The Creators of Baldur's Gate 3 Clarifies Its Application of Generative AI for Next Divinity Game

The studio behind hit RPGs like Baldur's Gate 3 and Divinity: Original Sin has recently unveiled its next major project, sparking immense anticipation within the industry. However, recent statements from the studio's co-founder have added clarity to the conversation, addressing the team's philosophy toward machine learning.

A Tool for Ideation, Not Replacement

In a recent message, Larian's director outlined that the company is utilizing machine learning for particular ancillary functions. These include developing presentation materials, producing early-stage concept art, and creating temporary dialogue.

Importantly, Vincke emphasized that the end assets in the game will be authored solely by real creatives. "Larian is creating everything manually," he affirmed.

Our studio is constantly growing our pool of concept artists and are actively forming dedicated writer rooms.

As visual development is being specifically referenced — we presently have 23 concept artists and have roles to fill for further artists.

Each initiative we do is incremental and aimed at letting our team spend more time on actual creation.

Any AI system applied correctly is a boost to a creative team process, never a stand-in for their craft.

Responding to Feedback and Defining the Path

The news of employing this technology originally generated backlash among portions of the fanbase. In reaction, Vincke offered more detail on online platforms.

"At Larian, we employ machine learning to gather inspiration, similar to we use Google and reference books," he stated. "During the conceptual brainstorming phase we use it as a simple sketch for composition which we then substitute with hand-crafted concept art."

He continued, "Larian brings on creatives for their inherent skill, not for their ability to replicate what a AI generates."

Focused Uses for Machine Learning

Vincke had previously broken down the company's targeted strategy to AI and ML, grouping its use into three main functions:

• Handling Monotonous Jobs: This encompasses polishing mocap data, dialogue cleanup, and technical processes like adapting animations for different models.
• Rapid Prototyping ('White Boxing'): Using technology to quickly build simple models of scenarios to experiment with concepts ahead of full development.
• Long-Term Aspirations: Exploring how machine learning could one day enhance emergent gameplay, especially in managing player-driven narratives in a complex RPG.

He specifically stated that central narrative areas — such as music composition — are are absolutely not departments where the company is reducing artistic input. In fact, Larian is expanding its staff in these very roles.

"Our studio is neither releasing a game with machine-made assets, nor planning on trimming down staff to replace them with artificial intelligence," Vincke concluded.