How I use LLMs

章节 1：引言与当前 LLM 生态系统概览

📝 本节摘要：

Andrej Karpathy 在本节开篇点明了本期视频的核心目标：从上一期的底层原理（训练与心理学）转向大模型的实际应用。他将 ChatGPT 视为该领域的“鼻祖”和当前功能最丰富的标杆，同时也详细介绍了 2025 年蓬勃发展的 LLM 生态系统，包括 Google 的 Gemini、Anthropic 的 Claude、xAI 的 Grok 等竞争对手。此外，他还分享了如何通过 Chatbot Arena 等排行榜来追踪不同模型的性能表现。,,

[原文] [Andrej Karpathy]: hi everyone so in this video I would like to continue our general audience series on large language models like chpd now in the previous video deep dive into llms that you can find on my YouTube we went into a lot of the underhood fundamentals of how these models are trained and how you should think about their cognition or psychology

[译文] [Andrej Karpathy]: 大家好，在这个视频中，我想继续我们关于像 ChatGPT 这样的大型语言模型的普通受众系列。在之前的视频《深入剖析 LLM》（你可以在我的 YouTube 频道找到）中，我们深入探讨了许多关于这些模型是如何训练的底层原理，以及你应该如何思考它们的认知或心理学。

[原文] [Andrej Karpathy]: now in this video I want to go into more practical applications of these tools I want to show you lots of examples I want to take you through all the different settings that are available and I want to show you how I use these tools and how you can also use them uh in your own life and work so let's dive in

[译文] [Andrej Karpathy]: 而在这个视频中，我想深入探讨这些工具的更实际的应用。我想向你们展示大量的例子，带你们了解所有可用的不同设置，并向你们展示我是如何使用这些工具的，以及你们如何在自己的生活和工作中通过使用它们。那么，让我们开始吧。

[原文] [Andrej Karpathy]: okay so first of all the web page that I have pulled up here is chp.com now as you might know chpt it was developed by openai and deployed in 2022 so this was the first time that people could actually just kind of like talk to a large language model through a text interface and this went viral and over all over the place on the internet and uh this was huge

[译文] [Andrej Karpathy]: 好的，首先，我这里打开的网页是 chatgpt.com。正如你们可能知道的，ChatGPT 是由 OpenAI 开发并在 2022 年部署的。这是人们第一次能够真正通过文本界面与大型语言模型进行交谈，它迅速走红并席卷了整个互联网，这在当时是一件大事。

[原文] [Andrej Karpathy]: now since then though the ecosystem has grown a lot so I'm going to be showing you a lot of examples of Chachi PT specifically but now in 2025 uh there's many other apps that are kind of like Chachi PT like and this is now a much bigger and richer ecosystem

[译文] [Andrej Karpathy]: 不过从那时起，这个生态系统已经有了巨大的增长。所以我虽然会具体展示很多 ChatGPT 的例子，但在 2025 年的今天，还有许多其他类似 ChatGPT 的应用程序，这是一个规模更大、内容更丰富的生态系统。

[原文] [Andrej Karpathy]: so in particular I think Chachi PT by openai is this Original Gangster incumbent it's most popular and most featur rich also because it's been around the longest but there are many other kind of clones available I would say I don't think it's too unfair to say but in some cases there are kind of like unique experiences that are not found in chashi p and we're going to see examples of those

[译文] [Andrej Karpathy]: 特别是，我认为 OpenAI 的 ChatGPT 是这个领域的“元老级”（Original Gangster）现任霸主，它是最受欢迎且功能最丰富的，也因为它存在的时间最长。但现在有许多其他的“克隆版”可用——我想这样说也不算太不公平——但在某些情况下，它们提供了一些 ChatGPT 中找不到的独特体验，我们将看到这方面的例子。

[原文] [Andrej Karpathy]: so for example big Tech has followed with a lot of uh kind of chat GPT like experiences so for example Gemini met and co-pilot from Google meta and Microsoft respectively and there's also a number of startups so for example anthropic uh has Claud which is kind of like a chasht equivalent xai which is elon's company has Gro uh and there's many others

[译文] [Andrej Karpathy]: 举个例子，大型科技公司已经紧随其后，推出了许多类似 ChatGPT 的体验，比如 Google 的 Gemini、Meta 的（LLaMA相关产品）和 Microsoft 的 Copilot。还有许多初创公司，例如 Anthropic 推出了 Claude，它有点像 ChatGPT 的等价物；Elon 的公司 xAI 推出了 Grok；还有许多其他的。

[原文] [Andrej Karpathy]: so all of these here are from the United States um companies basically deep seek is a Chinese company and lchat is a French company Mistral now where can you find these and how can you keep track of them well number one on the internet somewhere but there are some leaderboards and in the previous video I've shown you uh chatbot arena is one of them

[译文] [Andrej Karpathy]: 这里提到的基本上都是美国公司。DeepSeek 是一家中国公司，Le Chat 是法国公司 Mistral 的产品。那么，你在哪里可以找到这些模型以及如何跟踪它们呢？第一，在互联网的某个地方；但也有一些排行榜，在之前的视频中我向你们展示过，Chatbot Arena（聊天机器人竞技场）就是其中之一。

[原文] [Andrej Karpathy]: so here you can come to some ranking of different models and you can see sort of their strength or ELO score and so this is one place where you can keep track of them I would say like another place maybe is this um seal Le leaderboard from scale and so here you can also see different kinds of eval and different kinds of models and how well they rank and you can also come here to see which models are currently performing the best on a wide variety of tasks

[译文] [Andrej Karpathy]: 在这里你可以看到不同模型的排名，看到它们的实力或 ELO 分数，这是你可以跟踪它们的一个地方。我想说另一个地方可能是 Scale 的这个 SEAL Leaderboards，在这里你也可以看到不同类型的评估、不同的模型以及它们的排名情况，你可以来这里看看哪些模型目前在各种任务上表现最好。

[原文] [Andrej Karpathy]: so understand that the ecosystem is fairly rich but for now I'm going to start with open AI because it is the incumbent and is most feature Rich but I'm going to show you others over time as well

[译文] [Andrej Karpathy]: 所以要明白，现在的生态系统相当丰富，但目前我将从 OpenAI 开始，因为它是现任霸主且功能最丰富，但我随着时间的推移也会向你们展示其他的模型。