The Divinity Developer Explains Its Use of Machine Learning for Upcoming Divinity Game

The studio behind popular RPGs like Baldur's Gate 3 and Divinity: Original Sin recently teased its upcoming project, sparking immense excitement within the industry. However, follow-up statements from the company's figurehead have brought a new dimension to the narrative, addressing the studio's philosophy toward AI tools.

A Tool for Ideation, Not Replacement

In a latest message, Larian's director outlined that the developer is employing machine learning for certain supporting functions. These include enhancing PowerPoint slides, producing initial artistic references, and creating draft text.

Notably, Vincke emphasized that the shipping assets in the game will be created entirely by real writers. "We are creating every line ourselves," he stated.

Larian is constantly expanding our pool of concept artists and are actively assembling writing teams.

Since this area is being specifically mentioned — we presently have 23 visual developers and have job openings for additional creatives.

Everything we do is additive and aimed at letting our team spend greater focus on making content.

Any ML tool implemented properly is supplementary to a artist's process, not a replacement for their craft.

Addressing Concerns and Clarifying the Vision

The revelation of using AI at first provoked backlash among a segment of the player base. In reaction, Vincke issued more elaboration on online platforms.

"We use machine learning to gather inspiration, in the same way we use search engines and physical media," he explained. "In the conceptual brainstorming phase we use it as a simple sketch for composition which we then replace with hand-crafted artwork."

He noted, "Larian brings on artists for their unique talent, not for their willingness to execute what a algorithm proposes."

Focused Uses for Machine Learning

Vincke had in the past detailed the company's practical method to AI and ML, categorizing its use into key pillars:

• Handling Monotonous Jobs: Areas like polishing mocap data, audio processing, and technical processes like retargeting animations.
• Rapid Prototyping ('White Boxing'): Using systems to quickly build rough mock-ups of gameplay ideas to experiment with concepts prior to complete production.
• Experimental Frontiers: Researching how machine learning could one day facilitate emergent player agency, especially in simulating player-driven narratives in a vast role-playing world.

He specifically affirmed that core creative areas — like writing — are are in no way departments where the company is cutting human involvement. In fact, Larian is recruiting more in these precise roles.

"Larian is neither releasing a game with AI-generated content, and we are certainly not looking at cutting teams to substitute them with AI," Vincke concluded.