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

The studio behind acclaimed role-playing games like Baldur's Gate 3 and Divinity: Original Sin has recently unveiled its next major project, creating significant anticipation within the player base. However, recent remarks from the studio's figurehead have introduced nuance to the discussion, addressing the studio's philosophy toward AI tools.

AI as a Creative Assistant, Not a Substitute

In a new clarification, the studio's founder detailed that the team is utilizing machine learning for particular preliminary tasks. These include fleshing out PowerPoint slides, generating rough concept art, and drafting draft text.

Importantly, Vincke made clear that the end material in the game will be authored entirely by human writers. "Larian is writing everything in-house," he said.

Larian is constantly growing our pool of concept artists and are busily forming dedicated writer rooms.

As concept art is being particularly referenced — we presently have 23 visual developers and have roles to fill for more creatives.

All our efforts we do is additive and focused on having people spend additional energy on actual creation.

Every AI system applied correctly is additive to a developer's process, not a replacement for their talent.

Addressing Concerns and Clarifying the Vision

The news of using AI initially generated unease among some the fanbase. In response, Vincke offered additional detail on public forums.

"We use machine learning to gather inspiration, just like we use search engines and reference books," he explained. "In the initial planning process we use it as a rough outline for structure which we then replace with authentic concept art."

He noted, "We've hired artists for their creative vision, not for their willingness to execute what a algorithm proposes."

Key Areas of AI Integration

Vincke had in the past broken down the team's targeted method to machine learning, categorizing its use into three main functions:

• Handling Monotonous Jobs: This includes motion capture cleaning, dialogue cleanup, and pipeline-specific tasks like adapting animations for different models.
• Fast-Tracked Experimentation: Using tools to speedily create basic mock-ups of gameplay ideas to experiment with concepts before full development.
• Future Potential for Gameplay: Researching how machine learning could one day enhance innovative gameplay, particularly in managing player-driven narratives in a vast role-playing world.

He clearly stated that central narrative domains — including writing — are not departments where the team is cutting human involvement. Conversely, Larian is expanding its staff in these precise roles.

"We are not shipping a game with any AI components, and we are certainly not looking at reducing teams to replace them with artificial intelligence," Vincke concluded.