Comment by epistasis

2 days ago

The LLM produces a probability distribution over the likelihood of all possible next tokens. So whatever the tokens are, "ch", "ex", etc. the next one gets a probability.

During training, real life text is fed through the LLM, and rhe "correct" token is the one actually observed in the training text. Here's a recent video walkthrough in some detail, mostly aimed at providing a deeper understanding than "next token predictor function":

https://youtu.be/GlYgs6v2YfU?is=IxVMhoCCE4N4WRVK

(Start at 15:30 for the LLM specific parts)

4 comments

epistasis

Reply
Sprotch  2 days ago

Thanks - that makes sense. On that basis the article’s thesis is totally wrong - it would be like a computer program rating its ability based on how well it predicts moves played by grandmasters in the past. It’s not inventing new moves.

  • epistasis  1 day ago

    I wouldn't necessarily say that. Anybody who's playing a chess game is predicting their next move, whether or not they're inventing new moves.

    LLMs are not simple things like a Markov model, there's a lot going on in there, it's not deterministic, and it's completely capable of creating entire new styles of play based on complex interactions of internal states.