The Creators of Baldur's Gate 3 Explains Its Application of Machine Learning for Next Project

The studio behind acclaimed role-playing games like Baldur's Gate 3 and Divinity: Original Sin has recently shown its new project, generating a wave of excitement within the player base. However, recent remarks from the company's lead designer have introduced nuance to the conversation, focusing on the studio's philosophy toward machine learning.

Augmenting Workflows, Not Cutting Jobs

In a latest statement, Larian's director explained that the company is employing AI technology for certain preliminary purposes. These involve fleshing out pitch decks, generating early-stage concept art, and creating draft text.

Crucially, Vincke emphasized that the final content in the game will be created solely by human creatives. "We are creating all the content manually," he affirmed.

Our studio is actively growing our pool of writers and are currently forming dedicated writer rooms.

As visual development is being particularly mentioned — we presently have twenty-three artistic staff and have roles to fill for further talent.

All our efforts we do is supplementary and focused on having people spend greater focus on actual creation.

Every AI system applied correctly is a boost to a artist's process, not a substitute for their craft.

Responding to Feedback and Defining the Path

The revelation of using AI initially generated unease among a segment of the fanbase. In reply, Vincke provided additional clarification on public forums.

"We use machine learning to gather inspiration, in the same way we use search engines and art books," he explained. "In the initial brainstorming phase we use it as a rough outline for composition which we then replace with original illustrations."

He noted, "Larian brings on artists for their creative vision, not for their ability to follow what a machine suggests."

Three Pillars of Practical Application

Vincke had in the past broken down the team's practical approach to this technology, categorizing its use into primary areas:

• Streamlining Repetitive Work: Areas like motion capture cleaning, audio processing, and Larian-specific work like retargeting animations.
• Accelerated Iteration: Using technology to rapidly prototype basic mock-ups of mechanics to experiment with concepts ahead of expensive production.
• Long-Term Aspirations: Exploring how machine learning could in the future enhance emergent gameplay, especially in simulating player-driven narratives in a detailed game universe.

He specifically stated that central narrative domains — like writing — are are in no way areas where the team is reducing artistic talent. On the contrary, Larian is expanding its staff in these very positions.

"Our studio is not shipping a game with machine-made assets, and we are certainly not planning on trimming down staff to replace them with AI," Vincke concluded.