The Creators of Baldur's Gate 3 Details Its Implementation of Machine Learning for New Project

The developer behind acclaimed RPGs like Baldur's Gate 3 and Divinity: Original Sin just teased its upcoming project, creating immense excitement within the industry. However, recent comments from the company's lead designer have introduced clarity to the discussion, addressing the studio's philosophy toward AI tools.

AI as a Creative Assistant, Not a Substitute

In a recent statement, Swen Vincke detailed that the team is employing generative AI for particular supporting tasks. These involve fleshing out presentation materials, generating initial visual ideas, and drafting draft text.

Crucially, Vincke emphasized that the shipping material in the game will be authored entirely by real writers. "Larian is writing everything in-house," he said.

Our studio is continuously expanding our team of storytellers and are currently forming writing teams.

Since visual development is being particularly mentioned — we presently have twenty-three visual developers and have job openings for more creatives.

Everything we do is additive and designed to having people spend greater focus on the creative process.

Any machine learning application implemented properly is supplementary to a artist's workflow, not a substitute for their skill.

Responding to Feedback and Defining the Path

The news of using AI originally generated concern among portions of the fanbase. In reply, Vincke offered further elaboration on public forums.

"We use machine learning to gather inspiration, just like we use search engines and reference books," he stated. "During the conceptual ideation stages we use it as a basic framework for layout which we then swap out with hand-crafted illustrations."

He continued, "Our studio recruits talent for their inherent skill, not for their willingness to replicate what a algorithm proposes."

Focused Uses for Machine Learning

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

• Streamlining Repetitive Work: This includes motion capture cleaning, voice editing, and Larian-specific work like retargeting animations.
• Fast-Tracked Experimentation: Using systems to speedily create basic mock-ups of mechanics to validate concepts prior to complete implementation.
• Experimental Frontiers: Exploring how machine learning could in the future facilitate new forms of reactivity, especially in managing unforeseen permutations in a vast role-playing world.

He clearly affirmed that core creative domains — including visual art — are are absolutely not departments where the team is replacing human involvement. On the contrary, Larian is actively hiring in these very roles.

"We are neither launching a game with machine-made assets, nor planning on reducing creatives to swap them out with artificial intelligence," Vincke stated definitively.