The Creators of Baldur's Gate 3 Explains Its Implementation of Generative AI for Next Divinity Game

The studio behind acclaimed RPGs like Baldur's Gate 3 and Divinity: Original Sin has recently shown its new project, creating immense anticipation within the player base. However, recent comments from the studio's lead designer have brought clarity to the conversation, focusing on the developer's philosophy toward generative artificial intelligence.

Augmenting Workflows, Not Cutting Jobs

In a new statement, Larian's director outlined that the developer is utilizing AI technology for certain supporting functions. These encompass fleshing out presentation materials, creating early-stage visual ideas, and drafting temporary copy.

Crucially, Vincke made clear that the shipping assets in the game will be crafted exclusively by human creatives. "Our team is writing every line manually," he said.

Larian is constantly growing our team of storytellers and are busily assembling writing teams.

Given that visual development is being explicitly called out — we presently have over twenty concept artists and have job openings for further creatives.

Everything we do is incremental and designed to letting our team spend greater focus on actual creation.

Every machine learning application implemented properly is supplementary to a developer's process, not a substitute for their talent.

Responding to Feedback and Defining the Path

The revelation of AI usage initially generated backlash among portions of the community. In reply, Vincke issued further elaboration on online platforms.

"At Larian, we employ AI tools to research ideas, in the same way we use the internet and physical media," he stated. "In the very early brainstorming phase we use it as a basic framework for structure which we then replace with hand-crafted artwork."

He added, "We've hired talent for their creative vision, not for their willingness to follow what a algorithm proposes."

Three Pillars of Practical Application

Vincke had previously broken down the studio's practical method to machine learning, grouping its use into key areas:

• Handling Monotonous Jobs: Areas like polishing mocap data, audio processing, and pipeline-specific tasks like adapting animations for different models.
• Fast-Tracked Experimentation: Using technology to rapidly prototype rough versions of gameplay ideas to experiment with concepts prior to full implementation.
• Future Potential for Gameplay: Investigating how machine learning could in the future facilitate new forms of gameplay, specifically in simulating player-driven narratives in a complex RPG.

He explicitly affirmed that core creative domains — including writing — are are in no way areas where the studio is reducing creative involvement. On the contrary, Larian is recruiting more in these very fields.

"Larian is not shipping a game with machine-made assets, nor planning on trimming down staff to swap them out with artificial intelligence," Vincke concluded.