contains some encoding of the entire (very large) training set
Not just "some" encoding. It is in fact a semantic encoding. Concepts that are semantically close together are also close together in the encoding. It also doesn't find answers from a set. It actually translates its internal semantic concept into words, and this process is guided by flexible requirements.
You can do stuff like tell it to provide the answer in consonants only, or in the form of a song, or pirate speak, even though the training data would barely have any relevant examples.
Not just "some" encoding. It is in fact a semantic encoding. Concepts that are semantically close together are also close together in the encoding. It also doesn't find answers from a set. It actually translates its internal semantic concept into words, and this process is guided by flexible requirements.
You can do stuff like tell it to provide the answer in consonants only, or in the form of a song, or pirate speak, even though the training data would barely have any relevant examples.