alt Hacker NewsYeah but not all tokens are created equal. Some tokens are hard to predict and thus encode useful information; some are highly predictable and therefore don't. Spending an entire forward pass through the token-generation machine just to generate a very low-entropy token like "is" is wasteful. The LLM doesn't get to "remember" that thinking, it just gets to see a trivial grammar-filling token that a very dumb LLM could just as easily have made. They aren't stenographically hiding useful computation state in words like "the" and "and".
Replies
> They aren't stenographically hiding useful computation state in words like "the" and "and".
Do you know that is true? These aren’t just tokens, they’re tokens with specific position encodings preceded by specific context. The position as a whole is a lot richer than you make it out to be. I think this is probably an unanswered empirical question, unless you’ve read otherwise.
can you prove this?
train an LLM to leave out the filler words, and see it get the same performance at a lower cost? or do it at token selection time?
>They aren't stenographically hiding useful computation state in words like "the" and "and".
When producing a token the model doesn't just emit the final token but you also have the entire hidden states from previous attention blocks. These hidden states are mixed into the attention block of future tokens (so even though LLMs are autoregressive where a token attends to previous tokens, in terms of a computational graph this means that the hidden states of previous tokens are passed forward and used to compute hidden states of future tokens).
So no it's not wasteful, those low-perplexity tokens are precisely spots that can instead be used to do plan ahead and do useful computation.
Also I would not be sure that even the output tokens are purely "filler". If you look at raw COT, they often have patterns like "but wait!" that are emitted by the model at crucial pivot points. Who's to say that the "you're absolutely right" doesn't serve some other similar purpose of forcing the model into one direction of adjusting its priors.