This website contains age-restricted materials including nudity and explicit depictions of sexual activity.
By entering, you affirm that you are at least 18 years of age or the age of majority in the jurisdiction you are accessing the website from and you consent to viewing sexually explicit content.
But then the AI just looks up the definition of 13, and the definition of 7, and should be able to answer anyhow. I mean, this is how computers work. Are you sure that’s what the other commenter was refering to?
That’s when you get into more of the nuance with tokenization. It’s not a simple lookup table, and the AI does not have access to the original definitions of the tokens. Also, tokens do not map 1:1 onto words, and a word might be broken into several tokens. For example “There’s” might be broken into “There” + “'s”, and “strawberry” might be broken into “straw” + “berry”.
The reason we often simplify it as token = words is that it is the case for most of the common words.
It’s not how AIs specifically work. They’re pretty brain-like, and learn through their experiences during the training process. (Which is also why they’re so hard to consistently control)
It’s possible they still might be able to learn this spelling fact from some bit of their training data, somehow, but they’re at an immense disadvantage.