I love this idea. This is a computer program that writes itself. Just ask for something that doesn’t exist. And there it is a self extending AI, if you will. Okay, so what is this, Deepse has given us amazing, free and open weight AI systems. And now a free and open source harness. This is what gives your AI arms and legs to actually make it able to do things for you, but.Wait, harnessornesses are not new. Theres piey, theres open code How is this different Why use it Well four things one the user interface can be completely rewritten. That is the thing with the flying whale or putting the snake in the harness that you see in the promo video by the way, snake in the harness that’s not a term you use very often is it but in this corner of the internet it is normal.Welcome to two minute papers,2, the agents inside the H can also be customized. You see a code review mode added here that tells the AI to look at a code base find issues and rank them by severity. That was just made up on the spot. So every major part can be rewritten. But three, this is the most important. Now, hold on your paperss fellow scholars, because it’s not you who realizeds the.😊But the program rewrites itself Now that is the key Just ask for something that doesn’t even exist and it creates it specifically for you ask it for a research mode where it checks a document claims against real research papers Super good ask for a local AI lab that monitors your token speed and GPU memory doing video production ask for a storyboard and for an agent for planning your shots This is incredible.For it does all this while it is incredibly lean and efficient, you can save some time and money using it. brilliantt. Okay, so how the heck did they do that, What is this black magic, De fellow Scs. This is two minute papers with Doctor. Carri onna iffa here. Well, it’s not just finger practice, We have a proper 88 page paper describing the background of it, And I am going to give you some beautiful hieroglyphs. and then.Actually try to explain what they mean in simple words Now, all this tinkering sounds great, but it sooner or later will have the program fall apart. So why is this not falling apart Well, look at this beauty this beautifully says that with every change comes clean up instructions and the system remembers them automatically no components can be safely removed Everything is reversible and the key is that.😊It is baked deeply into the system and an additional tasty tidbit for you brilliant fellow scholars here is another clever part the uno machinery can live beside the original action without changing the action itself so you hand over your code at the code check and you get a ticket the ticket is separate from the code but gives the system what it needs to revert this action later.Okay so where does this put us Well As are getting so smart and so fast that the operating system around them should no longer be fixed It is now able to recreate it on the fly and tailored specifically to you that is unbelievably amazing Thank you so much and only days after release it already has hundreds of plugins by you brilliant fellow scholars.😊All this locally on your own machine or on Lambda No tracking no games with token limits What a time to be alive and hit the bell if you enjoyed this I use Lambda to reproduce AI research papers often in minutes It’s also great to train your own models or fine tune and existing one run inference or text2 image or video easyas P running a deeps chatt or agent super fast super reliable.Lambda gives you powerful NviIdia GPUs to run your own experiments, I test ideas from the papers I cover and moments later results, love it seriously try it out now at Lambda.ai/papers.😊
我太喜欢这个创意了。这是一个能自我编写的计算机程序。只需提出一个尚不存在的需求，它就能自我扩展，打造出你需要的AI。那么，这到底是什么呢？DeepSeek为我们提供了令人惊叹的免费开源权重AI系统，现在又推出了一个免费开源的工具框架。正是这个框架赋予了AI“手脚”，让它真正能够为你做事。不过等等，工具框架并不是什么新鲜事。有Piey，有OpenCode。这有什么不同？为什么要用它？原因有四点：第一，用户界面可以完全重写。这就是宣传视频里那只飞行的鲸鱼，或者说“把蛇装进框架”的由来。顺便说一句，“把蛇装进框架”可不是什么常用词，但在互联网的这个小圈子里，这再正常不过了。欢迎来到“两分钟论文”。第二，框架内的智能体也可以定制。你看，这里添加了一个代码审查模式，让AI检查代码库、找出问题并按严重程度进行排序。这完全是即兴创建的。所以，每个主要部分都可以重写。第三，也是最重要的一点。各位优秀的学者们，请坐稳扶好，因为意识到这一点的不是你们😊，而是程序在自我重写！这才是关键所在。只需提出一个根本不存在的需求，它就会专门为你创造出来。让它开启研究模式，将文档中的主张与真实研究论文进行比对，效果超棒；让它搭建一个本地AI实验室，在做视频制作时监控你的token速度和GPU显存；让它生成故事板，并安排一个智能体来规划你的镜头。这简直不可思议。而且它在做所有这些事的同时，还保持着极高的精简和高效，能为你节省不少时间和金钱。太棒了。那么，他们到底是怎么做到的？这是什么黑魔法？各位优秀的学者们。这里是“两分钟论文”，我是Karoly Zsolnai。这可不是随便敲敲键盘就搞定的，我们有一份长达88页的正规论文详细描述了其背景。接下来我会给大家展示一些漂亮的“象形文字”，然后再试着用通俗易懂的语言解释它们的含义。这些修修补补听起来很棒，但迟早会让程序崩溃。那为什么这个程序没有崩溃呢？看看这个精妙的设计，它完美地说明了每次修改都会附带清理指令，系统会自动记住这些指令，没有任何组件可以被随意移除，一切都是可逆的。关键在于😊，这种机制深深植根于系统之中。另外，各位优秀的学者们，再给大家分享一个美味的小彩蛋，这里还有另一个巧妙的部分：撤销机制可以与原始操作并存，而不改变操作本身。所以，在代码检查时你提交代码并获得一个凭证，这个凭证独立于代码，但能让系统掌握后续撤销该操作所需的信息。那么，这让我们处于什么境地呢？随着AI变得越来越聪明、越来越快，围绕它们的操作系统也不应再是一成不变的。现在，它能够即时重建系统，并专门为你量身定制，这简直令人难以置信。非常感谢大家，发布仅几天，各位优秀的学者们就已经为它开发了数百个插件。😊所有这些都可以在你自己的本地机器或Lambda上运行。没有追踪，没有在token限制上玩套路。生逢其时啊！如果喜欢这期视频，请点击小铃铛。我经常使用Lambda来复现AI研究论文，通常几分钟就能搞定。它也非常适合训练你自己的模型，或微调现有模型，运行推理、文生图或文生视频，简直易如反掌，运行DeepSeek聊天或智能体也是超级快、超级可靠。Lambda为你提供强大的NVIDIA GPU来运行你自己的实验，我测试我所讲解论文中的想法，片刻之后就能看到结果，真的超爱。说真的，现在就去Lambda.ai/papers试试吧。😊