Larian Studios Explains Its Implementation of Machine Learning for New Divinity Game

The studio behind hit titles like Baldur's Gate 3 and Divinity: Original Sin has recently shown its new project, creating immense excitement within the gaming community. However, recent remarks from the company's co-founder have introduced clarity to the conversation, addressing the developer's philosophy toward machine learning.

AI as a Creative Assistant, Not a Substitute

In a new message, Swen Vincke outlined that the company is using machine learning for specific preliminary tasks. These encompass enhancing presentation materials, generating rough concept art, and writing draft copy.

Crucially, Vincke emphasized that the end material in the game will be created solely by human writers. "Our team is writing every line in-house," he affirmed.

Our studio is continuously growing our roster of writers and are currently forming writing teams.

As concept art is being specifically mentioned — we presently have twenty-three visual developers and have positions available for more talent.

All our efforts we do is additive and focused on enabling creatives to spend greater focus on the creative process.

Any ML tool implemented properly is additive to a developer's routine, never a stand-in for their talent.

Responding to Feedback and Defining the Path

The revelation of employing this technology at first provoked concern among some the fanbase. In response, Vincke provided additional elaboration on online platforms.

"Our team utilizes machine learning to gather inspiration, similar to we use the internet and reference books," he explained. "During the conceptual brainstorming phase we use it as a simple sketch for composition which we then swap out with authentic artwork."

He continued, "We've hired creatives for their creative vision, not for their willingness to execute what a machine suggests."

Focused Uses for Machine Learning

Vincke had earlier outlined the team's focused approach to machine learning, grouping its use into primary pillars:

• Automation of Tedious Tasks: Areas like motion capture cleaning, dialogue cleanup, and Larian-specific work like adjusting assets for various species.
• Accelerated Iteration: Using tools to quickly build rough models of scenarios to test concepts prior to expensive implementation.
• Experimental Frontiers: Exploring how AI could one day enhance new forms of gameplay, particularly in creating dynamic reactions in a vast role-playing world.

He clearly affirmed that key artistic disciplines — such as writing — are are in no way departments where the company is reducing human talent. On the contrary, Larian is expanding its staff in these very roles.

"We are neither launching a game with AI-generated content, and we are certainly not looking at cutting teams to replace them with artificial intelligence," Vincke concluded.