Unity

Headlines · 3

1. 3h
   Google Playground hands-on: prompt-to-game platform built with Unity

   Google announced Playground, an experimental AI game platform made with Unity, open to users in the US aged 18 and over, where people can play others' creations and generate their own games from prompts. The site integrates Unity Spark for more complex gameplay and higher-fidelity 3D content, and uses Nano Banana 2 to auto-generate game thumbnails; free users must join a waitlist for creation access, while Google One AI members get it immediately. In a hands-on test, simple games were playable but complex level design, controls and balance remained rough, and thumbnails looked far better than actual gameplay.

   36氪 人工智能 · 🔥 9
2. 2d
   Google launches Playground, a browser-based no-code AI game creation platform

   Google on October 7 introduced Playground, an experimental platform where users describe a game idea in natural language and get a playable game they can test, refine and share — no coding required, with follow-up prompts able to change physics, rules, characters or environments. It runs in the browser on phones and laptops, and creators can keep games private, share a link or publish to the Playground Explore gallery, which supports leaderboards, multiplayer in select genres and Google Play Games profiles. According to The Verge, it is powered by Gemini, Nano Banana and Lyria plus custom software Google tuned on games it built itself; it is available to US users aged 18+ with creation access tiered by Google One membership, and a Unity Spark integration (still in testing) is promised later.

   Google AI · The Keyword · 🔥 62
3. 2d
   SWE-Game benchmark tests whether coding agents can build games

   An arXiv paper introduces SWE-Game, a benchmark of 247 tasks grounded in 41 executable reference Godot games spanning 13 gameplay categories in 2D and 3D, with five task types: brief-to-game, implementation from a design document, skeleton completion, repair of 83 injected-fault cases, and Godot-to-Unity porting. Across six evaluated models, Opus5 scored highest overall in all five task types, yet best overall scores on the three construction tasks stayed below 60 out of 100, with Brief-to-Game at 50.38; the authors flag requirement omissions and gameplay logic errors as the predominant problems. The paper reports executable checks reaching 92.59% balanced accuracy on human-labeled behaviors from 100 agent-built games versus 78.41% for a video-based VLM judge, and rubric visual scores with a 0.829 Spearman correlation to human ratings.

   Hugging Face · Papers · 🔥 0

Experience and discussion from the community

Share my Unity experienceAsk about Unity