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

The developer behind acclaimed role-playing games like Baldur's Gate 3 and Divinity: Original Sin just shown its new project, sparking a wave of excitement within the industry. However, recent statements from the studio's co-founder have introduced a new dimension to the discussion, touching on the studio's stance toward machine learning.

Augmenting Workflows, Not Cutting Jobs

In a new message, the studio's founder detailed that the developer is using machine learning for specific supporting functions. These include fleshing out pitch decks, producing rough concept art, and creating placeholder text.

Crucially, Vincke stressed that the end content in the game will be authored solely by actual creatives. "We are writing all the content in-house," he said.

Our studio is constantly expanding our team of storytellers and are busily assembling writing teams.

Given that this area is being specifically mentioned — we right now have 23 artistic staff and have roles to fill for more creatives.

All our efforts we do is incremental and focused on enabling creatives to spend additional energy on the creative process.

Any AI system applied correctly is supplementary to a artist's routine, never a stand-in for their craft.

Tempering Reactions with Clear Intent

The admission of employing this technology originally sparked unease among portions of the player base. In reaction, Vincke issued additional detail on public forums.

"Our team utilizes AI tools to gather inspiration, similar to we use Google and reference books," he explained. "In the initial planning process we use it as a simple sketch for layout which we then swap out with authentic illustrations."

He noted, "Our studio recruits artists for their inherent skill, not for their capacity to replicate what a algorithm proposes."

Focused Uses for Machine Learning

Vincke had previously broken down the studio's focused strategy to this technology, categorizing its use into primary pillars:

• Streamlining Repetitive Work: Areas like motion capture cleaning, voice editing, and Larian-specific work like adapting animations for different models.
• Fast-Tracked Experimentation: Using technology to speedily create rough mock-ups of scenarios to experiment with concepts before complete production.
• Long-Term Aspirations: Investigating how machine learning could in the future enhance innovative player agency, particularly in managing unforeseen permutations in a vast role-playing world.

He clearly affirmed that key artistic disciplines — like visual art — are not departments where the company is reducing creative involvement. Conversely, Larian is recruiting more in these very roles.

"Our studio is not shipping a game with AI-generated content, nor considering cutting staff to swap them out with AI," Vincke summarized.