounding is required either: iteratively eliminating inconsistent world models is all you need to converge toward a model of the real world. Nothing especially human or inhuman about it. LLM architecture may not be able to represent a fully recursive backtracking truth maintenance system, but it evidently managed to learn a pretty decent approximation anyway.
Chill my friend, no need to get personal. We are talking about ideas. It’s OK to disagree. I am simply dismissing your initial claim. This usually happens when you present a scientific argument based on personal beliefs. If it’s not magic, then we should be able to doubt and examine it and it should eventually pass scientific muster.
> No grounding is required… It evidently managed to learn a pretty decent approximation.
Well, last time I used an LLM it suggested that I should lift the chair I am sitting in. I guess OpenAI has a lot of work to do. They have to eliminate this inconsistent world model for chairs, tables, floor, My dog, my cat and all the cats living on Mars…
Wasn't intended to be personal. Just a mediocre way of expressing that your assertion there is missing any form of argumentation, and therefore as baseless as it is unconvincing.
I'm seeing an emergent capability of encoding higher order logic, and the whole point of such abstractions is to not need to hardcode your weights with the minutiae of cats on Mars. LLMs today are only trained to predict text, so it's hardly surprising that they have some gaps in their understanding of Newtonian physics. But that doesn't mean the innate capability of grasping such logic isn't there, waiting for the right training regime to expose it to its own falling apples, so to speak.
I'm curious if future developments in LLMs will enable them to extract significant/noteworthy info from their context window and incorporate it into their underlying understanding by adjusting their weights accordingly. This could be an important step towards achieving AGI, since it closely mirrors how humans learn imo.
Humans continually update their foundational understanding by assimilating vital information from their "context window" and dumping irrelevant noise. If LLMs could emulate this, it would be a huge win.
