OpenAI launched ChatGPT Work on 9 July and has been updating it aggressively since then. It is a confusing but powerful product. Here is what I have worked out so far.
It is two different products
The version running in the cloud is the more interesting one. You access this via chatgpt.com or the mobile apps. I will call this Work Cloud.
Installing the desktop app, formerly known as Codex, gives you access to a version that runs on your machine. It can read files and execute programs locally. I will call this Work Local. It feels like the old Codex rebranded to look less daunting to non-developers.
I will focus entirely on Work Cloud for this article.
It requires a paid subscription
Both versions are currently restricted to subscribers paying $20 a month or more. Free users and those on the $8 Go plan cannot access it.
It has capabilities Chat lacks
The interface presents Work as a separate tab next to Chat:
The obvious question is when to use Chat and when to use Work. OpenAI’s official answer is:
Use Chat when you want an answer, explanation, brainstorm, or short draft. Use ChatGPT Work when you want ChatGPT to complete a task with a clear outcome, such as a brief, deck, analysis, recurring update, workflow, or file you can review and use.
I find this distinction entirely useless. I have been using regular ChatGPT for all those categories for years.
The better question is what features Work has that Chat does not.
After extensive experimentation, I have mostly identified these:
- Options to use Luna and Terra models instead of Sol
- A code execution environment with internet access
- A headless Chrome browser
- A persistent filesystem shared between sessions
- The ability to publish ChatGPT Sites
- The ability to run sub-agent sessions with Sol, Luna, and Terra
- Scheduled prompt automations
Model selection
Work allows you to pick GPT-5.6 Sol, Luna, or Terra, each with Light, Medium, High, Extra High, Max, or Ultra reasoning levels. You can also select GPT-5.5 at Light, Medium, High, or Extra High.
These appear to be the same models available through the OpenAI API.
Chat offers a different selection: 5.6 Instant, Medium, High, Extra High, and Pro. It does not explain if these are Luna, Terra, or Sol. I assume Sol. 5.6 Pro appears exclusive to Chat, with no equivalent in Work.
My current understanding from using Codex is that Ultra is a special mode that more eagerly delegates to sub-agents.
I believe ChatGPT Work sessions are billed against your Codex allowance, while ChatGPT Chat sessions get their own, separate allowance. This may explain the model availability differences.
Code execution with internet access
As a long-time fan of the Code Interpreter pattern, pioneered by OpenAI in 2023, this is by far the most exciting feature of ChatGPT Work Cloud for me.
The code execution environment can now talk to the rest of the internet.
ChatGPT Chat cannot do this. If you ask it to install additional software packages or interact with websites, access will be blocked by the container proxy.
Weirdly, back in January it gained the ability to install packages, but that does not seem to work any more. I wish they had better changelogs.
Claude’s equivalent container has allowed restricted internet access since it launched last September. Claude can install packages from PYPI and NPM and clone repositories from GitHub. But that is about it: the allowlist of domains is very short.
ChatGPT Work allows a whole lot more. It can be configured with a specific list of allowed domains, but the default appears to be open to all.
This makes Work a useful tool. You can have it clone GitHub repositories, install their dependencies, then use them to interact with the rest of the web.
A full, headless Chrome browser
Another killer feature of ChatGPT Work is the browser tool. ChatGPT Work can launch a full Chrome instance, load websites, fill out forms, and take screenshots.
It can even run JavaScript against the DOM of those pages. I prompted:
Load simonwillison.net in your browser and extract the headings using JavaScript
ChatGPT Work fired up a browser instance and ran the code:
await tab.playwright.evaluate(() => {
return Array.from(document.querySelectorAll("h1,h2,h3,h4,h5,h6"), heading => {
level: heading.tagName.toLowerCase(),
text: heading.innerText.trim().replace(/\s+/g, " "),
id: heading.id || null
});
});This feels a lot like my shot-scraper javascript tool, only now I can access it on my phone.
A persistent, shared filesystem
ChatGPT Chat gets a fresh filesystem for each chat session. These cannot be accessed from any other session.
In ChatGPT Work each session gets its own scratch folder, named something like /workspace/scratch/e00a0a017944, but each of those are persisted across sessions, so you can access files from previous chats. I have 171 folders in /workspace/scratch right now.
As far as I can tell that /workspace volume is mounted to all Work sessions that are currently running. File edits from one can be instantly seen by the others. They do not seem to share the same process space though, and localhost servers running in one cannot be accessed from another.
ChatGPT Sites
ChatGPT Work has the ability to build and deploy entire websites, using Cloudflare Workers. These can have HTML and JavaScript and can run server-side features too, including stateful features on top of Cloudflare D1 and R2.
Here is a simple site I built with this feature:
london-pelicans-in-her-piety.simonw.chatgpt.site
Source Read original →
