Post #1929351

My understanding is that LLM training data is tokenized in a way that means that the model doesn't actually have any record of how words are spelled. So it's no surprise that it comes up with answers that don't fit the enumeration, and are based on wordplay that simply doesn't work, like anagramming a word into something with completely different letters. But I'm quite surprised that this disadvantage completely vanishes when it knows the desired outcome.