The Creators of Baldur's Gate 3 Explains Its Use of Machine Learning for Next Project

The studio behind hit RPGs like Baldur's Gate 3 and Divinity: Original Sin recently unveiled its new project, generating immense excitement within the player base. However, recent comments from the studio's lead designer have brought a new dimension to the narrative, addressing the studio's philosophy toward AI tools.

AI as a Creative Assistant, Not a Substitute

In a new clarification, Larian's director outlined that the company is employing generative AI for specific preliminary tasks. These encompass enhancing PowerPoint slides, producing initial artistic references, and writing placeholder text.

Crucially, Vincke emphasized that the shipping assets in the game will be created entirely by actual creatives. "We are developing every line manually," he said.

Larian is actively expanding our team of writers and are currently assembling narrative groups.

Since concept art is being particularly mentioned — we presently have over twenty concept artists and have roles to fill for further creatives.

Everything we do is supplementary and aimed at enabling creatives to spend more time on actual creation.

Any machine learning application used well is supplementary to a developer's routine, not a replacement for their craft.

Responding to Feedback and Defining the Path

The news of employing this technology initially provoked backlash among a segment of the fanbase. In reply, Vincke issued further clarification on social media.

"We use AI tools to research ideas, just like we use Google and art books," he stated. "During the conceptual brainstorming phase we use it as a simple sketch for layout which we then substitute with hand-crafted illustrations."

He added, "Our studio recruits creatives for their creative vision, not for their ability to execute what a algorithm proposes."

Focused Uses for Machine Learning

Vincke had previously broken down the company's focused method to AI and ML, defining its use into primary areas:

• Automation of Tedious Tasks: Areas like motion capture cleaning, dialogue cleanup, and technical processes like retargeting animations.
• Fast-Tracked Experimentation: Using systems to rapidly prototype basic versions of gameplay ideas to experiment with concepts prior to expensive development.
• Experimental Frontiers: Researching how machine learning could one day facilitate emergent player agency, especially in managing player-driven narratives in a detailed game universe.

He explicitly affirmed that key artistic disciplines — including music composition — are are absolutely not areas where the team is reducing artistic talent. In fact, Larian is expanding its staff in these precise fields.

"We are neither releasing a game with AI-generated content, and we are certainly not looking at reducing teams to replace them with artificial intelligence," Vincke summarized.