News for hackers. Stuff that matters.
Re:Do Large Language Models learn world models or just surfa... by shadowofneptune on Sunday January 22, 2023 @02:13AM (#34475143)
The mind itself, perhaps. The person in possession of it though usually does have a conscious strategy to play a game once they are proficient, and can happily explain it to you.
Re:Do Large Language Models learn world models or just surfa... by pyinstallwoes on Sunday January 22, 2023 @02:15AM (#34475149)
How many people can actually explain their state of mind and rational or seemingly rational thought process?
Re:Do Large Language Models learn world models or just surfa... by space_fountain on Sunday January 22, 2023 @02:24AM (#34475187)
And we have all sorts of social science these days implying the explanations when people do try to explain themselves they’re justifying decisions that came out of black box rather than actual describing how the decision happened
Re:Do Large Language Models learn world models or just surfa... by nequo on Sunday January 22, 2023 @02:51AM (#34475318)
And also neuroscience examining whether what we think we did out of choice was really done out of our choice:

https://en.wikipedia.org/wiki/Neuroscience_of_free_will

Re:Do Large Language Models learn world models or just surfa... by taneq on Sunday January 22, 2023 @08:15AM (#34477045)
What do you (or they) think “our choice” is if not the result of these processes? It’s not like “you” are just the past of your brain that is consciously aware of making decisions.
Re:Do Large Language Models learn world models or just surfa... by Tepix on Sunday January 22, 2023 @04:21AM (#34475706)
I play Othello. In most situations i can give you detailed reasons why i choose to make a particular move.
Re:Do Large Language Models learn world models or just surfa... by taneq on Sunday January 22, 2023 @08:46AM (#34477301)
Are they actually the reasons for your move, or are they post-hoc justifications, and how would you know?
Re:Do Large Language Models learn world models or just surfa... by Isinlor on Sunday January 22, 2023 @12:34PM (#34479882)
You are not explaining your internal processes (neurobiology, brain chemistry, neuron firing patterns etc.) that caused you to arrive at given moves. You will only provide proofs that your moves are good.
Re:Do Large Language Models learn world models or just surfa... by bobbruno on Sunday January 22, 2023 @04:47PM (#34482569)
You can justify post facto the move you made. Can you write down the logical process (probably a combination of strategy, move generation, analysis and selection) that would replicate the moves you picked from the beginning of the game? I don’t even need the brain chemistry (the implementation), but I don’t think even writing down the logic that generates those moves (in contrast with a logic to justify each move after it was generated) is something humans can do in most cases.
Re:Do Large Language Models learn world models or just surfa... by bsenftner on Sunday January 22, 2023 @07:51AM (#34476881)
Asking people to explain themselves often triggers various sorts of youth punishment memory, resulting in them being both uncomfortable probing their own reasoning, and then they produce what is essentially a comforting deception for their reasoning simple for the sake of ending the agony of self probing. Asking people their internal states requires their internal guard and internal (potentially filled with self deception) voice what they are up to is very similar to asking children why they are misbehaving, and all manners of mental protections activate.
Re:Do Large Language Models learn world models or just surfa... by gpm on Sunday January 22, 2023 @04:47AM (#34475829)
I strongly disagree with this statement. A good player can usually walk you through the portion of the game tree that they expanded in their head, but the moves they had to think about (expand their mental game tree to include the resulting position) versus the moves they instinctively ruled out is basically inexplicable, and where a lot of the skill lies.

(I'm thinking more chess than othello, since I'm much better at the former, but I assume the thought process is similar)

Re:Do Large Language Models learn world models or just surfa... by ch33zer on Sunday January 22, 2023 @05:25AM (#34476012)
Strongly agree. I'm NOT good at chess, but I still like watching it on YouTube. The explanations that top players give for their moves sound like magic a lot of the time. If they sat down with me for an hour could they explain every step of how they got to their conclusion? I think they could, but I don't think that they'd explain the exact same process they actually went through, which is based on inexplicable heuristic as parent mentioned. Often times at complex decision points in chess players will just say that a move feels better. That feeling can't be explained.
Re:Do Large Language Models learn world models or just surfa... by shadowofneptune on Sunday January 22, 2023 @05:57AM (#34476172)
I have to admit you're right there, now thinking about how I would explain games I play, approaches to tasks, etc.
Re:Do Large Language Models learn world models or just surfa... by jacquesm on Sunday January 22, 2023 @09:02AM (#34477479)
That's not correct. It doesn't matter whether they can explain their moves to you. What matters is if they can explain their moves to another grand master and they always can unless they moved a random piece to break up a position to make a boring game more interesting (this rarely happens, but it is an interesting way to play, but not to win contests).
Re:Do Large Language Models learn world models or just surfa... by Isinlor on Sunday January 22, 2023 @12:32PM (#34479853)
They are not explaining their internal processes (neurobiology, brain chemistry, neuron firing patterns etc.) that caused them to arrive at given moves. They just provide proofs that their moves were good.
Re:Do Large Language Models learn world models or just surfa... by jacquesm on Sunday January 22, 2023 @03:10PM (#34481707)
Works for me. Just like you won't be able to explain to a lay person what a computer program does doesn't mean that the logic is sound without going all the way to the atomic level. But if you really wanted to you could because a computer is a deterministic and relatively simple system, small enough to explain in principle from which we can extrapolate. Wetware doesn't have that luxury so you have the choice to believe the explainer, or not. But when dealing with such a vast gap in experience the best way is to try to learn as much as possible from such an explanation in the hope that you'll be able to capture more of it in the future. This isn't always possible, for instance due to time constraints or interest levels but in principle it could be done.