The Creators of Baldur's Gate 3 Explains Its Implementation of Machine Learning for New Divinity

The studio behind popular titles like Baldur's Gate 3 and Divinity: Original Sin just unveiled its new project, creating significant excitement within the gaming community. However, follow-up statements from the studio's co-founder have brought a new dimension to the discussion, touching on the studio's approach toward machine learning.

Augmenting Workflows, Not Cutting Jobs

In a latest statement, Swen Vincke detailed that the team is using machine learning for specific preliminary tasks. These include developing PowerPoint slides, generating early-stage artistic references, and drafting placeholder text.

Importantly, Vincke emphasized that the shipping assets in the game will be authored exclusively by human writers. "Our team is creating every line ourselves," he affirmed.

We are constantly increasing our pool of storytellers and are currently assembling narrative groups.

Since this area is being particularly called out — we presently have twenty-three visual developers and have roles to fill for more artists.

Each initiative we do is incremental and aimed at enabling creatives to spend more time on actual creation.

Every ML tool applied correctly is a boost to a artist's process, not a substitute for their talent.

Tempering Reactions with Clear Intent

The admission of AI usage originally provoked unease among portions of the community. In response, Vincke issued additional clarification on social media.

"At Larian, we employ these tools to gather inspiration, in the same way we use Google and physical media," he stated. "During the conceptual brainstorming phase we use it as a simple sketch for composition which we then replace with authentic artwork."

He noted, "We've hired artists for their inherent skill, not for their ability to execute what a AI generates."

Key Areas of AI Integration

Vincke had previously broken down the studio's practical strategy to this technology, grouping its use into primary areas:

• Handling Monotonous Jobs: Areas like refining animations, dialogue cleanup, and technical processes like adapting animations for different models.
• Rapid Prototyping ('White Boxing'): Using tools to rapidly prototype simple models of gameplay ideas to validate concepts prior to full implementation.
• Future Potential for Gameplay: Researching how machine learning could eventually facilitate innovative gameplay, particularly in managing player-driven narratives in a detailed game universe.

He specifically stated that central narrative disciplines — such as writing — are are absolutely not departments where the company is cutting artistic input. Conversely, Larian is actively hiring in these precise positions.

"Larian is not shipping a game with machine-made assets, and we are certainly not considering reducing creatives to swap them out with AI," Vincke summarized.