The Divinity Developer Details Its Use of Machine Learning for Upcoming Project

The developer behind acclaimed RPGs like Baldur's Gate 3 and Divinity: Original Sin recently teased its new project, generating immense anticipation within the player base. However, follow-up remarks from the studio's figurehead have brought clarity to the discussion, addressing the team's philosophy toward AI tools.

A Tool for Ideation, Not Replacement

In a latest message, Swen Vincke explained that the developer is using machine learning for certain supporting tasks. These encompass enhancing PowerPoint slides, producing rough concept art, and writing draft dialogue.

Notably, Vincke emphasized that the end material in the game will be authored entirely by real creatives. "Our team is writing everything manually," he said.

We are continuously increasing our team of storytellers and are actively forming dedicated writer rooms.

As this area is being explicitly mentioned — we presently have 23 concept artists and have positions available for more creatives.

Each initiative we do is additive and aimed at letting our team spend greater focus on the creative process.

Any ML tool applied correctly is a boost to a creative team routine, not a replacement for their craft.

Tempering Reactions with Clear Intent

The admission of using AI at first provoked unease among a segment of the community. In reaction, Vincke issued further clarification on public forums.

"We use AI tools to gather inspiration, in the same way we use search engines and art books," he wrote. "During the very early brainstorming phase we use it as a simple sketch for structure which we then swap out with original illustrations."

He noted, "Larian brings on talent for their creative vision, not for their willingness to follow what a machine suggests."

Three Pillars of Practical Application

Vincke had previously detailed the company's focused strategy to machine learning, grouping its use into primary areas:

• Handling Monotonous Jobs: This includes refining animations, dialogue cleanup, and pipeline-specific tasks like adjusting assets for various species.
• Fast-Tracked Experimentation: Using technology to rapidly prototype simple models of gameplay ideas to experiment with concepts prior to expensive implementation.
• Long-Term Aspirations: Investigating how machine learning could eventually enhance new forms of gameplay, especially in creating unforeseen permutations in a detailed game universe.

He clearly affirmed that key artistic areas — including music composition — are are absolutely not fields where the studio is cutting artistic involvement. In fact, Larian is recruiting more in these precise fields.

"We are neither shipping a game with any AI components, and we are certainly not considering cutting teams to substitute them with AI," Vincke concluded.