Larian Studios Explains Its Implementation of Machine Learning for New Divinity

The studio behind popular titles like Baldur's Gate 3 and Divinity: Original Sin has recently shown its upcoming project, creating significant anticipation within the gaming community. However, subsequent comments from the studio's figurehead have brought a new dimension to the discussion, focusing on the team's philosophy toward AI tools.

A Tool for Ideation, Not Replacement

In a recent message, the studio's founder outlined that the team is using machine learning for particular supporting purposes. These involve enhancing presentation materials, producing early-stage artistic references, and creating temporary dialogue.

Crucially, Vincke stressed that the shipping content in the game will be authored entirely by real creatives. "Larian is developing everything ourselves," he said.

Our studio is continuously increasing our pool of concept artists and are busily forming narrative groups.

Since visual development is being explicitly called out — we currently have twenty-three artistic staff and have positions available for more artists.

Each initiative we do is additive and designed to enabling creatives to spend additional energy on actual creation.

Any ML tool used well is additive to a artist's process, not a substitute for their skill.

Tempering Reactions with Clear Intent

The revelation of employing this technology at first provoked unease among portions of the player base. In reply, Vincke provided additional clarification on public forums.

"At Larian, we employ machine learning to research ideas, in the same way we use Google and art books," he explained. "In the initial brainstorming phase we use it as a simple sketch for composition which we then substitute with original illustrations."

He noted, "We've hired artists for their unique talent, not for their ability to replicate what a machine suggests."

Key Areas of AI Integration

Vincke had earlier detailed the company's practical method to this technology, defining its use into three main functions:

• Streamlining Repetitive Work: This encompasses motion capture cleaning, dialogue cleanup, and Larian-specific work like retargeting animations.
• Fast-Tracked Experimentation: Using tools to speedily create basic mock-ups of mechanics to test concepts ahead of full development.
• Long-Term Aspirations: Exploring how machine learning could eventually enhance new forms of reactivity, specifically in managing unforeseen permutations in a complex RPG.

He explicitly affirmed that central narrative domains — such as visual art — are not areas where the company is replacing human involvement. Conversely, Larian is expanding its staff in these very positions.

"We are neither launching a game with AI-generated content, nor looking at cutting creatives to replace them with artificial intelligence," Vincke concluded.