GPT-4o being a truly multimodal model is exciting, does open the door to more interesting products. I was curious about the new tokenizer which uses much fewer tokens for non-English, but also 1.1x fewer tokens for English, so I'm wondering if this means each token now can be more possible values than before? Might make sense provided that they now also have audio and image output tokens? https://openai.com/index/hello-gpt-4o/

I wonder what "fewer tokens" really means then, without context on raising the size of each token? It's a bit like saying my JPEG image is now using 2x fewer words after I switched from a 32-bit to a 64-bit architecture no?