The Creators of Baldur's Gate 3 Explains Its Implementation of Machine Learning for Next Divinity
The studio behind popular RPGs like Baldur's Gate 3 and Divinity: Original Sin just unveiled its next major project, sparking significant anticipation within the industry. However, subsequent statements from the studio's figurehead have brought nuance to the narrative, focusing on the developer's approach toward AI tools.
A Tool for Ideation, Not Replacement
In a latest message, Swen Vincke detailed that the company is utilizing machine learning for certain supporting purposes. These involve fleshing out PowerPoint slides, generating rough concept art, and creating placeholder text.
Notably, Vincke stressed that the end assets in the game will be authored entirely by actual artists. "Our team is developing every line ourselves," he stated.
Our studio is continuously increasing our team of storytellers and are busily putting together dedicated writer rooms.
Given that concept art is being particularly called out — we currently have twenty-three concept artists and have positions available for additional talent.
Each initiative we do is incremental and designed to having people spend additional energy on actual creation.
Any machine learning application used well is additive to a artist's process, never a stand-in for their skill.
Tempering Reactions with Clear Intent
The admission of AI usage at first sparked concern among some the player base. In reply, Vincke provided more clarification on public forums.
"Our team utilizes machine learning to explore references, similar to we use Google and reference books," he explained. "During the conceptual brainstorming phase we use it as a basic framework for layout which we then swap out with original illustrations."
He continued, "We've hired creatives for their unique talent, not for their willingness to replicate what a machine suggests."
Three Pillars of Practical Application
Vincke had in the past detailed the team's focused approach to this technology, grouping its use into key areas:
- Automation of Tedious Tasks: This includes refining animations, voice editing, and Larian-specific work like adapting animations for different models.
- Fast-Tracked Experimentation: Using tools to quickly build simple mock-ups of gameplay ideas to experiment with concepts before expensive production.
- Future Potential for Gameplay: Researching how machine learning could one day create new forms of gameplay, particularly in managing unforeseen permutations in a detailed game universe.
He explicitly noted that central narrative domains — like writing — are not departments where the studio is reducing artistic talent. On the contrary, Larian is recruiting more in these precise roles.
"Larian is neither releasing a game with any AI components, and we are certainly not considering trimming down staff to swap them out with artificial intelligence," Vincke stated definitively.