Ubisoft is one of the biggest names on the gaming scene and has been riding high on the success of Assassin's Creed: Origins. Now, as the game studio prepares for the release of Far Cry 5, the company has shared with us some information about the AI used to predict bugs in a game's code that comes as a boon to developers.

Ubisoft has changed the testing process for new games, allowing artificial intelligence algorithms to do the heavy lifting, allowing developers to focus on fixing bugs rather than finding them.

Dubbed the Commit Assistant, Ubisoft says it fed the AI with over 10 years of code from across its software library and enabled the system to learn where mistakes have historically been made. The system also referenced any patches applied to games post-release. It uses this data to predict when a developer might make a similar mistake in new code.

In addition to Commit Assistant, Ubisoft is also focusing on AlphaGo, the AI system they have embedded in their games. Ubisoft explained how their AI works in their previous game, Watch Dogs 2. Using an example of a non-player-controlled car driving around the game's virtual San Francisco, Olivier Delalleau, an AI programmer at Ubisoft, showed how it initially would more often careen out of control when cornering. The car was programmed with the goal of reaching a destination or going around the streets, giving a visual flavor to the game world. Later, the team used augmented machine learning to train the AI. Cars effectively learned how to take corners smoothly using effective braking, making Watch Dogs 2's representation of San Francisco more realistic and reducing random crashes.