The Creators of Baldur's Gate 3 Explains Its Application of Generative AI for Upcoming Project

The team behind hit titles like Baldur's Gate 3 and Divinity: Original Sin has recently unveiled its new project, sparking immense anticipation within the industry. However, recent statements from the company's lead designer have introduced a new dimension to the conversation, touching on the studio's approach toward machine learning.

AI as a Creative Assistant, Not a Substitute

In a new statement, Swen Vincke detailed that the team is utilizing machine learning for particular preliminary functions. These include enhancing PowerPoint slides, producing early-stage visual ideas, and creating placeholder text.

Importantly, Vincke made clear that the shipping content in the game will be authored solely by actual artists. "We are developing every line manually," he affirmed.

We are continuously growing our team of writers and are actively forming writing teams.

Since visual development is being particularly mentioned — we right now have twenty-three concept artists and have positions available for further creatives.

All our efforts we do is additive and designed to letting our team spend greater focus on the creative process.

Every ML tool implemented properly is supplementary to a creative team routine, never a stand-in for their craft.

Tempering Reactions with Clear Intent

The admission of using AI originally generated concern among some the player base. In reaction, Vincke issued further elaboration on social media.

"We use AI tools to explore references, similar to we use search engines and art books," he stated. "During the very early planning process we use it as a basic framework for composition which we then substitute with authentic concept art."

He continued, "Our studio recruits creatives for their inherent skill, not for their capacity to replicate what a machine suggests."

Focused Uses for Machine Learning

Vincke had earlier outlined the studio's practical approach to machine learning, grouping its use into key functions:

  • Handling Monotonous Jobs: This encompasses polishing mocap data, audio processing, and technical processes like adapting animations for different models.
  • Accelerated Iteration: Using tools to quickly build basic models of scenarios to experiment with concepts prior to complete implementation.
  • Long-Term Aspirations: Investigating how AI could eventually facilitate new forms of gameplay, particularly in creating unforeseen permutations in a vast role-playing world.

He explicitly affirmed that core creative domains — like writing — are are in no way departments where the team is replacing creative involvement. Conversely, Larian is expanding its staff in these very positions.

"We are neither releasing a game with AI-generated content, and we are certainly not considering reducing staff to swap them out with artificial intelligence," Vincke concluded.

Joyce Gomez
Joyce Gomez

Elara is a seasoned betting analyst with over a decade of experience in sports gambling and data-driven strategy development.