What would an adventure game designed by the worlds most dangerous A.I. look like? A neuroscience grad student is here to help you find out. Earlier this year, OpenAI, an A.I. startup once sponsored by Elon Musk, created a text-generating bot deemed too dangerous to ever release to the public. Called GPT-2, the algorithm was designed to generate text so humanlike that it could convincingly pass itself off as being written by a person. Feed it the start of a newspaper article, for instance, and it would dream up the rest, complete with imagined quotes.
On Friday night, at Albert Park, in San Rafael, California, the Sonoma Stompers ran on to the pitching mound, hugged one another, laughed, and sprayed champagne. Jose Flores, their six-foot-four closer, had just sailed a fastball by the San Rafael Pacifics slugger Brent Gillespie, leaving the bases loaded and preserving the team's 5–4 victory. With it, the Stompers claimed the Pacific Association title. Five hundred and ninety-two fans were on hand to watch. Few baseball fans have heard of the tiny Pacific Association, an independent league founded in 2013.
ZDNet editor Jason Hiner spoke with Wendi Whitmore, Global Lead for IBM's Incident Response Team, at this year's RSA Conference. Jason Hiner: Welcome back to RSAC TV. And with me this time, I've got a very special guest, Wendi Whitmore from IBM. Wendi, welcome. And why don't you talk a little bit about what you do at IBM. So Jason, I lead a team at IBM called X-Force IRIS, which is our Incident Response and Intelligence Services team.
We've seen people turn neural networks to almost everything from drafting pickup lines to a new Harry Potter chapter, but it turns out classic text adventure games may be one of the best fits for AI yet. This latest glimpse into what artificial intelligence can do was created by a neuroscience student named Nathan. Nathan trained GPT-2, a neural net designed to create predictive text, on classic PC text adventure games. Inspired by the Mind Game in Ender's Game, his goal was to create a game that would react to the player. Since he uploaded the resulting game to a Google Colab notebook, people like research scientist Janelle Shane have had fun seeing what a text adventure created by an AI looks like.
Interactive fictions, or text-adventures, are games in which a player interacts with a world entirely through textual descriptions and text actions. Text-adventure games are typically structured as puzzles or quests wherein the player must execute certain actions in a certain order to succeed. In this paper, we consider the problem of procedurally generating a quest, defined as a series of actions required to progress towards a goal, in a text-adventure game. Quest generation in text environments is challenging because they must be semantically coherent. We present and evaluate two quest generation techniques: (1) a Markov chains, and (2) a neural generative model. We specifically look at generating quests about cooking and train our models on recipe data. We evaluate our techniques with human participant studies looking at perceived creativity and coherence.