雪踏乌云

@Pluvio9yte • 44,649 subscribers

📌 聚焦：AI & Vibe coding & Prompt & Agent 🌏 在做：创业 | Web出海 | Web3 🌊 持续分享AI编程、AI工具、出海干货和创业经验

Shorts

将最近全网爆火的分手片段复刻了一下。同样的提示词，来看 Minimax H3 和 Seedance 2.5 的实测对比，差异这么大啊 Seedance2.5明显人物对微表情控制的更好。

将最近全网爆火的分手片段复刻了一下。同样的提示词，来看 Minimax H3 和 Seedance 2.5 的实测对比，差异这么大啊 Seedance2.5明显人物对微表情控制的更好。

37,315 Aufrufe

Codex 大更新 —— Chrome 内置最完全功能应用解析 1. 内置浏览器 + Chrome Cookie 一键导入现在导入了 Cookie 之后，能够把抖音、小红书、推特的账号 Cookie 都导入。现在打开，直接就是登录状态。 2. 开发者模式可以查 DOM、Console、Network 请求、性能等。比如说，原来我开发网站如果遇到性能问题，让它优化就会麻烦一些。现在直接用内置的浏览器，速度非常快，这个优化速度。下面是一些应用场景内容创作与研究让 Codex 带着你的账号去小红书、微博、知乎等平台“逛”，找选题、分析爆款、抓用户反馈。开发者调试开启开发者模式后，Codex 能实时 inspect 页面：快速定位 console error、网络请求异常。分析 DOM 结构、调试已登录态的内部工具。提示词示例：“开启开发者模式，打开这个页面，检查 Network 请求里和用户数据相关的接口，并把 console 里的 error 列出来。” 测试需要真实登录态的 Web 应用等

Codex 大更新 —— Chrome 内置最完全功能应用解析 1. 内置浏览器 + Chrome Cookie 一键导入现在导入了 Cookie 之后，能够把抖音、小红书、推特的账号 Cookie 都导入。现在打开，直接就是登录状态。 2. 开发者模式可以查 DOM、Console、Network 请求、性能等。比如说，原来我开发网站如果遇到性能问题，让它优化就会麻烦一些。现在直接用内置的浏览器，速度非常快，这个优化速度。下面是一些应用场景内容创作与研究让 Codex 带着你的账号去小红书、微博、知乎等平台“逛”，找选题、分析爆款、抓用户反馈。开发者调试开启开发者模式后，Codex 能实时 inspect 页面：快速定位 console error、网络请求异常。分析 DOM 结构、调试已登录态的内部工具。提示词示例：“开启开发者模式，打开这个页面，检查 Network 请求里和用户数据相关的接口，并把 console 里的 error 列出来。” 测试需要真实登录态的 Web 应用等

158,697 Aufrufe

AI Is Moving Beyond “Generating Videos” — Toward “Generating Worlds” Over the past two years, AI video models have advanced at an astonishing pace. From Runway and Pika to Sora and Veo, AI-generated videos have become increasingly realistic and more consistent with the physical laws of the real world. Many people believe the next objective is simply to generate videos that are longer, sharper, and more lifelike. But if we take a step back, we can see that the real transformation is not happening in video itself. It is happening in world models. What Is a World Model? In 1943, psychologist Kenneth Craik proposed an idea that would influence artificial intelligence research for decades. He argued that the human brain does not merely react to the outside world. Instead, it maintains an internal model of how the world works. Because we have this internal model, we can predict the outcome of an action before we actually take it. Before crossing a road, we estimate whether a car will pass by. Before catching a ball, we predict its trajectory. These abilities come from continuously simulating the world in our minds, rather than relying entirely on trial and error. This idea later became known by a more formal term: World Model. A world model does not describe a single image or a fixed video clip. It is an internal representation capable of continuously simulating the rules and dynamics of the real world. Why Is AI Research Turning Toward World Models? Because predicting “what comes next” is becoming increasingly central to how AI systems work. Language models predict the next token. Image models predict the next step in the denoising process. Video models predict the next frame. A world model, however, attempts to predict something broader: What should the world look like in the next moment? In 2018, David Ha and Jürgen Schmidhuber proposed in their paper World Models that an intelligent agent could first learn a model of the world, and then use that internal model to plan its actions. The Dreamer series later demonstrated that many complex tasks could be learned by training agents inside an “imagined world.” At the same time, the development of video models such as Sora and Veo led researchers to another realization: A model capable of continuously generating video has already learned, at least implicitly, many of the rules governing the real world. As a result, these two research directions have gradually begun to converge. But Video Is Not Yet a World This is where the distinction is often misunderstood. For a world model to support meaningful real-time interaction, it must solve several critical problems. Most video models today are essentially answering one question: What should the next frame look like? A true world model needs to answer much more: What happens if I take one step forward? If I walk behind a building and then return, will the building still be there? If I suddenly change the camera angle, will the entire space remain consistent? If I enter a command such as: “Summon a dragon.” Will the world respond immediately? In other words, a world model must do more than generate content. It must understand space. It must understand time. It must understand causality. And it must understand interaction. Moving from watching to participating is where the real difficulty of world models begins. World Models Are Entering the Interactive Era One of the latest attempts in this direction is Alaya World, recently open-sourced by Alaya World, or Alaya Lab. Instead of generating a fixed video clip, it generates a world that users can explore in real time. Users can begin with text, an image, or a video, enter the generated scene, move freely through it, and introduce new prompts at any moment during generation. The world responds immediately. According to the publicly released information, Alaya World provides: Real-time streaming generation at 720p and 24 FPS Stable continuous exploration for more than one minute The ability to switch prompts and trigger skills or events during generation Model weights and inference code released under the Apache 2.0 License Training code and datasets planned for future release What makes these capabilities important is not simply the technical specifications. It is that the generated “world” can now support continuous interaction. The official demo shows that users can genuinely control, transform, and explore the generated environment. AI Is Evolving From a Tool Into an Environment Over the past few years, most discussions around AI have focused on content generation. Generating text. Generating images. Generating videos. But world models raise a fundamentally different question: Can AI generate an environment that people can inhabit, explore, and continuously evolve? If the answer is yes, the impact will extend far beyond video generation. Game development, robotics training, embodied intelligence, digital twins, virtual production, and many other fields could be transformed by the development of world models. World models are still at a very early stage. Yet from Craik’s proposal of an internal mental model more than eighty years ago to the emergence of today’s interactive world-generation systems, a clear evolutionary path is beginning to take shape. Perhaps what AI is ultimately learning has never been limited to images, videos, or language. Perhaps it is learning the world itself. References GitHub: Technical Report:

AI Is Moving Beyond “Generating Videos” — Toward “Generating Worlds” Over the past two years, AI video models have advanced at an astonishing pace. From Runway and Pika to Sora and Veo, AI-generated videos have become increasingly realistic and more consistent with the physical laws of the real world. Many people believe the next objective is simply to generate videos that are longer, sharper, and more lifelike. But if we take a step back, we can see that the real transformation is not happening in video itself. It is happening in world models. What Is a World Model? In 1943, psychologist Kenneth Craik proposed an idea that would influence artificial intelligence research for decades. He argued that the human brain does not merely react to the outside world. Instead, it maintains an internal model of how the world works. Because we have this internal model, we can predict the outcome of an action before we actually take it. Before crossing a road, we estimate whether a car will pass by. Before catching a ball, we predict its trajectory. These abilities come from continuously simulating the world in our minds, rather than relying entirely on trial and error. This idea later became known by a more formal term: World Model. A world model does not describe a single image or a fixed video clip. It is an internal representation capable of continuously simulating the rules and dynamics of the real world. Why Is AI Research Turning Toward World Models? Because predicting “what comes next” is becoming increasingly central to how AI systems work. Language models predict the next token. Image models predict the next step in the denoising process. Video models predict the next frame. A world model, however, attempts to predict something broader: What should the world look like in the next moment? In 2018, David Ha and Jürgen Schmidhuber proposed in their paper World Models that an intelligent agent could first learn a model of the world, and then use that internal model to plan its actions. The Dreamer series later demonstrated that many complex tasks could be learned by training agents inside an “imagined world.” At the same time, the development of video models such as Sora and Veo led researchers to another realization: A model capable of continuously generating video has already learned, at least implicitly, many of the rules governing the real world. As a result, these two research directions have gradually begun to converge. But Video Is Not Yet a World This is where the distinction is often misunderstood. For a world model to support meaningful real-time interaction, it must solve several critical problems. Most video models today are essentially answering one question: What should the next frame look like? A true world model needs to answer much more: What happens if I take one step forward? If I walk behind a building and then return, will the building still be there? If I suddenly change the camera angle, will the entire space remain consistent? If I enter a command such as: “Summon a dragon.” Will the world respond immediately? In other words, a world model must do more than generate content. It must understand space. It must understand time. It must understand causality. And it must understand interaction. Moving from watching to participating is where the real difficulty of world models begins. World Models Are Entering the Interactive Era One of the latest attempts in this direction is Alaya World, recently open-sourced by Alaya World, or Alaya Lab. Instead of generating a fixed video clip, it generates a world that users can explore in real time. Users can begin with text, an image, or a video, enter the generated scene, move freely through it, and introduce new prompts at any moment during generation. The world responds immediately. According to the publicly released information, Alaya World provides: Real-time streaming generation at 720p and 24 FPS Stable continuous exploration for more than one minute The ability to switch prompts and trigger skills or events during generation Model weights and inference code released under the Apache 2.0 License Training code and datasets planned for future release What makes these capabilities important is not simply the technical specifications. It is that the generated “world” can now support continuous interaction. The official demo shows that users can genuinely control, transform, and explore the generated environment. AI Is Evolving From a Tool Into an Environment Over the past few years, most discussions around AI have focused on content generation. Generating text. Generating images. Generating videos. But world models raise a fundamentally different question: Can AI generate an environment that people can inhabit, explore, and continuously evolve? If the answer is yes, the impact will extend far beyond video generation. Game development, robotics training, embodied intelligence, digital twins, virtual production, and many other fields could be transformed by the development of world models. World models are still at a very early stage. Yet from Craik’s proposal of an internal mental model more than eighty years ago to the emergence of today’s interactive world-generation systems, a clear evolutionary path is beginning to take shape. Perhaps what AI is ultimately learning has never been limited to images, videos, or language. Perhaps it is learning the world itself. References GitHub: Technical Report:

113,347 Aufrufe

接入anysearch后，我的agent搜索效率提高了 Parallel、Perplexity、Tavily 这些搜索工具给 Agent 用，有个一直没解决好的问题——返回的是链接加摘要，Agent 拿到之后还要自己点开网页、筛选内容、判断哪条有用。金融、学术、代码这些垂直领域的搜索质量更差。输出没有结构，光解析内容就要烧掉大量 token。分享一个我一直在用的为 AI Agent 设计的搜索基础设施 —AnySearch，一个为 Agent 量身打造的「搜索 Skill」： - 实时网页搜索 - 支持金融、学术、代码、社会媒体等垂直领域搜索 - 直接把网页转成干净的 Markdown（extract） - 输出结构化，Agent 能直接拿来用安装 AnySearch SKILL 超级简单：复制下方提示词并发送给你的 Agent，即可自动完成安装：

接入anysearch后，我的agent搜索效率提高了 Parallel、Perplexity、Tavily 这些搜索工具给 Agent 用，有个一直没解决好的问题——返回的是链接加摘要，Agent 拿到之后还要自己点开网页、筛选内容、判断哪条有用。金融、学术、代码这些垂直领域的搜索质量更差。输出没有结构，光解析内容就要烧掉大量 token。分享一个我一直在用的为 AI Agent 设计的搜索基础设施 —AnySearch，一个为 Agent 量身打造的「搜索 Skill」： - 实时网页搜索 - 支持金融、学术、代码、社会媒体等垂直领域搜索 - 直接把网页转成干净的 Markdown（extract） - 输出结构化，Agent 能直接拿来用安装 AnySearch SKILL 超级简单：复制下方提示词并发送给你的 Agent，即可自动完成安装：

94,323 Aufrufe

Claude Fable 5 经过1个月紧急下架后再回归，我这两天也重新去测试了一下。正好一直刷到赛博斗蛐蛐的视频，正好拿来测试一下，看看能不能做个同款出来。给大伙看看fable 5 的效果：视频1 再来对比一下GPT-5.5的效果，老实说有点拉了，为什么把restart按钮直接盖住了屏幕啊？不是很理解：视频2 最后再来看看国产Deepseek V4 Pro的效果，物理效果感觉还是不行，有点迟钝的感觉：视频3 Fable 5的整体效果是最接近我刷到的小视频的效果的。虽然效果很强，但是现在fable 5最大的问题在于，官方在6月22日以后，订阅套餐不能用Fable，只能走API。但是价格实在是遭不住：每 M 输出 50 美元的定价让社区吐槽声不断！我推荐用Zenmux，这个省一些。目前有个加赠20%的活动，每人最高可享 300刀！官网在这里： RPM、不限流。可调用全平台 200+ 模型（含 Claude Fable 5），非常适合做这种评测、并排对比和长期开发。

Claude Fable 5 经过1个月紧急下架后再回归，我这两天也重新去测试了一下。正好一直刷到赛博斗蛐蛐的视频，正好拿来测试一下，看看能不能做个同款出来。给大伙看看fable 5 的效果：视频1 再来对比一下GPT-5.5的效果，老实说有点拉了，为什么把restart按钮直接盖住了屏幕啊？不是很理解：视频2 最后再来看看国产Deepseek V4 Pro的效果，物理效果感觉还是不行，有点迟钝的感觉：视频3 Fable 5的整体效果是最接近我刷到的小视频的效果的。虽然效果很强，但是现在fable 5最大的问题在于，官方在6月22日以后，订阅套餐不能用Fable，只能走API。但是价格实在是遭不住：每 M 输出 50 美元的定价让社区吐槽声不断！我推荐用Zenmux，这个省一些。目前有个加赠20%的活动，每人最高可享 300刀！官网在这里： RPM、不限流。可调用全平台 200+ 模型（含 Claude Fable 5），非常适合做这种评测、并排对比和长期开发。

48,569 Aufrufe

I went a little overboard with Codex last week and burned through my entire weekly allowance in two days. Luckily, my quota reset today. Otherwise, I’m not sure what I would’ve done. It got me thinking: instead of asking one large model to handle everything from start to finish, why not let a stronger model plan the project and review the work, while a model built for execution handles the day-to-day implementation? So I tried it. The result was better than I expected. I used GPT-5.6 Sol in Codex as the decision-maker, then ran Ling-3.0-flash from Ant Ling inside OpenCode as the execution engine. Together, they built a small 3D farming game. Before writing any code, I had Codex create four documents: SPEC.md defined the product scope and the lines we couldn’t cross. ARCHITECTURE.md laid out the isometric coordinate system, state machine, and module boundaries. TASKS.md broke the project into small jobs Ling could tackle one at a time. ACCEPTANCE.md explained how each step would be tested and what “done” actually meant. Then I gave Ling a very straightforward role: You are the execution model for this project. Read all four documents before you begin. Work only on the task assigned for this round. When you’re done, run typecheck, test, and build. If anything fails, read the error, fix it, and run the checks again. Do not move on to the next task early. Ling handled dependency installation, project structure, strict TypeScript configuration, test setup, and a production build in 6 minutes and 3 seconds. It ran into issues with the Vite test config, a TS6310 error, and a missing jsdom dependency along the way. Instead of stopping at the first error, it kept reading the logs and fixing the problems until all three checks passed. The speed was honestly hard to believe. If you exclude the time spent waiting on tools, it was producing more than 100 tokens per second. That made the whole development loop feel noticeably faster. After this experiment, I’m planning to keep using the same workflow. If the task is small, there’s no reason to call an expensive planning model for every single step. If the task is large, handing the entire project to a Flash model in one prompt isn’t a great idea either. The setup that makes more sense to me is: Use a more capable model such as Codex to explore the project, make architectural decisions, and break the work down. Put the constraints into specs, schemas, types, and tests instead of leaving them buried in chat history. Give Ling-3.0-flash a steady stream of clear, verifiable implementation tasks. Report bugs with structured context and actual error logs, rather than saying, “It still doesn’t work.” Bring Codex back in for architecture reviews, visual checks, and changes that affect multiple parts of the project. The point of this setup isn’t to give AI a big “build the whole project” button. It’s to turn software development into a pipeline with a much more sensible cost structure: Codex figures out the plan, sets the boundaries, and catches problems. Ling-3.0-flash moves quickly, calls tools reliably, and works through well-defined tasks at scale. For agent workflows that involve lots of repetitive edits, production tasks, and tool calls, this may be a more practical answer than simply using the biggest model for everything.

I went a little overboard with Codex last week and burned through my entire weekly allowance in two days. Luckily, my quota reset today. Otherwise, I’m not sure what I would’ve done. It got me thinking: instead of asking one large model to handle everything from start to finish, why not let a stronger model plan the project and review the work, while a model built for execution handles the day-to-day implementation? So I tried it. The result was better than I expected. I used GPT-5.6 Sol in Codex as the decision-maker, then ran Ling-3.0-flash from Ant Ling inside OpenCode as the execution engine. Together, they built a small 3D farming game. Before writing any code, I had Codex create four documents: SPEC.md defined the product scope and the lines we couldn’t cross. ARCHITECTURE.md laid out the isometric coordinate system, state machine, and module boundaries. TASKS.md broke the project into small jobs Ling could tackle one at a time. ACCEPTANCE.md explained how each step would be tested and what “done” actually meant. Then I gave Ling a very straightforward role: You are the execution model for this project. Read all four documents before you begin. Work only on the task assigned for this round. When you’re done, run typecheck, test, and build. If anything fails, read the error, fix it, and run the checks again. Do not move on to the next task early. Ling handled dependency installation, project structure, strict TypeScript configuration, test setup, and a production build in 6 minutes and 3 seconds. It ran into issues with the Vite test config, a TS6310 error, and a missing jsdom dependency along the way. Instead of stopping at the first error, it kept reading the logs and fixing the problems until all three checks passed. The speed was honestly hard to believe. If you exclude the time spent waiting on tools, it was producing more than 100 tokens per second. That made the whole development loop feel noticeably faster. After this experiment, I’m planning to keep using the same workflow. If the task is small, there’s no reason to call an expensive planning model for every single step. If the task is large, handing the entire project to a Flash model in one prompt isn’t a great idea either. The setup that makes more sense to me is: Use a more capable model such as Codex to explore the project, make architectural decisions, and break the work down. Put the constraints into specs, schemas, types, and tests instead of leaving them buried in chat history. Give Ling-3.0-flash a steady stream of clear, verifiable implementation tasks. Report bugs with structured context and actual error logs, rather than saying, “It still doesn’t work.” Bring Codex back in for architecture reviews, visual checks, and changes that affect multiple parts of the project. The point of this setup isn’t to give AI a big “build the whole project” button. It’s to turn software development into a pipeline with a much more sensible cost structure: Codex figures out the plan, sets the boundaries, and catches problems. Ling-3.0-flash moves quickly, calls tools reliably, and works through well-defined tasks at scale. For agent workflows that involve lots of repetitive edits, production tasks, and tool calls, this may be a more practical answer than simply using the biggest model for everything.

23,107 Aufrufe

我的视频复刻Skill在Sol模型的加持下，现在非常牛逼，只要你觉得某个视频是Remotion或者Hyperframes做的，都能复刻。评论区还有视频样例和开源地址

我的视频复刻Skill在Sol模型的加持下，现在非常牛逼，只要你觉得某个视频是Remotion或者Hyperframes做的，都能复刻。评论区还有视频样例和开源地址

23,709 Aufrufe

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

最近发现一个实用的开源项目：OpenCodex。它可以让 Codex 不再局限于 GPT 模型，还能接入 Kimi、Grok、GLM 等其他大模型。配置一次后，原来的 Codex 应用和工作流基本不用变，需要时直接切换模型即可。开源地址

最近发现一个实用的开源项目：OpenCodex。它可以让 Codex 不再局限于 GPT 模型，还能接入 Kimi、Grok、GLM 等其他大模型。配置一次后，原来的 Codex 应用和工作流基本不用变，需要时直接切换模型即可。开源地址

331,176 Aufrufe • vor 28 Tagen

这次我用 Qwen3.8-Max 完成了三个代码项目，其中最直观的是一个类似《我的世界》的网页游戏。游戏已经具备完整的可玩性：角色可以移动、跳跃和探索地图，也可以挖掘、放置方块、切换物品，并使用背包与合成系统。地形能够自动生成，基础的生存机制也已经实现。另外两个项目分别是可交互的 3D AI 芯片展示，以及读取19个真实来源的多模态供应商评审系统。 Qwen3.8-Max 还是个开源模型，国产模型真是越来越强了。

这次我用 Qwen3.8-Max 完成了三个代码项目，其中最直观的是一个类似《我的世界》的网页游戏。游戏已经具备完整的可玩性：角色可以移动、跳跃和探索地图，也可以挖掘、放置方块、切换物品，并使用背包与合成系统。地形能够自动生成，基础的生存机制也已经实现。另外两个项目分别是可交互的 3D AI 芯片展示，以及读取19个真实来源的多模态供应商评审系统。 Qwen3.8-Max 还是个开源模型，国产模型真是越来越强了。

68,246 Aufrufe • vor 28 Tagen

最近Claude又发生了一波封号潮，经过这么久的摸索了，总体就这几个主要原因 1. IP IP不是绝对因素，但是干净的IP绝对是大大加分，而且Anthropic也把IP检测平台列为了合作伙伴这个IP质量检测平台是Anthropic的合作平台，大家可以自己检查一下 2. 开卡方式虚拟卡以及一些经常批量开Claude的卡台，这也是封号最为严重的因素之一，使用虚拟卡开卡风险会比较高。如果你试了好几个卡都不行，可以试试专门为AI订阅优化的卡台服务商。我自己用的是yika 3. 反代不要反代，比如sub2api这种，反代基本必封号，实测只有百分之几的幸运号而且还是一并发的反代号能活，几率非常小 4. 设备🫆 如果你怎么开都封，那就不是以上因素，是设备问题。换个浏览器重新开。 5. 邮箱邮箱使用谷歌或者Outlook比较好，乱七八糟的邮箱一个是弹验证码几率高，一个是封号概率高，不干净的邮箱有的开号会秒封其他乱七八糟的使用英文对话，改设备时区到美国时区，根本没有一分钱关系。

最近Claude又发生了一波封号潮，经过这么久的摸索了，总体就这几个主要原因 1. IP IP不是绝对因素，但是干净的IP绝对是大大加分，而且Anthropic也把IP检测平台列为了合作伙伴这个IP质量检测平台是Anthropic的合作平台，大家可以自己检查一下 2. 开卡方式虚拟卡以及一些经常批量开Claude的卡台，这也是封号最为严重的因素之一，使用虚拟卡开卡风险会比较高。如果你试了好几个卡都不行，可以试试专门为AI订阅优化的卡台服务商。我自己用的是yika 3. 反代不要反代，比如sub2api这种，反代基本必封号，实测只有百分之几的幸运号而且还是一并发的反代号能活，几率非常小 4. 设备🫆 如果你怎么开都封，那就不是以上因素，是设备问题。换个浏览器重新开。 5. 邮箱邮箱使用谷歌或者Outlook比较好，乱七八糟的邮箱一个是弹验证码几率高，一个是封号概率高，不干净的邮箱有的开号会秒封其他乱七八糟的使用英文对话，改设备时区到美国时区，根本没有一分钱关系。

68,877 Aufrufe • vor 1 Monat

Codex做视频的工作流基本跑的差不多了。目前还差一个中文断句+语句组织skill、好一点的钩子skill(不同类型的视频需要不同类型的钩子) 总体上细节能够完善的地方还有不少，但是能够确定的是以后也不用自己费劲录自己的口播视频了，自己的数字人也能够P好看一点，减少出镜容貌焦虑。感谢AI大时代。下面这个视频就是寥寥两轮提示词三四句话做出来的(其中一个风格模板)。等我整理一下，明天开源😋

Codex做视频的工作流基本跑的差不多了。目前还差一个中文断句+语句组织skill、好一点的钩子skill(不同类型的视频需要不同类型的钩子) 总体上细节能够完善的地方还有不少，但是能够确定的是以后也不用自己费劲录自己的口播视频了，自己的数字人也能够P好看一点，减少出镜容貌焦虑。感谢AI大时代。下面这个视频就是寥寥两轮提示词三四句话做出来的(其中一个风格模板)。等我整理一下，明天开源😋

24,790 Aufrufe • vor 22 Tagen

Kimi K3的游戏制作能力也在线啊，用K3制作了一个马里奥游戏，基本就是提示词直出的，没有修改过。部署到vercel了，大家感兴趣可以试一下，地址在评论区。还是带音乐的，有点带感。。。

Kimi K3的游戏制作能力也在线啊，用K3制作了一个马里奥游戏，基本就是提示词直出的，没有修改过。部署到vercel了，大家感兴趣可以试一下，地址在评论区。还是带音乐的，有点带感。。。

28,451 Aufrufe • vor 1 Monat

去掉视频效果，感觉就是ai做出来很普通的页面... motionsite这网站太逆天了🫪

去掉视频效果，感觉就是ai做出来很普通的页面... motionsite这网站太逆天了🫪

20,036 Aufrufe • vor 24 Tagen

发现一个宝藏平台 AI game builder Makeplay.ai | Free AI Game Maker，只需要输入一句指令，就能帮你完成美术开发，音效设计，动效实现，从0到1直接实现一款属于你自己的小游戏——关键是全程免费！整个开发过程全部在浏览器中就能实现，我最喜欢的是它的分支开发功能，可以把不同的想法塞进同一款游戏，然后对比实际游玩体验那种方案更有趣。我写的这个游戏叫越跑越龙，大伙也可以在平台上搜一下，体验一下我一句话生成的游戏，肉鸽跑酷。

发现一个宝藏平台 AI game builder Makeplay.ai | Free AI Game Maker，只需要输入一句指令，就能帮你完成美术开发，音效设计，动效实现，从0到1直接实现一款属于你自己的小游戏——关键是全程免费！整个开发过程全部在浏览器中就能实现，我最喜欢的是它的分支开发功能，可以把不同的想法塞进同一款游戏，然后对比实际游玩体验那种方案更有趣。我写的这个游戏叫越跑越龙，大伙也可以在平台上搜一下，体验一下我一句话生成的游戏，肉鸽跑酷。

12,770 Aufrufe • vor 15 Tagen

我的视频复刻Skill在Sol模型的加持下，现在非常牛逼，只要你觉得某个视频是Remotion或者Hyperframes做的，都能复刻。评论区还有视频样例和开源地址

我的视频复刻Skill在Sol模型的加持下，现在非常牛逼，只要你觉得某个视频是Remotion或者Hyperframes做的，都能复刻。评论区还有视频样例和开源地址

23,709 Aufrufe • vor 1 Monat

Codex 中隐藏着一个几乎无人提及的功能…… "根据 Chronicle 的记录，我在电脑上的哪些操作效率低下？请直言不讳，告诉我那些我必须面对的事实" 然后它就会给出非常具有针对性的建议，效果见评论区👇

Codex 中隐藏着一个几乎无人提及的功能…… "根据 Chronicle 的记录，我在电脑上的哪些操作效率低下？请直言不讳，告诉我那些我必须面对的事实" 然后它就会给出非常具有针对性的建议，效果见评论区👇

37,938 Aufrufe • vor 3 Monaten

用了两天的Fable-5，得到了一个与大部分人截然相反的结论，实测体验如下：速度：非常慢，尤其是开始分析和规划的时候能感受到像乌龟慢爬价格：我是Max5订阅用户，虽然输入输出定价为Opus的两倍，但是实际消耗量并没有像流水一样，消耗速度确实变快了，但命中缓存后消耗没有特别高，没有人传人的消耗那么离谱的快所以铺天盖地说消耗非常快的只有三种可能：第一种是Pro订阅账号容量本来就小，第二种是没自己账号纯造谣，第三种是本来对Opus的消耗没有感知，看到别人说fable消耗快自己也一用发现消耗快于是觉得是真的消耗快了。本身Opus的消耗就非常快嘛，现在只不过是变为了原来的大概1.5x 对于我来说，我通常只用Opus，所以这个1.x倍Opus的消耗量能够接受。实际使用中建议把缓存重建修改为1小时。能力：能力强体现在思维边界更广，架构能力更强。对于前端能力测试确实是有很大提高，尤其是创意能力。真正落地到工程项目中，我的体感是能够真正发现GPT-5.5的问题了，不会再像之前基本一直认为GPT的分析是对的。实际能力类似于Claude Opus4.6++与GPT-5.5++的结合版，目前没有到非常惊艳的程度结合价格和6月22之后就没了，我也没有升级Max20的打算，Max5+GPT-5.5乃至即将出现的5.6我觉得完全够用。也建议大家理性消费。如果想走按量体验可以看下评论区。最后给大家看一下昨晚用Fable简单构建的前端的效果，关于为什么我吐槽过还要做前端，是因为我也需要在抖音小红书炸裂搞流量，人作为视觉动物，前端是最开始抓住注意力的开头的。视频如下，网站部署在verel地址放在评论区了，大家可以自行查看

用了两天的Fable-5，得到了一个与大部分人截然相反的结论，实测体验如下：速度：非常慢，尤其是开始分析和规划的时候能感受到像乌龟慢爬价格：我是Max5订阅用户，虽然输入输出定价为Opus的两倍，但是实际消耗量并没有像流水一样，消耗速度确实变快了，但命中缓存后消耗没有特别高，没有人传人的消耗那么离谱的快所以铺天盖地说消耗非常快的只有三种可能：第一种是Pro订阅账号容量本来就小，第二种是没自己账号纯造谣，第三种是本来对Opus的消耗没有感知，看到别人说fable消耗快自己也一用发现消耗快于是觉得是真的消耗快了。本身Opus的消耗就非常快嘛，现在只不过是变为了原来的大概1.5x 对于我来说，我通常只用Opus，所以这个1.x倍Opus的消耗量能够接受。实际使用中建议把缓存重建修改为1小时。能力：能力强体现在思维边界更广，架构能力更强。对于前端能力测试确实是有很大提高，尤其是创意能力。真正落地到工程项目中，我的体感是能够真正发现GPT-5.5的问题了，不会再像之前基本一直认为GPT的分析是对的。实际能力类似于Claude Opus4.6++与GPT-5.5++的结合版，目前没有到非常惊艳的程度结合价格和6月22之后就没了，我也没有升级Max20的打算，Max5+GPT-5.5乃至即将出现的5.6我觉得完全够用。也建议大家理性消费。如果想走按量体验可以看下评论区。最后给大家看一下昨晚用Fable简单构建的前端的效果，关于为什么我吐槽过还要做前端，是因为我也需要在抖音小红书炸裂搞流量，人作为视觉动物，前端是最开始抓住注意力的开头的。视频如下，网站部署在verel地址放在评论区了，大家可以自行查看

24,152 Aufrufe • vor 2 Monaten

发现了一个开源的生图 Claude Skill MeiGen-AI-Design-MCP，一个把大模型变成“专业设计助理”的仓库。该 Skill 和内置的 Prompt 提示词库搭配，能够搜索1300+提示词。产出的图片效果非常不错。最近我开发SaaS添加展示图片时经常用到。通过 7个内置的 MCP Tools 为大模型提供一整套“设计能力插件”，能够：像创意总监一样拆解需求像设计师一样做多方向视觉探索像工程师一样并行、自动化生成图像能够启动多个子代理： prompt-crafter写多套高质量提示 image-generator并行生成图像 gallery-researcher灵感搜索不污染主上下文安装过程如下 /plugin marketplace add jau123/MeiGen-AI-Design-MCP /plugin install meigen@meigen-marketplace 此外，还支持 ComfyUI 工作流程导入和 OpenClaw，但是我暂时用不到，大家可以自行探索，链接放在评论区了。视频展示效果如下

发现了一个开源的生图 Claude Skill MeiGen-AI-Design-MCP，一个把大模型变成“专业设计助理”的仓库。该 Skill 和内置的 Prompt 提示词库搭配，能够搜索1300+提示词。产出的图片效果非常不错。最近我开发SaaS添加展示图片时经常用到。通过 7个内置的 MCP Tools 为大模型提供一整套“设计能力插件”，能够：像创意总监一样拆解需求像设计师一样做多方向视觉探索像工程师一样并行、自动化生成图像能够启动多个子代理： prompt-crafter写多套高质量提示 image-generator并行生成图像 gallery-researcher灵感搜索不污染主上下文安装过程如下 /plugin marketplace add jau123/MeiGen-AI-Design-MCP /plugin install meigen@meigen-marketplace 此外，还支持 ComfyUI 工作流程导入和 OpenClaw，但是我暂时用不到，大家可以自行探索，链接放在评论区了。视频展示效果如下

15,296 Aufrufe • vor 6 Monaten

Keine weiteren Inhalte verfügbar