The Creators of Baldur's Gate 3 Clarifies Its Use 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, creating a wave of excitement within the industry. However, subsequent comments from the studio's figurehead have added nuance to the discussion, focusing on the developer's approach toward machine learning.

A Tool for Ideation, Not Replacement

In a recent statement, Larian's director detailed that the team is utilizing machine learning for particular preliminary functions. These include fleshing out PowerPoint slides, creating initial artistic references, and drafting draft copy.

Notably, Vincke made clear that the shipping content in the game will be authored exclusively by real creatives. "We are creating every line ourselves," he said.

Our studio is constantly growing our pool of concept artists and are busily forming writing teams.

Given that visual development is being specifically mentioned — we presently have twenty-three artistic staff and have positions available for further artists.

Everything we do is incremental and designed to having people spend greater focus on actual creation.

Every ML tool applied correctly is a boost to a creative team process, not a replacement for their skill.

Tempering Reactions with Clear Intent

The revelation of using AI initially sparked concern among portions of the player base. In reaction, Vincke provided further clarification on social media.

"Our team utilizes these tools to gather inspiration, similar to we use the internet and physical media," he wrote. "In the very early ideation stages we use it as a rough outline for structure which we then swap out with authentic artwork."

He continued, "Larian brings on artists for their unique talent, not for their capacity to follow what a machine suggests."

Three Pillars of Practical Application

Vincke had previously detailed the studio's focused method to machine learning, categorizing its use into primary functions:

• Streamlining Repetitive Work: This encompasses motion capture cleaning, audio processing, and technical processes like adjusting assets for various species.
• Rapid Prototyping ('White Boxing'): Using technology to speedily create simple models of mechanics to experiment with concepts prior to full production.
• Long-Term Aspirations: Researching how machine learning could eventually create new forms of reactivity, specifically in simulating unforeseen permutations in a detailed game universe.

He explicitly noted that key artistic domains — such as visual art — are are absolutely not fields where the company is reducing artistic input. Conversely, Larian is recruiting more in these precise roles.

"Larian is neither shipping a game with any AI components, nor looking at cutting staff to replace them with artificial intelligence," Vincke stated definitively.