Q: 什么是代理 AI，它与 ChatGPT 和 Claude 等生成式 AI 模型有何不同?
Q: What is agentic AI and how is it different from generative AI models like ChatGPT and Claude?
A: Agentic AI 是在世界中采取行动的 AI。这些操作可以是物理操作,，例如机器人操作,，也可以是数字操作,，例如预订航班。另一方面,我们认为生成人工智能是编故事,诗歌,艺术,和图像,而不是为我们采取行动。
A: Agentic AI is AI that takes actions in the world. These actions could be a physical action, like robotic manipulation, or a digital action, like booking a flight. On the other hand, we think of generative AI as making up stories, poems, art, and images, rather than taking actions for us.
“agent” 这个词只是一个品牌名称。它通常意味着人工智能将帮助人们与应用程序,、网站, 或物理世界进行交互。我们今天遇到的大多数代理都是数字代理,，例如可以与您讨论产品投诉的客户服务代理。
The word “agent” is just a brand name. It usually means AI that is going to help people interact with an application, a website, or the physical world. Most agents we encounter today are digital agents, like customer service agents you can talk with about product complaints.
大多数提供代理的公司在底层都使用相同的几个人工智能模型，让他们能够采取行动并记住发生的事情。代理从基本的生成 AI 系统, 开始，如 Claude, 的核心。然后，公司为其产品或应用程序围绕该基础模型放置不同的包装器。这些包装器可能是代理可以使用, 的特定工具，并且这些工具取决于应用程序。也许代理可以访问计算器，因此它可以解决数学问题,，或者它可以访问更复杂的硬盘驱动器和操作系统，以便它可以记住公司’的财务数据和过去的业务谈判。
Most companies that offer agents use the same few AI models under the hood and give them the ability to take actions and remember what happened. An agent starts with a fundamental generative AI system, like Claude, at the core. Then companies put different wrappers around that foundation model for their product or application. Those wrappers might be specific tools that agent can use, and those tools depend on the application. Maybe the agent has access to a calculator so it can solve math problems, or maybe it has access to a more complicated hard drive and operating system so it can remember a firm的 financial data and past business negotiations.
开发代理人工智能的最大挑战来自缺乏训练数据。如果我想创建一个可以上网并为我预订航班的系统,，这看起来非常简单。但我们没有’t 有大量数据详细说明如何执行此操作— 将鼠标移到哪里, 单击哪些按钮, 如果出现问题该怎么办, 或者如何打电话给某人并协商机票价格。训练这样的系统的一种方法是让 AI 代理访问航空公司网站, 尝试,，看看哪些有效，哪些无效’。这些环境很难建模,，因此代理必须通过反复试验来学习。
The biggest challenge in developing agentic AI comes from a lack of training data. If I want to create a system that can go online and book a flight for me, that seems pretty simple. But we don’t have a lot of data that spells out exactly how to do that — where to move the mouse, which buttons to click on, what to do if something goes wrong, or how to call somebody and negotiate about the price of the airline ticket. One way to train a system like this is to have the AI agent visit airline websites, try things out, and see what works and what doesn’t work. These environments are hard to model, so often the agent must learn by trial and error.
Q: 代理 AI 有哪些有前景的应用?
Q: What are some promising applications of agentic AI?
A: 我认为我们 最成功的领域是编码代理。这是从生成人工智能演变而来的。人们在代码, 上训练语言模型，然后他们可以预测人类会做什么来解决编码问题。此外, 代理可以通过反馈循环来学习做到这一点，在反馈循环中尝试不同的解决方案并检查是否得到了正确的答案。只要它可以检查答案,，人工智能代理就可以执行这个试错循环，直到找出一个好的策略。
A: I think the area where we’ve seen the most success has been with coding agents. This is something that evolved from generative AI. People trained language models on code, and then they can predict what a human would do to solve a coding problem. In addition, an agent can learn to do this by going through a feedback loop where it tries out different solutions and checks to see if it got the answer right. As long as it can check the answer, the AI agent can perform this trial-and-error loop until it figures out a good strategy.
但自动化决策与简单地协助和通知人类之间始终存在平衡。分析人工智能方法,，例如帮助预测决策可能结果,的系统，本质上不是代理,，但对人类决策者来说信息量很大。对于高风险或安全关键, 的情况，例如医学, 安全, 高级业务策略, 等,，该技术可能还没有准备好让人工智能完全自动化这些流程,，或者我们甚至可能对此感到不舒服。
But there is always a balance between automating decision making versus simply assisting and informing humans. Analytical AI methods, like the systems that help predict possible outcomes of decisions, are not agentic in nature, but are very informative to human decision-makers. For cases that are either high-stakes or safety-critical, like medicine, security, high-level business policies, etc., the technology might not be ready for AI to completely automate those processes, or we might not even be comfortable with that.
Q: 使用人工智能代理时我们应该考虑哪些风险?
Q: Are there risks we should be thinking about when using AI agents?
A: 一个很大的风险领域来自这样一个事实：通常很容易让代理为您做某些类型的工作。通过编码代理,，您可以“vibe 代码”，只需要求代理为您创建一个代码,，这样您就不必 自己完成艰苦的工作。存在很大的风险，, 因为这太容易了，, 人们不会投入足够的精力来验证它是否在做正确的事情。将引入错误, 私人数据将被泄露 — 这已经发生了。
A: One big risk area comes from the fact that it is often very easy to get agents to do certain types of work for you. With coding agents, you can “vibe code” and just ask the agent to make a code for you, so you don’t have to do the hard work yourself. There is a big risk that, because it is so easy, people will not put enough effort into verifying that it is doing the right thing. Bugs will be introduced, private data will get leaked — this is already happening.
代理’并不完美,，因为他们可能会犯错误，因为他们没有经过良好的训练，并且不’不知道该做什么。但即使它们非常有能力,，如果人类没有 正确使用它们或给它们的指令太模糊,，人工智能代理也可能会因为人类犯了错误而犯错误。如果人类较少思考所有后果,，我认为我们可能更容易犯这些错误。
Agents aren’t perfect, in the sense that they might make mistakes because they are not well-trained and don’t know what to do. But even if they are very competent, if a human doesn’t use them appropriately or gives them an instruction that is too vague, the AI agent could make a mistake because the human made a mistake. If humans are less involved in thinking through all the consequences, I think we might be more prone to making those mistakes.
另外一个方面是去技能化的风险。目前尚不清楚这会走多远,，但当我们依靠代理来完成我们的作业,、编码,和数学,时，我们可能会失去自己完成这些工作的能力,，而且我们可能会很快失去这种能力，因为技术尚未准备好完全自动化这些过程。
An additional aspect is the risk of de-skilling. It is unclear how far this will go, but when we are relying on agents to do our homework, our coding, and our math, we might lose the ability to do that ourselves, and we might lose that ability too soon because the technology is not yet ready to fully automate those processes.
Q: 智能 AI 的未来会怎样?
Q: What does the future hold for agentic AI?
A: What we think of now as agentic AI refers to large language models using tools to interact with digital and physical systems. One obvious limitation is that, under the hood, these have the architecture of a language model and are trained on text data. To make even more powerful AI agents, we might need to model videos, physical forces, time series, radar scans, and other modalities.我们可能需要具有根本不同架构的模型，可以处理连续数据, 高维数据, 随机数据, 等等。
A: What we think of now as agentic AI refers to large language models using tools to interact with digital and physical systems. One obvious limitation is that, under the hood, these have the architecture of a language model and are trained on text data. To make even more powerful AI agents, we might need to model videos, physical forces, time series, radar scans, and other modalities. We might need to have models with fundamentally different architectures that can handle continuous data, high-dimensional data, stochastic data, and so on.
但, 另一方面，, 也许是一个非常好的编码模型，可以充当傀儡师，与传感器,、执行器, 和 Web API? 进行交互。也许,，一旦你拥有一个能够理解数学, 语言, 和代码, 的超级智能推理系统，你就可以给它一个摄像头和一个键盘，它会弄清楚在空间域中要做什么。人工智能的下一波浪潮是克劳德（Claude）拥有传感器,、执行器,和工具,，还是会以一种新的方式从头开始构建?，这’是许多人工智能领域的人现在正在努力解决的大问题。
But, on the other hand, maybe an extremely good coding model could act as a puppeteer to interface with sensors, actuators, and web APIs? Perhaps, once you have a super-smart reasoning system that understands math, language, and code, you can give it a camera and a keyboard and it will figure out what to do in the spatial domain. Is the next wave of AI just going to be Claude with sensors, actuators, and tools, or is it going to be something built in a new way from the ground up? That的 the big question a lot of people in AI are grappling with right now.