The Creators of Baldur's Gate 3 Clarifies Its Implementation of Machine Learning for Next Project

The developer behind popular role-playing games like Baldur's Gate 3 and Divinity: Original Sin recently teased its upcoming project, creating a wave of excitement within the player base. However, follow-up statements from the studio's co-founder have introduced nuance to the conversation, addressing the studio's approach toward machine learning.

Augmenting Workflows, Not Cutting Jobs

In a latest statement, the studio's founder explained that the developer is employing machine learning for specific preliminary purposes. These encompass enhancing PowerPoint slides, generating initial artistic references, and drafting placeholder dialogue.

Importantly, Vincke emphasized that the end assets in the game will be crafted exclusively by real artists. "Our team is writing everything in-house," he stated.

Larian is continuously expanding our team of writers and are busily putting together writing teams.

Given that this area is being explicitly mentioned — we presently have over twenty concept artists and have roles to fill for more artists.

All our efforts we do is incremental and aimed at having people spend greater focus on making content.

Any machine learning application applied correctly is additive to a artist's workflow, not a replacement for their craft.

Addressing Concerns and Clarifying the Vision

The news of using AI originally sparked concern among a segment of the fanbase. In response, Vincke provided additional clarification on online platforms.

"At Larian, we employ machine learning to gather inspiration, similar to we use search engines and reference books," he stated. "In the conceptual brainstorming phase we use it as a simple sketch for composition which we then swap out with original artwork."

He added, "We've hired talent for their unique talent, not for their ability to execute what a AI generates."

Focused Uses for Machine Learning

Vincke had previously detailed the company's practical strategy to this technology, categorizing its use into primary functions:

• Streamlining Repetitive Work: This encompasses refining animations, voice editing, and technical processes like adapting animations for different models.
• Fast-Tracked Experimentation: Using tools to quickly build rough versions of gameplay ideas to test concepts before full implementation.
• Long-Term Aspirations: Investigating how machine learning could eventually create innovative player agency, specifically in simulating dynamic reactions in a vast role-playing world.

He explicitly affirmed that core creative domains — such as writing — are not fields where the studio is cutting creative input. On the contrary, Larian is recruiting more in these precise positions.

"Larian is not releasing a game with machine-made assets, and we are certainly not planning on cutting creatives to swap them out with artificial intelligence," Vincke stated definitively.