Declarative knowledge is not the same as procedural knowledge. You can read as many chess tutorials, strategy documentation and game archives as you like, they won't make you good at chess until you actually start practicing chess.
The issue with the models isn't that they play a bad game, but that they persist in making illegal moves. An average intelligent human can be told the rules of chess and then play chess, badly, within the rules.
My point was you are misunderstanding G, or at least applying it erroneously here. Being good at chess is not a generalization of any other body of knowledge, it is a rigorous set of rules. The only way to be good at chess is to practice chess, or to apply deep calculations. The latter is the model writing code.
The illegal move aspect has more to do with a failure of online/in-context learning, which would support your point. I tend to think it is a byproduct of reasoning in language, which newer architectures would fix, but we shall see.
If you read all chess tutorials, strategy documentation and game archives on the internet and then would still suck at chess: yes.
Declarative knowledge is not the same as procedural knowledge. You can read as many chess tutorials, strategy documentation and game archives as you like, they won't make you good at chess until you actually start practicing chess.
Does practical improvement apply to only humans or intelligence in general?
The issue with the models isn't that they play a bad game, but that they persist in making illegal moves. An average intelligent human can be told the rules of chess and then play chess, badly, within the rules.
is that what I'm saying? or am I talking about AGI? perhaps there's some irony here to be explored when it comes to basic reading comprehension gaps
My point was you are misunderstanding G, or at least applying it erroneously here. Being good at chess is not a generalization of any other body of knowledge, it is a rigorous set of rules. The only way to be good at chess is to practice chess, or to apply deep calculations. The latter is the model writing code.
The illegal move aspect has more to do with a failure of online/in-context learning, which would support your point. I tend to think it is a byproduct of reasoning in language, which newer architectures would fix, but we shall see.
That's a polite way to put it. :-)