DeepSeek 开源可自我升级的 AI 工具链
DeepSeek’s AI Just Learned To Upgrade Itself
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? Deep Seek has given us amazing free and open weights 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. Harnesses are not new. There's Spy, there's Open Code.
我超爱这个想法。这是一个能自我编写的计算机程序。只要提出一个尚不存在的东西，它就能凭空出现。可以说，这是一个自我扩展的AI。好了，那这到底是什么呢？Deep Seek 给了我们惊艳的免费开放权重AI系统，现在又有了一个免费开源的工具框架。这就像是给AI装上了手脚，让它能真正为你做事。但是，等等，工具框架并不新鲜。有Spy，有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. Two, the agents inside the harness can also be customized.
这有什么不同？为什么要用它？嗯，有四点。第一，用户界面可以完全重写。这就是宣传视频里那个飞鲸或者把蛇放进框架里的东西。顺便说一句，把蛇放进框架，这可不是你经常用的说法，对吧？但在互联网的这个角落，这很正常。欢迎来到Two Minute Papers。第二，框架内部的智能体也可以定制。
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 to your papers, fellow scholars, because it's not you who rewrites the program, 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.
这里添加了一个代码审查模式，它告诉AI查看代码库，找出问题，并按严重程度排序。这完全是即兴想出来的。所以，每个主要部分都可以重写。但第三点，这是最重要的。现在，各位学者，请抓紧你们的论文，因为不是你来重写程序，而是程序自我重写。这才是关键。只要提出一个甚至不存在的东西，它就会专门为你创造出来。
Ask it for a research mode where it checks a document's 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 [clears throat] for a storyboard and for an agent for planning your shots. This is incredible. Four, it does all this while it is incredibly lean and efficient. You can save some time and money using it. Brilliant. Okay, so how the heck did they do that?
让它创建一个研究模式，用来对照真实研究论文检查文档中的声明。超级棒。让它创建一个本地AI实验室，监控你的令牌速度和GPU内存。做视频制作？请[清嗓子]让它创建一个故事板和一个规划镜头的智能体。这太不可思议了。第四，它在做到这一切的同时，还极其精简高效。用它还能节省时间和金钱。太棒了。好了，那他们到底是怎么做到的呢？
What is this black magic? Dear fellow scholars, this is Two Minute Papers with Dr. Károly Zsolnai-Fehér. 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?
这是什么黑魔法？亲爱的各位学者，这里是Károly Zsolnai-Fehér博士主持的Two Minute Papers。嗯，这不仅仅是手指练习。我们有一份完整的88页论文描述了它的背景。我要给你们展示一些漂亮的象形文字，然后试着用简单的语言解释它们的含义。现在，所有这些修修补补听起来很棒，但迟早会让程序崩溃。那么，为什么它不会崩溃呢？
Well, look at this beauty. This beautifully says that with every change comes clean up instructions and the system remembers them automatically. New 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 undo machinery can live beside the original action without changing the action itself.
看这个漂亮的东西。它优美地表明，每一次变更都附带清理指令，系统会自动记住这些指令。新组件可以安全移除。一切皆可逆。关键在于，这一点已深深融入系统之中。另外，给各位聪明的学者们一个额外的小惊喜，这里还有另一个巧妙之处。撤销机制可以紧邻原始操作存在，而无需改变操作本身。
So, you hand over your coat at the coat check and you get a ticket. Yes, the ticket is separate from the coat but gives the system what it needs to revert this action later to get your coat back. Okay, so where does this put us? Well, AIs 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 tailor it specifically to you. That is unbelievably amazing.
所以，你在衣帽间交出外套，拿到一张票。没错，票与外套是分开的，但它给了系统日后撤销此操作、取回外套所需的信息。好了，这让我们处于什么位置呢？嗯，人工智能变得如此聪明、如此迅速，以至于围绕它们的操作系统不应再是固定不变的。它现在能够即时重建，并专门为你量身定制。这简直令人难以置信。
Thank you so much. And only days after release, it already has hundreds of plugins by you brilliant fellow scholars. So, run all this locally on your own machine or on Lambda. No tracking, no games with token limits. What a time to be alive. Subscribe 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 an existing one.
非常感谢。而且发布仅几天后，它就已经有了数百个由你们这些聪明的学者开发的插件。所以，在你自己的机器上或Lambda上本地运行这一切。无追踪，无令牌限制的把戏。生逢其时啊。如果你喜欢这个视频，请订阅并点击铃铛。我经常用Lambda在几分钟内复现AI研究论文。它也非常适合训练你自己的模型或微调现有模型。
Run inference or text-to-image or video, easy-peasy. Running a deep fake chatbot or agent, super fast, super reliable. Lambda gives you powerful Nvidia 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.
运行推理或文本转图像或视频，易如反掌。运行深度伪造聊天机器人或代理，超快、超可靠。Lambda为你提供强大的Nvidia GPU来运行你自己的实验。我测试我报道的论文中的想法，片刻之后，结果就出来了。太喜欢了。说真的，现在就试试吧，访问lambda.ai/papers。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力