You are Thomas, a wizard living in the kingdom of Larion. You have a staff and a spellbook. You finish your long journey and finally arrive at the ruin you've been looking for. You look around and see that it's not much different than when you left it. A few rocks here and there, but nothing out of place. As you approach the ruins, you feel an odd sensation > eat a rock You turn to the nearest rock and begin eating i…
Since it seems the general population is becoming less and less able to read stories or information consisting of more than one thought or layer of abstraction, grammatically reasonable strings of words like these may satisfy plenty of people. Indeed, modern television and televised "news" seems to be no more impressive than this. But to me, this makes very little sense. It almost connects, but probably only because…
That's still not enough, and GPT-2 in particular has been heavily overhyped, with fanciful claims that people might use it to generate fake news. (What would the point of that be? You don't need N fake news articles to reach N people, only one, which can be written by a human.)
But it's progress. GPT-2 still feels like science fiction to me. What if a future text generator, maybe even one or two decades down the line, surpasses GPT-2 to the same extent that GPT-2 surpasses the earlier attempts I mentioned? What if that system extends the length of coherence to reliably cover entire articles and essays? What if it gets better at synthesizing the information about the world represented by its training data, so that its output on nonfiction prompts is factually true, rather than mere plausible-sounding nonsense? Is it possible? Perhaps not. But it seems a lot more likely to me now than it did before GPT-2 was created.