> Can you please explain how we can discern that GPT-2 in this instance really built a model of the board?

Read the article. It's very clear. To quote it:

"Next, I wanted to see if my model could accurately track the state of the board. A quick overview of linear probes: We can take the internal activations of a model as it’s predicting the next token, and train a linear model to take the model’s activations as inputs and predict board state as output. Because a linear probe is very simple, we can have confidence that it reflects the model’s internal knowledge rather than the capacity of the probe itself."

If the article doesn't satisfy your curiosity, you can continue with the academic paper it links to: https://arxiv.org/abs/2403.15498v2

See also Anthropic's research: https://www.anthropic.com/research/mapping-mind-language-mod...

If that's not enough, you might explore https://www.amazon.com/Thought-Language-Lev-S-Vygotsky/dp/02...

or https://www.amazon.com/dp/0156482401 to better connect language and world models in your understanding.

Check out Language in Thought and Action, written by an immigrant to Canada who worked his way up to being a US Senator.

http://www.amazon.com/Language-Thought-Action-Fifth-Edition/...

Highly recommend this book:

http://www.amazon.com/Language-Thought-Action-Fifth-Edition/...

Which talks in detail about the "informative" and "affective" connotations of words (it's a lot more entertaining than it sounds). Only slightly related, but I was just reading in the book how we have the terms "light meat" and "dark meat": because ladies and gentleman in 19th century Britain couldn't bring themselves to say "leg", "thigh" or "breast" – even of a chicken!

I've read Impro and it's a great book.

There is another book that I want to recommend to other Hacker News readers and that is 'Language in Thought and Action' by S.I. Hiyakawa[0]. Honestly, reading that changed my life.

[0] http://www.amazon.com/Language-Thought-Action-Fifth-Edition/...

Hey man the argument you seem to be a part of here (both sides) seems really dualistic and considering how poorly concepts and events in real life fit binary interpretations, I think you could reduce your stress by taking a broader approach.

Book I loved on the subject: http://www.amazon.com/Language-Thought-Action-Fifth-Edition/...

If you liked this list, you might be interested in:

Language in Thought and Action http://www.amazon.com/Language-Thought-Action-S-I-Hayakawa/d... by S I Hayakawa http://en.wikipedia.org/wiki/SI_Hayakawa)

The Art of Conversation http://www.basicincome.com/bp/artofconv.htm

And Ben Franklin's Autobiography http://www.gutenberg.org/ebooks/148