Skip to main content

What is ChatGPT Code Interpreter and how to use it

The latest buzz around OpenAI’s ChatGPT chatbot is that it can now access the internet and run plug-ins. You need to be a ChatGPT Plus subscriber, but if you are, the feature is widely available, and it’s gotten a lot of people very excited. Why? Because it lets ChatGPT do a whole lot more. In fact, some of its most dedicated users are already putting it to work in new and exciting ways.

From visualizing every lighthouse in America to converting images to text and even doing some video editing, ChatGPT’s code interpreter gives it all kinds of exciting new abilities.

Recommended Videos

What is ChatGPT Code Interpreter?

The ChatGPT Code Interpreter is one of a handful of new plug-ins that you can add to the standard ChatGPT experience to augment and improve its abilities. It makes it possible to run Python code within a chat with ChatGPT, with additional options to upload and download files. You can then further adjust the code, or have ChatGPT make its own changes and suggestions.

It’s already been used to collate big collections of data, such as mapping out where every lighthouse is in America. Having it perform basic video-editing functions was particularly impressive:

Basic video editing in ChatGPT, converting uploaded GIF to longer MP4 with slow zoom: pic.twitter.com/fmCPUBkedD

— Riley Goodside (@goodside) April 30, 2023

The most used function for the code interpreter for now is data analysis, since ChatGPT can do that very quickly and with great nuance. This is helping hobbyists and professionals look at large quantities of data in new and intriguing ways, and they’re having a lot of fun with it. Ethan Mollick at OneUsefulThing had it write programs to create unique GIFs and write PDF documentation to explain its workings.

He also highlighted how ChatGPT can, with Code Interpreter, become its own data analyst. It doesn’t just extract information from data — it can decide what is important to extract from it, potentially opening up some very exciting and completely unthought-of uses for all the existing data that has been collected.

The real potential for ChatGPT’s code interpreter is likely still to be discovered. Perhaps you could find a new, novel use for it?

How do you access ChatGPT Code Interpreter?

The ChatGPT Code Interpreter is one of many plug-ins now available to ChatGPT users. However, there are still some hurdles to get over.

For starters, ChatGPT creator OpenAI restricts plug-in access to ChatGPT Plus subscribers, so you’ll need to pay the $20-a-month subscription for access. Unfortunately, that still doesn’t guarantee you access to the code interpreter, as it is slowly being rolled out to all ChatGPT Plus users.

Assuming you are one of the lucky ones with access, here’s how to use it:

Step 1: Log in to ChatGPT on the OpenAI website.

Step 2: Select Settings.

Step 3: In the bottom-left of the window, next to your login-name, select the three dot menu.

Step 4: Select the Beta features menu and toggle on Plug-ins. If you want ChatGPT to be able to access the internet too, toggle on Web browsing. Alternatively, you can also use a Chrome extension.

Step 5: Close the menu and look for the small drop-down menu under the language model selector. Select it.

Step 6: Select Plugin Store.

Step 7: Select All plug-ins.

Step 8: Search through the list for the Code Interpreter and select Install.

Now, when you interact with ChatGPT, you’ll have the option to do so with the Code Interpreter plug-in enabled.

How to use ChatGPT Code Interpreter

How you actually use the ChatGPT Code Interpreter is up to you. OpenAI says that it’s particularly good at solving mathematical problems (both quantitative and qualitative), performing data analysis and visualization, and converting files between formats. You can have it do any of these by uploading files containing the kind of data it likes to chew over to see what it comes up with.

You can give it specific parameters for what you’re looking for, or leave it more open-ended.

ChatGPT Code Interpreter AI Plugin Demo

Have a go with it and see what you come up with.

Jon Martindale
Jon Martindale is a freelance evergreen writer and occasional section coordinator, covering how to guides, best-of lists, and…
OpenAI’s Advanced Voice Mode can now see your screen and analyze videos
Advanced Santa voice mode

OpenAI's "12 Days of OpenAI" continued apace on Wednesday with the development team announcing a new seasonal voice for ChatGPT's Advanced Voice Mode (AVM), as well as new video and screen-sharing capabilities for the conversational AI feature.

Santa Mode, as OpenAI is calling it, is a seasonal feature for AVM, and offers St. Nick's dulcet tones as a preset voice option. It is being released to Plus and Pro subscribers through the website and mobile and desktop apps starting today and will remain so until early January. To access the limited-time feature, first sign in to your Plus or Pro account, then click on the snowflake icon next to the text prompt window.

Read more
One of ChatGPT’s latest features comes to the free tier
ChatGPT's Canvas screen

In October, OpenAI debuted its Canvas feature, a collaborative interface that visually previews the AI response to the user's writing or coding request. However, it was only made available as a beta feature for Plus and Teams subscribers. On Tuesday, the company announced that it is bringing Canvas to all users, even at the free tier.

While one could easily mistake Canvas for a blatant knockoff of Anthropic's Artifacts feature, OpenAI is also incorporating a swath of new capabilities into Canvas. For one, Canvas is now integrated directly into the GPT-4o model so that it runs natively within ChatGPT, eliminating the need to select it specifically from the model-picking list.

Read more
ChatGPT unveils Sora with up to 20-second AI video generation
An AI generated image of a woman who walks the streets of Tokyo.

OpenAI has been promising to release its next-gen video generator model, Sora, since February. On Monday, the company finally dropped a working version of it as part of its "12 Days of OpenAI" event.

"This is a critical part of our AGI roadmap," OpenAI CEO Sam Altman said during the company's live stream.

Read more