News for hackers. Stuff that matters.
Re:Do Large Language Models learn world models or just surfa... by pmontra on Sunday January 22, 2023 @03:51AM (#34475576)
I read the web page and the PDF paper quickly (https://arxiv.org/pdf/2210.13382.pdf) and it seems that there are no examples of the prompts they used. It would be great to see which technique they are using or is it obvious for experts of the field?

It would help with reproducibility too.

Re:Do Large Language Models learn world models or just surfa... by jchmrt on Sunday January 22, 2023 @04:16AM (#34475677)
I'm no expert in this field, but as I understand it they trained a new GPT model from scratch to play Othello. So the prompts were simply the transcript of moves that came before.
Re:Do Large Language Models learn world models or just surfa... by Al-Khwarizmi on Sunday January 22, 2023 @04:40AM (#34475796)
Yes, it's that. This model wasn't trained on natural language texts at all, so it can't be "prompted" with sentences like ChatGPT, etc. Lists of Othello moves is all it has seen.