最有趣的ai模式带代码解释器的chatgpt-凯发ag旗舰厅

利用人工智能实现数据分析民主化democratizing data analysis with ai

每个人everyone

code interpreter 延续了 openai 给事物起可怕名字的悠久传统，因为它可能对那些根本不编码的人最有用。它本质上允许最先进的人工智能（gpt-4）上传和下载信息，并在持久工作空间中为您编写和执行程序。这使得人工智能能够做以前无法做的各种事情，并以 chatgpt 无法做到的方式发挥作用。code interpreter continues openai’s long tradition of giving terrible names to things, because it might be most useful for those who do not code at all. it essentially allows the most advanced ai available, gpt-4, to upload and download information, and to write and execute programs for you in a persistent workspace. that allows the ai to do all sorts of things it couldn’t do before, and be useful in ways that were impossible with chatgpt.

具体来说，它为 ai 提供了一个解决问题的通用工具箱（通过用 python 编写代码）、一个可使用的大内存（您可以上传高达 100mb 的文件，并且这些文件可以是压缩形式），并以发挥大型语言模型优势的方式将该工具箱集成到 ai 中。这有助于解决以前版本的 chatgpt 存在的许多问题：specifically, it gives the ai a general-purpose toolbox to solve problems (by writing code in python), a large memory to work with (you can upload files up to 100mb, and those can be in compressed form) and integrates that toolbox into the ai in ways that play to the strengths of large language models. this helps address a number of problems that previous versions of chatgpt had:

• 它允许人工智能做数学（非常复杂的数学）并更准确地处理单词（比如实际计算段落中的单词），因为它可以编写 python 代码来解决大型语言模型在数学和语言方面的天然弱点。它非常擅长正确使用这个工具，如下所示。it allows the ai to do math (very complex math) and do more accurate work with words (like actually counting words in a paragraph), since it can write python code to address the natural weaknesses of large language models in math and language. and it is really good at using this tool appropriately, as you can see below.

• 它降低了幻觉和虚构的发生率。当人工智能直接使用 python 代码时，代码有助于保持它的“诚实”，因为如果代码不正确，python 就会生成错误。由于代码操作的是数据，而不是法学硕士本身，因此人工智能不会在数据中插入错误。这并不完美，人工智能仍然会产生幻觉（它通常似乎认为它可以看到它可以生成的图表，而这种 chatgpt 模式却看不到），但这些错误不太常见，并且不太可能影响代码或数据本身。it lowers hallucination and confabulation rates. when the ai directly works with python code, the code helps keep it “honest” sinces python generates errors if the code is not correct. and as the code manipulates the data, rather than the llm itself, there are no errors inserted into the data by the ai. this isn’t perfect, the ai still hallucinates (it often seems to think it can see the graphs it can generate, which this mode of chatgpt cannot), but these errors are less common, and less likely to impact the code or data itself.

• 它使人工智能更加通用。大量问题可以通过代码解决，gpt-4 非常擅长以新颖有趣的方式确定何时使用代码解释器。例如，我要求它it makes the ai much more versatile. a remarkable number of problems can be solved with code, and gpt-4 is very good at figuring out when to use code interpreter in novel and interesting ways. for example, i asked it to 用代码向怀疑者证明地球是圆的prove to a doubter that the earth is round with code，它提供了多个论证，将文本与代码和图像结合在一起。, and it provided multiple arguments, integrating the text with code and images.

• 您不必编写代码，因为它会为您完成所有工作。所有主要的法学硕士都会编写代码，但你必须自己运行和调试它，即使人工智能有所帮助。对于以前从未真正使用过 python 的人（比如我自己）来说，这很烦人，并且需要反复使用 ai 来纠正错误。现在，人工智能会纠正自己的错误并为您提供输出。you don’t have to code, because it does all the work for you. all the major llms write code, but you have to run and debug it yourself, even though the ai helps. for people who never really used python before (like myself) this was annoying, and involved going back and forth with the ai to correct errors. now, the ai corrects it own errors and gives you the output.

• 它为您提供更多人工智能时刻。任何使用过 gpt-4 的人都可能至少遇到过一些感觉机器里确实有鬼魂的时刻。我知道这是一种幻觉，法学硕士根本没有感知能力或思考能力，但那些时刻令人兴奋，有时甚至令人不安，让我们看到了更智能的人工智能可能带来的未来。在我玩过的所有人工智能系统中，代码解释器每次使用时都提供了最“奇怪”的时刻。我一直在收集很多例子，比如当我要求人工智能用it gives you more of those ai moments. anyone who has worked with gpt-4 has probably encountered at least a few moments where it felt like there was, indeed, a ghost in the machine. i know it is an illusion, and that llms are in no way sentient or thinking, but those moments are a thrilling, and sometimes unnerving, glimpses of possible futures with smarter ais. code interpreter provides the most “that’s weird” moments per use of any ai systems i have played with. i have been collecting a number of examples, such as when i asked the ai to ，或者 or 下面，您可以看到当我询问人工智能“使用您可用的绘图工具，通过创建图像来创建一个全新的模因时发生的情况。让它与你作为人工智能与人类合作的体验相关。”below, you can see what happened when i asked the ai “using the tools available to you to draw, create an entirely new meme by creating an image. make it relevant to your experience as an ai working with humans.”

因此，请将此视为使用这个新工具的邀请。作为一个切入点，这里是使用代码解释器处理数据的入门指南。so, take that as an invitation to play with this new tool. as one entry point, here is a getting started guide to using code interpreter with data.

代码解释器是一位令人印象深刻的数据科学家。在过去的几个月里，我一直在广泛使用它，它的运行水平非常先进，可以自动执行许多复杂的定量分析，并且能够采用非常复杂的数据方法。作为说明这一点的一种方式，我从一个有趣的数据集开始，这是code interpreter is an impressive data scientist. i have been using it extensively over the past months, and it is operating at a very advanced level, automating a lot of the complexity of quantitative analysis, and capable of very sophisticated approaches to data. as one way of of illustrating this, i started with a fun dataset, 。如果您想和我一起尝试这些步骤，您可以下载它。. you can download it if you want to try these steps with me.

只需点击加号按钮即可轻松上传数据，甚至是 zip 文件等压缩数据。您应该在数据中包含一个初始提示，但它可以非常小，我确实使用了it is easy to upload data, even compressed data like a zip file, by hitting the plus button. you should include an initial prompt with the data, but it can be pretty minimal, i literally used 这里是一些关于超级英雄力量的数据，仔细查看它并告诉我您发现了什么here is some data on superhero powers, look through it and tell me what you find并获得了良好的结果。如果您有数据字典，也可以将其粘贴进去。人工智能擅长仅从上下文中找出数据的含义和结构。 and got good results. if you have a data dictionary, you can just paste that in, too. the ai is good at figuring out the meaning and structure of the data from context alone.

您会注意到，代码解释器更多的是与人工智能进行对话，而不是提示制作。像分析师一样对待它，并与它交谈。事实上，只有两个真正的例外情况，提示制作似乎很重要。首先，人工智能有时会忘记它可以做一些事情（例如制作 gif 或 3d 绘图），而你可能需要鼓励它（“你可以制作 gif，请尝试”）。其次，你会希望人工智能改进自己的工作。只需要求它“对该结果进行进一步的测试”或“使该图表变得更好”通常会起作用。you will note that code interpreter is much less about prompt crafting than about having a conversation with the ai. treat it like an analyst, and talk with it. in fact, there are only two real exceptions where prompt-crafting seems to matter. first, the ai sometimes forgets it can do things (like make gifs or 3d plots) and you may need to encourage it (“you are able to make a gif, please try”). second, you will want the ai to improve on its own work. just asking it to “run further tests on that result” or “make this graph even nicer” will often work.

现在我们已经加载了数据，我们可以让 gpt 完成任何数据分析工作中最糟糕的部分：数据合并和清理。它会以一种相当复杂的方式自动处理这一切，但我发现直接询问通常会有所帮助，就像我在指导人类数据分析师一样。您还会注意到有关系统工作方式的一些非常重要的事情 - 它是无情的，通常会在发现错误时纠正自己的错误。例如，它会注意到列名称错误并修复该问题。尽管这令人印象深刻，但我仍然建议仔细检查结果和过程，而不是盲目相信人工智能。now that we have the data loaded, we can have gpt do the worst part of any data analysis job: data merging and cleaning. it will handle this all automatically in a quite sophisticated way, but i find it usually helps to ask directly, as if i was directing a human data analyst. you will also note something really important about the way the system works - it is relentless, usually correcting its own errors when it spots them. it notices, for example, that columns are misnamed and fixes that issue. impressive as this is, i would still recommend double-checking the results and process, rather than blindly trusting the ai.

现在，进行分析。人工智能似乎对分析方法很了解——值得阅读下面的交流来明白我的意思。我提示now, on to an analysis. the ai seems knowledgeable about analytical approaches - it is worth reading the exchange below to see what i mean. i prompted 我有兴趣进行一些预测建模，我们可以根据其他因素预测英雄可能拥有的能力。我们应该如何处理这个问题？i am interested in doing some predictive modelling, where we can predict what powers a hero might have based on other factors. how should we approach this? 它构建了一个随机森林分类器 - 酷！但您也可以明白为什么专家的监督很重要，因为我不同意它通过使用数值数据的方法来估算缺失数据的决定。我本来会放弃数据，但我可以要求人工智能改变其方法，或者讨论替代选项。and it built a random forest classifier - cool! but you can also see why it is important to have expert human oversight, since i would diagree with its decision to impute missing data by using the means for numerical data. i would have dropped the data instead, but i could ask the ai to change its approach, or discuss alternate options.

人工智能能够进行许多其他分析（毕竟，它“只是”编写 python 代码），但它选择有意义的分析方法的能力常常给我留下深刻的印象。例如，这是一个超级大国的网络分析，来自我只是提示the ai is capable of many other analyses (it is “just” writing python code, after all) but i was often impressed by its ability to select analytical approaches that made sense. for example, here is a network analysis of superpowers, that came from me just prompting 你可以进行另一个非常复杂和有趣的分析吗could you conduct another really sophisticated and interesting analysis：:

但 code interpreter 最令人印象深刻的一点是，它以非常人性化的方式对数据进行“推理”。当被问及网络分析的结果时，得出了有趣的结论：英雄通常拥有的一组能力本质上是视觉的（因为它们来自漫画书），适合某些原型，并且最适合构建持续的冒险。将数据和故事集成在一起的巧妙方法！but some of what makes code interpreter most impressive is that it “reasons” about data in ways that seem very human. when asked about the results of the network analysis, it came to interesting conclusions: the set of powers that heroes commonly had were visual in nature (because they were from comic books), fit certain archetypes, and were best suited to building continuing adventures. a neat way to integrate data and story together!

可视化的交互性水平仍在继续，您可以与人工智能来回请求改进和更改。例如，我提示the level of interactivity continues for visualizations, you can go back and forth with the ai asking for improvements and changes. for example, i prompted 创建一个交互式仪表板，其中至少包含 6 个富有洞察力的图表，其中包括一个 3d 图表。让仪表板美观。create an interactive dashboard with at least 6 insightful charts, including one in 3d. make the dashboard beautiful. 它生成了一个仪表板，但不完全是我想要的。所以我只能要求改变英语：it produced a dashboard, but not exactly what i wanted. so i was able to just ask for changes in english: 让这变得更好。您还会注意到make this better. include more names，它为我提供了一个, etc. you will also notice that it gave me a downloadable file for the的可下载文件（您可以在链接中尝试），我只是将其放入网络浏览器中并且它起作用了 - 可下载的输出是代码解释器的另一个巧妙技巧。 (you can try it at the link), which i just put in a web browser and it worked - downloadable outputs are another neat trick of code interpreter.

and a few more experiments i have done over the past months: 里，我还做了一些实验：3d 交互式情节、、、、、等等。 with a 3d interactive plot, building, ,, , , , and a besides.

这只是代码解释器的皮毛，我认为这是未来人工智能成为复杂知识工作的宝贵伴侣的最有力的案例。我在博士期间花了几周时间才能掌握的事情，人工智能在几秒钟内就完成了，而且错误通常比我对人类分析师的预期要少。人工监督仍然至关重要，但目前我不会在没有代码解释器的情况下进行数据项目。this is just scratching the surface of code interpreter, which i think is the strongest case yet for a future where ai is a valuable companion for sophisticated knowledge work. things that took me weeks to master in my phd were completed in seconds by the ai, and there were generally fewer errors than i would expect from a human analyst. human supervision is still vital, but i would not do a data project without code interpreter at this point.

但对我来说同样清楚的是，人类不会被代码解释器取代。相反，人工智能会做我们一直希望自动化做的事情——将我们从工作中最烦人、最重复的部分中解放出来，这样我们就可以专注于好的事情。通过简化分析的过程，我可以做更多、更深入、更令人满意的工作。我的时间变得更有价值，而不是更少，因为我可以专注于重要的事情，而不是死记硬背。代码解释器代表了迄今为止人工智能对工作的最清晰、积极的愿景：颠覆，是的，但颠覆会带来更好、更有意义的工作。我认为，对于我们所有人来说，重要的是要考虑如何对受人工智能影响的其他工作采取同样的方法。but it is just as clear to me that humans are not going to be replaced by code interpreter. instead, the ai does what we always hope automation will do - free us from the most annoying, repetitive parts of our job so we can focus on the good stuff. by simplifying the process of analysis, i can do more and deeper and more satisfying work. my time becomes more valuable, not less, as i can concentrate on what is important, rather than the rote. code interpreter represents the clearest positive vision so far of what ais can mean for work: disruption, yes, but disruption that leads to better, more meaningful work. i think it is important for all of us to think about how we can take this same approach to other jobs that will be impacted by ai.