They Plugged GPT-4 Into Minecraft—and Unearthed New Potential for AI

THE TECHNOLOGY THAT underpins ChatGPT has the potential to do much more than just talk. Linxi “Jim” Fan, an AI researcher at the chipmaker Nvidia, worked with some colleagues to devise a way to set the powerful language model GPT-4—the “brains” behind ChatGPT and a growing number of other apps and services—loose inside the blocky video game Minecraft.

The Nvidia team, which included Anima Anandkumar, the company’s director of machine learning and a professor at Caltech, created a Minecraft bot called Voyager that uses GPT-4 to solve problems inside the game. The language model generates objectives that help the agent explore the game, and code that improves the bot’s skill at the game over time. 

Voyager doesn’t play the game like a person, but it can read the state of the game directly, via an API. It might see a fishing rod in its inventory and a river nearby, for instance, and use GPT-4 to suggest the goal of doing some fishing to gain experience. It will then use this goal to have GPT-4 generate the code needed to have the character achieve it. 

Over time, Voyager builds a library of code in order to learn to make increasingly complex things and explore more of the game. A chart created by the researchers shows how capable it is compared to other Minecraft agents. Voyager obtains more than three times as many items; explores more than twice as far; and builds tools 15 times more quickly than other AI agents. Fan says the approach may be improved in the future with the addition of a way for the system to incorporate visual information from the game.

While chatbots like ChatGPT have wowed the world with their eloquence and apparent knowledge—even if they often make things up—Voyager shows the huge potential for language models to perform helpful actions on computers. Using language models in this way could perhaps automate many routine office tasks, potentially one of the technology’s biggest economic impacts. 

Video games have long been a test bed for AI algorithms, of course. AlphaGo, the machine learning program that mastered the extremely subtle board game Go back in 2016, cut its teeth by playing simple Atari video games. AlphaGo used a technique called reinforcement learning, which trains an algorithm to play a game by giving it positive and negative feedback, for example from the score inside a game. 

It is more difficult for this method to guide an agent in an open-ended game such as Minecraft, where there is no score or set of objectives and where a player’s actions may not pay off until much later. Whether or not you believe we should be preparing to contain the existential threat from AI right now, Minecraft seems like an excellent playground for the technology.