The Creators of Baldur's Gate 3 Details Its Application of Generative AI for New Divinity

The team behind acclaimed titles like Baldur's Gate 3 and Divinity: Original Sin recently unveiled its next major project, creating immense anticipation within the player base. However, subsequent remarks from the studio's figurehead have brought clarity to the narrative, touching on the team's approach toward machine learning.

Augmenting Workflows, Not Cutting Jobs

In a new message, Larian's director explained that the team is employing AI technology for certain supporting purposes. These involve developing pitch decks, creating initial concept art, and writing temporary dialogue.

Crucially, Vincke stressed that the shipping material in the game will be crafted solely by human writers. "We are developing everything manually," he affirmed.

Larian is constantly increasing our pool of storytellers and are actively assembling writing teams.

Given that visual development is being particularly called out — we presently have twenty-three concept artists and have roles to fill for additional talent.

All our efforts we do is supplementary and aimed at letting our team spend more time on making content.

Every machine learning application used well is a boost to a developer's process, never a stand-in for their skill.

Addressing Concerns and Clarifying the Vision

The revelation of AI usage at first sparked backlash among some the fanbase. In response, Vincke offered additional clarification on online platforms.

"At Larian, we employ AI tools to gather inspiration, just like we use the internet and reference books," he wrote. "During the very early brainstorming phase we use it as a simple sketch for structure which we then swap out with original concept art."

He continued, "Larian brings on talent for their creative vision, not for their capacity to execute what a algorithm proposes."

Three Pillars of Practical Application

Vincke had earlier outlined the team's targeted method to this technology, grouping its use into primary areas:

• Streamlining Repetitive Work: Areas like polishing mocap data, dialogue cleanup, and technical processes like adjusting assets for various species.
• Accelerated Iteration: Using tools to rapidly prototype rough versions of gameplay ideas to experiment with concepts before expensive implementation.
• Long-Term Aspirations: Researching how machine learning could eventually facilitate emergent player agency, specifically in creating dynamic reactions in a vast role-playing world.

He clearly noted that central narrative disciplines — including writing — are are in no way departments where the team is reducing human involvement. Conversely, Larian is expanding its staff in these very fields.

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