The Divinity Developer Details Its Implementation of Machine Learning for New Divinity

The developer behind hit RPGs like Baldur's Gate 3 and Divinity: Original Sin recently unveiled its next major project, generating significant anticipation within the gaming community. However, follow-up remarks from the studio's co-founder have added clarity to the conversation, addressing the studio's stance toward machine learning.

Augmenting Workflows, Not Cutting Jobs

In a new clarification, Swen Vincke explained that the team is employing AI technology for particular ancillary tasks. These encompass developing presentation materials, producing early-stage visual ideas, and drafting draft dialogue.

Notably, Vincke emphasized that the shipping assets in the game will be crafted exclusively by human creatives. "Larian is writing every line in-house," he said.

Our studio is constantly growing our pool of writers and are currently forming narrative groups.

As visual development is being specifically called out — we presently have 23 concept artists and have roles to fill for further creatives.

Everything we do is supplementary and focused on having people spend more time on actual creation.

Every machine learning application applied correctly is supplementary to a artist's routine, not a substitute for their craft.

Tempering Reactions with Clear Intent

The admission of AI usage originally sparked unease among some the fanbase. In response, Vincke issued additional detail on online platforms.

"At Larian, we employ these tools to research ideas, just like we use search engines and physical media," he wrote. "During the very early planning process we use it as a rough outline for layout which we then swap out with authentic artwork."

He added, "Our studio recruits talent for their unique talent, not for their capacity to execute what a algorithm proposes."

Key Areas of AI Integration

Vincke had earlier broken down the team's practical approach to this technology, defining its use into primary areas:

• Handling Monotonous Jobs: This encompasses polishing mocap data, voice editing, and pipeline-specific tasks like adapting animations for different models.
• Accelerated Iteration: Using technology to speedily create rough versions of mechanics to experiment with concepts ahead of complete implementation.
• Future Potential for Gameplay: Exploring how machine learning could one day enhance new forms of player agency, particularly in simulating dynamic reactions in a vast role-playing world.

He explicitly stated that key artistic disciplines — like writing — are are in no way fields where the team is replacing artistic input. On the contrary, Larian is expanding its staff in these very roles.

"We are neither shipping a game with machine-made assets, nor planning on trimming down staff to swap them out with AI," Vincke concluded.