Though it would be interesting to run an experiment where you somehow remove all of that from the training data.
Perhaps in 10 years training runs will be cheap enough, that one a whim you could just train a new AI model on data from only before the Pentium was released, and then see if it could come up with it?
Perhaps in 10 years training runs will be cheap enough, that one a whim you could just train a new AI model on data from only before the Pentium was released, and then see if it could come up with it?