Larian Studios Explains Its Application of AI Tools for Next Project
The team behind acclaimed titles like Baldur's Gate 3 and Divinity: Original Sin just unveiled its new project, sparking immense hype within the player base. However, follow-up remarks from the company's figurehead have introduced a new dimension to the conversation, focusing on the developer's approach toward machine learning.
AI as a Creative Assistant, Not a Substitute
In a latest statement, Larian's director explained that the team is using generative AI for certain preliminary purposes. These include developing presentation materials, creating rough artistic references, and drafting placeholder dialogue.
Importantly, Vincke emphasized that the final assets in the game will be authored exclusively by human artists. "We are writing all the content manually," he affirmed.
Larian is constantly expanding our team of storytellers and are currently putting together dedicated writer rooms.
Since concept art is being explicitly referenced — we right now have 23 artistic staff and have roles to fill for further talent.
Everything we do is incremental and aimed at having people spend additional energy on making content.
Every ML tool implemented properly is a boost to a artist's process, not a substitute for their craft.
Addressing Concerns and Clarifying the Vision
The revelation of employing this technology initially sparked concern among some the fanbase. In reply, Vincke provided further detail on social media.
"We use machine learning to gather inspiration, similar to we use the internet and physical media," he explained. "In the conceptual ideation stages we use it as a basic framework for layout which we then swap out with original artwork."
He noted, "Larian brings on creatives for their inherent skill, not for their capacity to execute what a machine suggests."
Three Pillars of Practical Application
Vincke had earlier outlined the team's practical method to AI and ML, defining its use into key pillars:
- Streamlining Repetitive Work: This encompasses polishing mocap data, voice editing, and pipeline-specific tasks like adapting animations for different models.
- Accelerated Iteration: Using tools to rapidly prototype basic versions of scenarios to test concepts ahead of expensive production.
- Experimental Frontiers: Exploring how machine learning could one day facilitate innovative player agency, especially in creating unforeseen permutations in a detailed game universe.
He clearly stated that central narrative domains — like music composition — are are in no way areas where the team is replacing creative input. Conversely, Larian is actively hiring in these very fields.
"We are not releasing a game with machine-made assets, and we are certainly not looking at reducing teams to substitute them with AI," Vincke concluded.
