The Divinity Developer Details Its Use of Machine Learning for Next Divinity Game

The team behind acclaimed role-playing games like Baldur's Gate 3 and Divinity: Original Sin has recently shown its upcoming project, generating a wave of hype within the player base. However, follow-up statements from the company's lead designer have brought a new dimension to the narrative, touching on the team's philosophy toward AI tools.

AI as a Creative Assistant, Not a Substitute

In a latest message, Swen Vincke outlined that the developer is using generative AI for certain ancillary purposes. These involve fleshing out PowerPoint slides, creating initial concept art, and creating temporary copy.

Importantly, Vincke made clear that the shipping material in the game will be authored exclusively by real creatives. "We are developing everything manually," he said.

Larian is continuously expanding our pool of writers and are actively forming narrative groups.

Since concept art is being explicitly referenced — we currently have twenty-three visual developers and have roles to fill for further talent.

Everything we do is supplementary and focused on letting our team spend additional energy on making content.

Every AI system applied correctly is supplementary to a artist's routine, not a replacement for their craft.

Responding to Feedback and Defining the Path

The revelation of employing this technology at first sparked unease among a segment of the community. In response, Vincke provided further clarification on public forums.

"We use machine learning to research ideas, similar to we use Google and physical media," he wrote. "During the conceptual planning process we use it as a rough outline for layout which we then substitute with original illustrations."

He noted, "We've hired artists for their unique talent, not for their willingness to follow what a algorithm proposes."

Key Areas of AI Integration

Vincke had earlier outlined the team's targeted method to this technology, grouping its use into key areas:

• Automation of Tedious Tasks: This encompasses motion capture cleaning, dialogue cleanup, and pipeline-specific tasks like adjusting assets for various species.
• Fast-Tracked Experimentation: Using technology to rapidly prototype simple versions of scenarios to test concepts before full development.
• Long-Term Aspirations: Investigating how AI could eventually facilitate emergent reactivity, specifically in simulating dynamic reactions in a complex RPG.

He clearly affirmed that central narrative domains — including writing — are not departments where the team is reducing human talent. In fact, Larian is recruiting more in these very positions.

"Our studio is not launching a game with AI-generated content, nor planning on cutting staff to substitute them with AI," Vincke summarized.