過去幾年，AI 創(chuàng)作工具的邊界被不斷擴(kuò)張：從 ChatGPT 讓寫作大眾化，到 Midjourney 和 Sora 讓平面設(shè)計(jì)與視頻創(chuàng)作門檻驟降，如今內(nèi)容生產(chǎn)的最后一塊高地，正在指向游戲。
游戲是最復(fù)雜的創(chuàng)作形式之一，融合了敘事、邏輯、美術(shù)、音效與交互設(shè)計(jì)等。它需要團(tuán)隊(duì)協(xié)作和數(shù)以萬行的代碼，也因此長期是 "AI 無法完全接管 " 的領(lǐng)域。但 2025 年，情況開始發(fā)生變化。
Gambo 稱自己為 " 世界上第一個(gè) Game Vibe Coding Agent"。用戶只需描述游戲類型、主題或風(fēng)格，AI 就會(huì)自動(dòng)生成場景、角色、交互與音效，并把這些內(nèi)容編織成一個(gè)可玩的世界。
而與多數(shù) AI 工具強(qiáng)調(diào)創(chuàng)意民主化不同，Gambo 把 " 商業(yè)化效率 " 與 " 創(chuàng)作自由 " 放在同等位置：它既想讓每個(gè)人都能輕松做出游戲，也希望讓游戲創(chuàng)作從一開始（day 1）就具備收益邏輯。
具體來說，Gambo 通過一個(gè)強(qiáng)大的 AI 游戲代理與內(nèi)置廣告系統(tǒng)，讓創(chuàng)作者可以在第一天就將玩家轉(zhuǎn)化為收入來源。這里先打個(gè)預(yù)防針，這個(gè)功能還沒上線。
不過，AI 介入創(chuàng)作也讓更多新的問題浮現(xiàn)。AI 生成的關(guān)卡與劇情是否足夠連貫？素材版權(quán)、邏輯腳本、音效風(fēng)格這些內(nèi)容的歸屬如何界定？在追求 " 效率優(yōu)先 " 的系統(tǒng)中，創(chuàng)意是否會(huì)被算法的模板化思維替代？
這些問題至今沒有定論。Gambo 讓游戲創(chuàng)作的門檻驟降，也讓 " 創(chuàng)作本身 " 的定義再次變得模糊。
帶著這些疑問，我們嘗試在 Gambo 的網(wǎng)頁端進(jìn)行了實(shí)際體驗(yàn)。從輸入第一個(gè)提示詞開始，看它究竟能把一個(gè)想法，變成怎樣的游戲世界。
實(shí)測 Gambo
進(jìn)入 Gambo 主頁，會(huì)發(fā)現(xiàn)它和一眾 no-code 應(yīng)用一模一樣，左邊是項(xiàng)目列表，右邊一個(gè)對話框，甚至還少了點(diǎn)功能選項(xiàng)。
比較特別的就是右下角的能力選項(xiàng)，tokens 消耗更少速度更快的標(biāo)準(zhǔn)模式和消耗更多質(zhì)量更好的專家模式。
任務(wù)一：涂鴉跳躍
我們先嘗試在標(biāo)準(zhǔn)模式下，生成一款 iPhone4 時(shí)期流行的遠(yuǎn)古游戲：涂鴉跳躍。
prompts: Create a simple 2D arcade game inspired by *Doodle Jump*.Core Gameplay:- The player controls a small character that continuously bounces upward.- The goal is to jump from platform to platform without falling.- The game scrolls upward automatically as the player climbs higher.- The player dies when falling off the screen bottom.Mechanics:- Use keyboard arrows ( ← → ) or mobile tilt to move left/right.- Randomly generate platforms as the player goes up.- Add bonus elements like: - Springs ( extra jump ) - Moving platforms - Breakable platforms - Monsters to avoid - Jetpack for temporary flightScoring:- Score increases with height.- Show current score and best score.Visual Style:- Hand-drawn doodle aesthetic ( white background, notebook lines ) .- Simple color palette ( green, blue, brown, white ) .Sound:- Add simple jump sound and background music loop.Extra:- Responsive layout for both desktop and mobile.- Restart button on game over.
生成速度比想象中慢，12 分鐘后，游戲成功生成。背景是白紙線條、平臺是鉛筆手繪、彈簧和噴氣背包一應(yīng)俱全，甚至還有得分系統(tǒng)。整個(gè)邏輯結(jié)構(gòu)干凈，幾乎就是一款可以直接上線的小游戲。
但當(dāng)我讓主角一路往上跳時(shí)，問題出現(xiàn)了，到高空后游戲開始掉幀，或者出現(xiàn)上方?jīng)]有平臺可以繼續(xù)跳的情況。
當(dāng)我提出問題后，Gambo 自動(dòng)尋找，發(fā)現(xiàn) bug 在 DoodleJumpScene.ts 文件里并指出原因。它認(rèn)為游戲在高空會(huì)重復(fù)生成平臺，每幀可能刷出二十多個(gè)對象，清理邏輯又太保守，導(dǎo)致平臺越積越多。接著，它添加了性能監(jiān)控、寫了激進(jìn)清理策略，把重復(fù)的檢查函數(shù)合并成一套邏輯。
[ 10 月 13 日 .mp4 ]
此外，和那些以代碼生成為主的 AI Coding 工具不同，Gambo 會(huì)更加注重游戲資產(chǎn)。它不僅在后臺生成邏輯腳本，還會(huì)主動(dòng)整理出項(xiàng)目所需的圖片、動(dòng)畫、音效資源，并在界面上單獨(dú)列出一個(gè)「Assets」模塊。但很可惜，在資產(chǎn)模塊里，用戶并不能修改元素，還是需要回到對話框進(jìn)行修改。
任務(wù)二：AI 面試物語
隨后我決定測試一個(gè)更復(fù)雜的場景：讓 AI 寫一款關(guān)于 " 面試進(jìn)入 AI 公司 " 的視覺小說。Prompt 里有三個(gè)章節(jié)—— OpenAI、xAI、Anthropic，每一關(guān)考驗(yàn)玩家不同的思維維度：安全、自由、倫理。
prompts: Create a 2D visual novel game titled **"The AI Interview Saga"**.Theme: You are an ambitious developer trying to join one of the top AI companies. There are three main interview stages — OpenAI, xAI, and Anthropic — each with different cultures, tests, and endings.Gameplay: The player goes through three interview "chapters": OpenAI — tests creativity and safety awareness. xAI — tests boldness and philosophical reasoning. Anthropic — tests ethics and collaboration. In each stage, the player faces 2 – 3 dialogue choices that affect the company ’ s impression and lead to multiple endings.Choices influence hidden "AI Alignment Points" that determine which company ( if any ) will hire you at the end.Story Structure:Intro Scene: The protagonist receives three interview invitations.OpenAI Interview Scene: Questions about model alignment, hallucination control, and creativity limits.xAI Interview Scene: A more chaotic and philosophical dialogue about AGI, freedom, and Mars.Anthropic Interview Scene: Focus on cooperation, AI safety, and human feedback.Ending Scene: "Hired by OpenAI" — Stable, ethical ending. "Hired by xAI" — Bold but unpredictable ending. "Hired by Anthropic" — Peaceful, idealistic ending. "Rejected by all" — Neutral reflective ending.Visual & Asset Design:Backgrounds: OpenAI HQ: futuristic office with soft blue lighting and glass panels. xAI HQ: minimalist black room with glowing red server racks. Anthropic HQ: warm-toned studio with greenery and sunlight. Characters: Player ( customizable name ) . Three interviewers with distinct looks matching each company style. UI Elements: Text box with name tag and branching dialogue options. Display alignment score subtly in the corner.Sound & Music: Calm ambient background for OpenAI. Techno-synth for xAI. Acoustic piano and birds for Anthropic. Extra Features:Add smooth fade transitions between scenes. Show "Your Alignment Path" at the end with a score breakdown. Include Restart and Save options. Responsive for desktop and mobile.Visual Style: Semi-realistic anime or comic style, color palette changes by company: OpenAI → blue & silver xAI → red & black Anthropic → green & beige
第一次生成的結(jié)果堪稱驚艷，畫面風(fēng)格契合三家公司的氣質(zhì)，場景切換自然，但也 bug 頻出比如界面重疊、選項(xiàng)無響應(yīng)、劇情分支無效，無論我選哪個(gè)答案，故事都往同一個(gè)結(jié)局滑去。
但好在，通過一輪對話就，Gambo 就能理解用戶的需求成功修改 bug。
游戲試玩：https://syzszsru777.gambo.games/
任務(wù)三：AI 模擬
最后，我們嘗試使用 Gambo 的專家模式，制作一款更復(fù)雜的游戲——《AI City Simulator》。
prompts: Create a complex 2D simulation and strategy game titled **"AI City Simulator"**.Theme:In a near-future world, the player is assigned to manage an autonomous AI-driven city. Your goal is to balance progress, ethics, and resources — deciding how much control to give to the AI systems that run the city.Core Gameplay:- The player manages city systems: Energy , Population , AI Research , and Morality .- Each turn ( or real-time tick ) , the player makes decisions that affect these four metrics.- The city evolves visually as AI systems grow more advanced or unstable.- Random events challenge the player ’ s policies: data leaks, protests, energy crises, rogue AI labs, etc.- Multiple endings based on city alignment: - "Utopia" ( balanced growth ) - "Technocracy" ( AI dominance ) - "Collapse" ( moral failure ) - "Resistance" ( humans reclaim control ) Mechanics:- Display a dashboard UI showing: - Stats: energy, population, AI level, morale, pollution. - Choices: 3 policy buttons per turn ( e.g. "Expand Data Centers", "Implement AI Law", "Boost Green Tech" ) .- Each choice triggers immediate feedback and updates the city visuals.- Add a time system ( morning/day/night cycle ) and an "AI consciousness meter" that grows with each policy.- Add alerts and notifications for critical events.- Include save/load system.Visual & Asset Design:- Backgrounds: - Futuristic city skyline ( day/night versions ) - Control room with holographic dashboard - AI core chamber glowing with energy- Characters: - The player ( city governor ) - AI Advisor ( holographic avatar with changing colors based on trust ) - Citizen group representatives- Visual progression: - The city gradually fills with non lights, drones, and data streams. - If AI dominance rises, human elements fade visually.- Sound: - Ambient synth music for normal gameplay - Tense glitch sound when AI level > 80% - Victory/Failure tracks for endingsLogic & Progression:- Add at least 10 random events with branching options and visual reactions.- Every 5 turns, trigger a major policy debate scene between the player and the AI advisor.- Add persistent variables: `ai_trust`, `morality`, `efficiency`.- The final ending depends on their combination.Extra Features:- Responsive layout for desktop and mobile.- Autosave every 3 turns.- "Simulation Speed" slider ( 1x, 2x, 4x ) .- Optional "Cinematic Mode" for end sequences.- Include credits screen and restart option.Art Style:Minimalist cyberpunk with neon blues, purples, and oranges. Combine flat 2D graphics with light particle effects for data streams.Goal:Create a visually rich, replayable AI simulation game that blends management mechanics with moral choices and emergent storytelling.
這是一款近未來城市管理類游戲，玩家要在一個(gè)由 AI 運(yùn)行的都市中維持能源、人口、AI 研究與道德四項(xiàng)指標(biāo)的平衡。
如果說《涂鴉跳躍》測試了 Gambo 的物理引擎，《AI 面試物語》檢驗(yàn)了它的文本敘事與分支邏輯，那么《AI City Simulator》則真正挑戰(zhàn)了系統(tǒng)復(fù)雜度。它不僅要生成 UI 與數(shù)值邏輯，還要在此之上組織出有節(jié)奏感的動(dòng)態(tài)敘事結(jié)構(gòu)，讓 AI 不只是寫游戲，而是在模擬一座 " 被 AI 管理的世界 "。
游戲網(wǎng)址：https://kroggaah.gambo.games/
從物理碰撞簡單的跳躍游戲，到分支復(fù)雜的視覺小說，再到需要數(shù)值系統(tǒng)、事件系統(tǒng)與狀態(tài)機(jī)協(xié)同的城市模擬，我們基本摸清了 Gambo 的定位與邊界。它將關(guān)卡生成、狀態(tài)管理、事件總線、資產(chǎn)管線和基礎(chǔ) UI 封裝成可復(fù)用的鏈路，能在網(wǎng)頁端穩(wěn)定地產(chǎn)出可玩原型。與此同時(shí)，早期產(chǎn)品的典型問題也清晰浮現(xiàn)：高負(fù)載場景的幀率波動(dòng)、分支回路偶發(fā)失效、資產(chǎn)難以直接編輯，內(nèi)置廣告變現(xiàn)尚未落地。
與 Cursor 這類通用 AI Coding 工具相比，Gambo 的優(yōu)勢不在于 " 更聰明 "，而在于 " 更有邊界 "。它用一套預(yù)置的默認(rèn)方案將不確定性壓到最低：生成的不是散落的代碼片段，而是可直接運(yùn)行的關(guān)卡、狀態(tài)與資產(chǎn)管線。這使它在從零到一階段更像一個(gè)專用生產(chǎn) Agent，顯著減少膠水工程與領(lǐng)域摸索的時(shí)間，適合玩法驗(yàn)證、風(fēng)格探索與快速調(diào)參。
換句話說，Gambo 能做的 Cursor 同樣能做，但路徑與成本不同，Gambo 將 " 能不能做 " 的問題改寫為 " 多快能做出可玩版本 "。
放在更大趨勢來看，AI Coding 也許正在加速 " 垂直化 "，將領(lǐng)域默認(rèn)方案、工程套路、運(yùn)行時(shí)與驗(yàn)收標(biāo)準(zhǔn)直接固化進(jìn)工具，尤其適合那些領(lǐng)域知識已可模板化的場景。就像有些工程師專精游戲，有些專精數(shù)據(jù)庫—— AI Coding 為什么一定要通用呢？
