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

The team behind hit RPGs like Baldur's Gate 3 and Divinity: Original Sin recently teased its new project, creating immense anticipation within the player base. However, follow-up statements from the studio's figurehead have introduced clarity to the narrative, focusing on the developer's stance toward AI tools.

A Tool for Ideation, Not Replacement

In a recent message, Larian's director detailed that the developer is using machine learning for particular supporting purposes. These involve developing presentation materials, producing initial concept art, and drafting placeholder copy.

Crucially, Vincke emphasized that the shipping content in the game will be authored solely by real artists. "We are developing every line manually," he said.

We are actively expanding our team of storytellers and are currently assembling writing teams.

As concept art is being specifically called out — we right now have twenty-three visual developers and have job openings for more artists.

Each initiative we do is supplementary and focused on enabling creatives to spend greater focus on actual creation.

Every AI system applied correctly is additive to a creative team routine, not a replacement for their talent.

Responding to Feedback and Defining the Path

The news of employing this technology at first generated unease among portions of the player base. In response, Vincke issued further clarification on social media.

"Our team utilizes machine learning to gather inspiration, just like we use Google and reference books," he stated. "During the very early brainstorming phase we use it as a basic framework for structure which we then replace with authentic artwork."

He noted, "We've hired creatives for their inherent skill, not for their willingness to replicate what a machine suggests."

Focused Uses for Machine Learning

Vincke had in the past detailed the company's targeted method to AI and ML, defining its use into key functions:

• Automation of Tedious Tasks: This encompasses polishing mocap data, dialogue cleanup, and Larian-specific work like adjusting assets for various species.
• Accelerated Iteration: Using technology to rapidly prototype rough models of scenarios to test concepts before complete production.
• Future Potential for Gameplay: Exploring how machine learning could one day facilitate new forms of reactivity, especially in simulating unforeseen permutations in a detailed game universe.

He specifically affirmed that core creative disciplines — such as visual art — are are in no way areas where the studio is cutting creative involvement. In fact, Larian is expanding its staff in these precise positions.

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