>Have you done this test for real? My nephew calls everything which moves but not a human a "dog". In his world there are flying dogs and swimming dogs. Probably if he would see an elephant that would be a big dog, while a giraffe would be a tall dog.
As long as he can tell a "tall dog" (giraffe) apart from a "swimming dog" (say, a duck) that's still compatible with what the parent says.
It's about recognizing them as distict, and assigning them to the same class of things, the rest is just naming, that is, its at the language and vocabulary level, not at the recognition level.
Even if people around the 3-year old child talk to it 16 hours per day constantly at 150 words per minute, they'd just have around 1GB of text in its training data. And not good quality words even, a lot of it would be variations of mundane everyday chit chat and "whose a cute baby?! You're a cute baby!".
For comparison GPT has like 1TB of text, and they're hundreds of thousands of books, articles, wikipedia, and so on. So already 3 orders of magnitude more.
And of course the "16 hours x 150 words per minute x 3 years" is totally off by a few orders of magnitude itself.
As long as he can tell a "tall dog" (giraffe) apart from a "swimming dog" (say, a duck) that's still compatible with what the parent says.
It's about recognizing them as distict, and assigning them to the same class of things, the rest is just naming, that is, its at the language and vocabulary level, not at the recognition level.