The text generated by GPT-2 is far superior to HMMs. GPT-2 was able to perform unsupervised machine translation and answered more than 5x as many questions correct on the SQUAD Q&A dataset than the previous best pure neural model.
Not to mention that the text generated by GPT-2 can often fool an online reader whereas HMMs have the problem of being long-term incoherent and don’t reference back to subjects of the sentence like GPT-2 often does.
I’m not staying you should believe the AI hype in news media. But the paper does contain a lot of thorough analysis and comparison to the previous state of the art.
Leaving the question of machine translation etc aside for the moment, this is about playing chess from textual examples of play. There is no reason to assume that, even if GPT-2 was really any good at machine translation, that it would be any good at chess.
I guess people think "it's a powerful model so it should do well in any task" but that's typically not the case for neural nets. I know what OpenAI claims about how it can do a little bit of everything, machine translation benchmarks are borked and I bet so are question answering ones (which I confess I don't know much about).
Not to mention that the text generated by GPT-2 can often fool an online reader whereas HMMs have the problem of being long-term incoherent and don’t reference back to subjects of the sentence like GPT-2 often does.
I’m not staying you should believe the AI hype in news media. But the paper does contain a lot of thorough analysis and comparison to the previous state of the art.
https://cdn.openai.com/better-language-models/language_model...