The Divinity Developer Explains Its Application of Machine Learning for Next Divinity

The studio behind acclaimed role-playing games like Baldur's Gate 3 and Divinity: Original Sin just unveiled its new project, generating a wave of excitement within the industry. However, follow-up statements from the company's lead designer have brought nuance to the narrative, addressing the team's philosophy toward machine learning.

AI as a Creative Assistant, Not a Substitute

In a recent clarification, Larian's director detailed that the company is using AI technology for specific preliminary purposes. These encompass fleshing out presentation materials, generating early-stage visual ideas, and writing draft dialogue.

Notably, Vincke made clear that the final material in the game will be created exclusively by human creatives. "Our team is writing all the content ourselves," he said.

Larian is constantly increasing our team of concept artists and are actively forming narrative groups.

Given that this area is being specifically called out — we currently have twenty-three visual developers and have positions available for more artists.

All our efforts we do is supplementary and focused on letting our team spend more time on making content.

Any machine learning application applied correctly is supplementary to a artist's routine, not a replacement for their craft.

Responding to Feedback and Defining the Path

The news of employing this technology at first provoked backlash among portions of the community. In response, Vincke offered further clarification on public forums.

"We use these tools to explore references, in the same way we use Google and physical media," he stated. "In the initial planning process we use it as a rough outline for structure which we then swap out with authentic artwork."

He continued, "Larian brings on artists for their inherent skill, not for their willingness to follow what a algorithm proposes."

Focused Uses for Machine Learning

Vincke had earlier outlined the studio's practical approach to machine learning, grouping its use into key functions:

• Handling Monotonous Jobs: Areas like polishing mocap data, voice editing, and technical processes like adjusting assets for various species.
• Rapid Prototyping ('White Boxing'): Using systems to rapidly prototype basic models of mechanics to validate concepts ahead of expensive development.
• Future Potential for Gameplay: Researching how AI could eventually create innovative player agency, particularly in managing dynamic reactions in a complex RPG.

He specifically affirmed that central narrative domains — like writing — are not fields where the studio is replacing creative input. Conversely, Larian is expanding its staff in these precise roles.

"We are neither launching a game with machine-made assets, and we are certainly not considering reducing staff to swap them out with AI," Vincke summarized.