alt Hacker Newscounting 'r' in 'raspberry' to the LLM is similar to 4-dimension space to human. Their world's unit is token, not character, although they could use indirect method such as "run code" to find out. It will stay that way until they change the fundamental of the token that the LLM can perceive characters.
Replies
I’m working on this problem using a vocab-free, byte-based approach. It’s definitely solvable.
How many 'r's are there in the next 30 seconds of this [1] song?
It's not even fair to call "run code" to be indirect compared to what a human would do. The word raspberry has no Rs in it in human language either. We have a written representation of it, which we can then write down either in our head or on paper, and then we can "run the algorithm" of counting each of the letters.
Nothing intrinsically more or less direct about the LLM's method than ours.
I hope you understand: it is a core point that systems that answer questions must have the ability to internally represent the objects they assess in a way that allows reliability. Whatever the object.