Larian Studios Details Its Implementation of Machine Learning for New Divinity Game

The developer behind acclaimed RPGs like Baldur's Gate 3 and Divinity: Original Sin recently teased its new project, sparking a wave of excitement within the gaming community. However, subsequent statements from the studio's co-founder have brought a new dimension to the discussion, addressing the team's philosophy toward machine learning.

Augmenting Workflows, Not Cutting Jobs

In a new statement, Larian's director detailed that the developer is utilizing AI technology for certain preliminary tasks. These involve developing pitch decks, generating early-stage visual ideas, and creating temporary dialogue.

Crucially, Vincke stressed that the final assets in the game will be authored exclusively by human writers. "Our team is creating every line in-house," he affirmed.

We are constantly expanding our team of writers and are busily forming narrative groups.

As concept art is being specifically called out — we presently have 23 artistic staff and have roles to fill for additional talent.

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

Every ML tool implemented properly is a boost to a developer's process, not a replacement for their talent.

Tempering Reactions with Clear Intent

The revelation of AI usage originally generated unease among portions of the fanbase. In response, Vincke provided further clarification on online platforms.

"We use these tools to gather inspiration, in the same way we use search engines and reference books," he stated. "During the very early planning process we use it as a rough outline for layout which we then swap out with authentic illustrations."

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

Three Pillars of Practical Application

Vincke had in the past outlined the studio's practical approach to this technology, grouping its use into three main functions:

• Automation of Tedious Tasks: Areas like polishing mocap data, audio processing, and pipeline-specific tasks like adjusting assets for various species.
• Accelerated Iteration: Using systems to speedily create basic mock-ups of mechanics to validate concepts ahead of expensive production.
• Long-Term Aspirations: Exploring how machine learning could one day create emergent reactivity, particularly in simulating player-driven narratives in a vast role-playing world.

He explicitly affirmed that key artistic areas — including visual art — are are in no way areas where the team is replacing creative input. Conversely, Larian is actively hiring in these exact roles.

"Our studio is not releasing a game with machine-made assets, nor planning on trimming down creatives to replace them with artificial intelligence," Vincke stated definitively.