Larian Studios Details Its Application of Machine Learning for New Divinity
The developer behind acclaimed role-playing games like Baldur's Gate 3 and Divinity: Original Sin recently shown its next major project, creating immense hype within the player base. However, recent statements from the studio's figurehead have added clarity to the discussion, addressing the team's philosophy toward machine learning.
AI as a Creative Assistant, Not a Substitute
In a latest clarification, Larian's director explained that the developer is using generative AI for specific ancillary functions. These involve fleshing out PowerPoint slides, generating early-stage concept art, and drafting draft dialogue.
Notably, Vincke stressed that the shipping content in the game will be crafted exclusively by human artists. "We are developing every line ourselves," he stated.
Larian is continuously increasing our pool of concept artists and are busily forming writing teams.
Given that concept art is being explicitly mentioned — we right now have 23 visual developers and have job openings for more creatives.
Each initiative we do is incremental and aimed at having people spend greater focus on the creative process.
Any AI system applied correctly is supplementary to a artist's routine, not a substitute for their craft.
Addressing Concerns and Clarifying the Vision
The admission of using AI originally provoked unease among some the fanbase. In reply, Vincke offered further clarification on social media.
"At Larian, we employ AI tools to explore references, just like we use the internet and reference books," he explained. "During the conceptual planning process we use it as a basic framework for structure which we then replace with original concept art."
He continued, "We've hired artists for their creative vision, not for their willingness to follow what a algorithm proposes."
Three Pillars of Practical Application
Vincke had earlier broken down the studio's practical approach to machine learning, categorizing its use into primary functions:
- Streamlining Repetitive Work: Areas like polishing mocap data, voice editing, and pipeline-specific tasks like adjusting assets for various species.
- Fast-Tracked Experimentation: Using systems to rapidly prototype basic mock-ups of gameplay ideas to validate concepts prior to full development.
- Experimental Frontiers: Exploring how machine learning could one day create emergent reactivity, particularly in simulating player-driven narratives in a vast role-playing world.
He clearly noted that key artistic disciplines — including visual art — are not fields where the company is cutting artistic involvement. Conversely, Larian is recruiting more in these precise roles.
"Larian is not shipping a game with AI-generated content, and we are certainly not considering trimming down teams to substitute them with AI," Vincke summarized.
