The Divinity Developer Explains Its Application of Machine Learning for Next Divinity Game
The team behind hit titles like Baldur's Gate 3 and Divinity: Original Sin recently teased its new project, creating immense anticipation within the gaming community. However, follow-up remarks from the company's lead designer have introduced nuance to the conversation, touching on the developer's approach toward machine learning.
AI as a Creative Assistant, Not a Substitute
In a new message, Larian's director explained that the company is using generative AI for particular supporting functions. These involve enhancing PowerPoint slides, creating rough visual ideas, and creating draft dialogue.
Crucially, Vincke emphasized that the final assets in the game will be crafted entirely by human artists. "Our team is writing all the content in-house," he stated.
Our studio is continuously increasing our pool of writers and are actively assembling writing teams.
Since visual development is being specifically mentioned — we currently have twenty-three artistic staff and have positions available for further creatives.
All our efforts we do is supplementary and designed to having people spend additional energy on making content.
Every ML tool applied correctly is supplementary to a creative team process, not a replacement for their skill.
Responding to Feedback and Defining the Path
The news of employing this technology at first generated backlash among a segment of the community. In response, Vincke issued additional elaboration on online platforms.
"We use AI tools to explore references, in the same way we use search engines and reference books," he wrote. "In the conceptual ideation stages we use it as a basic framework for structure which we then swap out with original illustrations."
He continued, "Our studio recruits talent for their inherent skill, not for their ability to replicate what a machine suggests."
Focused Uses for Machine Learning
Vincke had previously broken down the studio's focused method to AI and ML, defining its use into three main pillars:
- Automation of Tedious Tasks: Areas like polishing mocap data, dialogue cleanup, and pipeline-specific tasks like adapting animations for different models.
- Rapid Prototyping ('White Boxing'): Using technology to rapidly prototype simple models of mechanics to validate concepts prior to complete development.
- Future Potential for Gameplay: Researching how machine learning could eventually facilitate emergent reactivity, especially in simulating player-driven narratives in a detailed game universe.
He clearly stated that core creative areas — like writing — are are absolutely not fields where the company is cutting creative talent. In fact, Larian is actively hiring in these very positions.
"We are neither releasing a game with any AI components, and we are certainly not considering reducing staff to substitute them with artificial intelligence," Vincke summarized.
