
鹿友 AI — 只提供最好的模型
API relay service providing stable direct access to Claude Fable-5 models with transparent pricing.
@iveyzen · X
鹿友AI上线了 最贵的AI中转站,只因为想创造稳定fable-5访问专线
The full gallery
Tech stack
20 projects

API relay service providing stable direct access to Claude Fable-5 models with transparent pricing.
@iveyzen · X
鹿友AI上线了 最贵的AI中转站,只因为想创造稳定fable-5访问专线

Forge creatures in a 3D game with GPU-simulated water physics.
@rand_monsterlab · X
A monster walks into a GPU-simulated pond. Reactive SPH water in the browser with @threejs + WebGPU. Every movement sends ripples through Coming soon. Follow @rand_monsterlab: #ThreeJS #WebGPU #VibeCoding #IndieGame #Monster

Play 20 classic HTML5 games generated by Claude Fable 5, each with its AI prompt available.
yidaimaxia · V2EX
claude fable5 生成的游戏效果 最近 claude fable5 相当聒噪,我用这个模型一句话生成了 20 款经典的 H5 网页小游戏 为了方便大家试玩和研究,我把它们集成到了自己写的轻量级工具站里,并且将每款游戏生成所用到的完整英文 Prompt 提示词完全公开在了游戏详情页,可以使用这个 prompt 在其他模型跑跑看是啥效果。 👉 小游戏在线试玩与 Prompt 传送门: https://www.pokitx.com/zh/html-games 🎮 部分小游戏复刻 showcase: 森林冰火人 (Forest Ice & Fire) 复刻程度:完美还原了双人键盘控制、冰火物理陷阱的碰撞体积判定。 Prompt:我们在详情页附带了引导 AI 编写双人物理按键监听和关卡碰撞图纸的核心 Prompt 。 试玩 & 提示词: https://www.pokitx.com/zh/html-games/senlinbinghuoren 3D 坦克大战 (Tank Battle 3D) 技术要点:利用 H5 Three.js 库,由 AI 一

Daily-updated rankings of Simplified Chinese X account metrics and viral tweets.
@jedeeai · X
我做了一个网站 专门记录X上简中圈的“卷王” 并以此提醒自己 在现有的努力程度面前 还不足以谈论天赋。 你们还想看谁的数据,评论区告诉我

Upload a photo of your interior, describe changes you want, and get photorealistic design renderings instantly.
@mrgriggio · X
Big update shipped to my vibecoded app focused on the italian market 6 AI flows now: furnish, render→photo, empty a room, photo→video, facade colors, garden makeover. 100% Built with @Replit and brainstormed with Claude Organic traffic starting to move thanks to @outrank_so (Blog and backlinks) + @UseFastlane (for social). Still $0 MRR but I keep pushing 🔨


@sridharfyi https://t.co/EsNHxfUqXO
@SocialWithAI · X

Benchmark AI models by having them animate a 3D banana plant's full lifecycle.
fran-mora · HN
I gave 5 AI coding agents one prompt: grow a banana plant through its whole life in three.js: sprout, leaves, flower, fruit, rot, then pups that restart the loop. It's deceptively simple and yet very hard to get right from procedural code: you have to write working three.js and understand how the plant is actually built; how it hangs, ages and decays. Get the biology wrong and the code renders something weird. These are agents, not bare models (Claude Code and Codex for now). They can use tools, including playwright to check their work and improve it.