Skip to main content
GameDev.net gamedev.net

Generative Ai News

The latest Generative Ai coverage curated for game developers.

The happiest man in gaming hates generative AI

GamesIndustry.biz says Tarn Adams is still energized by Dwarf Fortress, but he’s firmly against generative AI in development. He argues it adds bloated code, weak productivity gains, and real job-security …

News GamesIndustry.biz · 1 day, 11 hours ago
"why can you not just enjoy AI art?"

Freya Holmér asks why AI art still sparks such a strong backlash, framing it as a culture clash as much as a tooling debate. For game teams, the real issue …

Video Freya Holmér · 3 days, 5 hours ago
Attributing HOW, Not Just WHICH: Counterfactual Response Trajectories for Diffusion Models

arXiv cs.GR details a new attribution method for diffusion models that tracks how training examples shape generation over time, not just which samples matter. CADT builds counterfactual response trajectories across …

Research arXiv cs.GR · 4 days, 20 hours ago
ScribbleEdit: A Benchmark for Scribble-Only Image Editing

arXiv cs.GR details ScribbleEdit, a new benchmark for scribble-only image editing that tests whether models can infer intent from sparse user marks. The team says current VLM- and LLM-based editors …

Research arXiv cs.GR · 5 days, 20 hours ago
Wizards of the Coast union expands, demands company stop pushing generative AI

GamesIndustry.biz reports that Wizards of the Coast’s union is expanding to cover the D&D team and Team X, while pressing Hasbro to drop its push for generative AI. The group …

News GamesIndustry.biz · 6 days, 8 hours ago
Unity unveils a web-based AI game creation platform

GamesIndustry.biz reports that Unity is launching Unity Spark, a browser-based AI game creation platform built on the Unity engine and tied to Google Playground. It lets users prototype 3D games …

News GamesIndustry.biz · 6 days, 12 hours ago
Local Content-Style Control for Diffusion-based Image Stylization

arXiv cs.GR details a no-retraining tweak for diffusion stylization that gives artists local control over both content and style. By turning two existing conditioning weights into spatial maps, the method …

Research arXiv cs.GR · 6 days, 20 hours ago
Google debuts new 'experimental' AI game platform named Google Playground

Game Developer reports that Google has debuted Google Playground, an experimental AI game platform aimed at people who want to play games made by AI. The pitch is simple: use …

News Game Developer · 1 week ago
Sega won't "entrust the creative aspect of games to AI," but is using tech to "improve efficiency" in other departments

GamesIndustry.biz reports Sega is drawing a hard line between AI-assisted production and creative authorship, saying it will not entrust game creativity to generative tools. The company is still using AI …

News GamesIndustry.biz · 1 week ago
Jagex responds to use of generative AI in RuneScape trailer made by "trusted external partner"

GamesIndustry.biz reports that Jagex pulled a RuneScape 3 trailer for Dragon Slayer 2 after fans spotted clear generative AI artifacts. The studio says a trusted external partner had promised not …

News GamesIndustry.biz · 1 week, 1 day ago
"Quite often it's given me more to do" – Why AI might be creating more work for games companies, rather than saving time

GamesIndustry.biz reports that generative AI is creating as much extra work as it saves for game studios, with HR leaders citing policy churn, data-leak fears, and employee anxiety. Some teams …

News GamesIndustry.biz · 1 week, 4 days ago
Diffusion Editing with Soft Mask: Pixel Level Redo of Image and Video with Adjustable Strength

arXiv cs.GR details SoftPaint, a zero-shot diffusion editing method that gives image and video tools pixel-level control with soft masks. Instead of all-or-nothing masking, it lets creators dial edit strength …

Research arXiv cs.GR · 1 week, 4 days ago
Frozen Scenes, Shifting Winners: Configuration Fragility in Text-to-3D Evaluation

arXiv cs.GR says text-to-3D leaderboards can flip just from changing render and caption settings, even when the generated scenes stay frozen. In tests across 300 scenes and 19 evaluators, protocol …

Research arXiv cs.GR · 1 week, 4 days ago
Strike a Chord! Modal Kinetic Typography

arXiv cs.GR details a modal kinetic typography system that animates vector letters from their own vibration modes while keeping them readable. The method uses a finite-element eigenproblem plus a frozen …

Research arXiv cs.GR · 1 week, 5 days ago
talking to a normie [sic] about the dangers of AI in art, game dev, and humanity

Freya Holmér follows up her AI-doom panel with a longer conversation about how generative tools may erode meaning in art and game development. The discussion centers on whether AI changes …

Video Freya Holmér · 2 weeks, 1 day ago
Intervention, Not Shared Latents: Blocking Visual Shortcuts in Audio-Video Generation

arXiv cs.GR details a causal study showing audio-video generators can latch onto visual shortcuts instead of the event itself. The paper argues shared-latent designs don’t solve the problem, and that …

Research arXiv cs.GR · 3 weeks ago
Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene Reconstruction

arXiv cs.GR details Mira-Scene, a 3D scene reconstruction method that aligns generated objects to pixels instead of relying on sparse pose guesses. For game teams building scene tools or AI-assisted …

Research arXiv cs.GR · 3 weeks ago
WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory

arXiv cs.GR details WorldCrafter, a video world model that uses implicit 3D-aware memory to keep scenes consistent across viewpoints and long horizons. The system lets the requested camera angle shape …

Research arXiv cs.GR · 3 weeks ago
Tokyo Game Show 2026 celebrated the past, and an uncertain AI future | Opinion

GamesIndustry.biz says Tokyo Game Show 2026 leaned hard on legacy IP while AI loomed over the floor. With the final day canceled by typhoon risk, the clearest signal for developers …

News GamesIndustry.biz · 3 weeks, 1 day ago
joining an AI doom panel discussion oh boy

Freya Holmér is joining an AI doom panel discussion, and she says she’ll argue that generative AI is an anti-humanity technology. The panel is hosted and moderated by Whick-TV, with …

Video Freya Holmér · 3 weeks, 4 days ago
Page 1 of 7 Next