OpenAI’s Operator can surf the web for you

OpenAI has begun previewing a new tool called Operator that can navigate within a web browser. According to a blog post published Thursday, the software is powered by what the company calls a Computer-Using Agent. “CUA is trained to interact with graphical user interfaces (GUIs) — the buttons, menus, and text fields people see on a screen — just as humans do,” says OpenAI of the model. “This gives it the flexibility to perform digital tasks without using OS- or web-specific APIs.“

The current release of Operator builds on OpenAI’s GPT-4o model. It combines the vision capabilities of that algorithm with “advanced reasoning” trained through reinforcement learning. Operator has the ability to “break tasks into multi-step plans and adaptively self-correct when challenges arise.” According to OpenAI, that capability represents the next stage in AI development.

Operator can interact with a variety of websites, including Instacart's ordering platform.  Operator can interact with a variety of websites, including Instacart's ordering platform.

Instacart

As with past research previews, OpenAI warns that Operator is “still early and has limitations,” and that it won’t “perform reliably in all scenarios just yet.” For instance, depending on the complexity of the task and interface involved, the agent greatly benefits from the user taking a few extra moments to write a more detailed prompt. Per The Verge, Operator will give the user control if it ever gets stuck on a task. It will also hand control over whenever a website asks for sensitive information, including login credentials. The company says it designed the tool to “refuse harmful requests and block disallowed content.”

ADVERTISEMENT

Advertisement

OpenAI is making Operator first available to users of its $200 per month ChatGPT Pro subscription. It is also partnering with companies like Instacart to offer the agent on their platforms, though there again you’ll need a ChatGPT Pro subscription to test the integration.

Operator joins a growing list of AI agents that can either navigate a web browser or an entire operating system. Anthropic was the first to offer the capability with the release of its Claude 3.5 Sonnet model in October, followed more recently by Google with its Gemini 2.0 model and Project Mariner.

If you buy something through a link in this article, we may earn commission.

Related Posts

The Nintendo Switch 2 has been revealed, here’s everything we know so far

As the world turns, so do the console generations. The Nintendo Switch is over seven years old, so it’s due for a refresh. Nintendo Switch 2 rumors have been swirling…

Read more

How to Responsibly Dispose of Your Electronics (2025)

Whether you have an old phone languishing in a desk drawer or a broken laptop gathering dust in the back of a closet, there will never be a better time…

Read more

The Beats Studio Pro headphones are back on sale for $180

There’s a reason I didn’t pick up my first pair of over-ear headphones until last year: they’re expensive. But, that’s where nice sales come in handy. And, there’s a very…

Read more

Can You Still Use A Laptop That Has A Broken Screen?

We may receive a commission on purchases made from links. rawf8/Shutterstock While laptops from reliable brands like Dell and Apple typically land on the higher end of the price spectrum,…

Read more

Therabody PowerDot 2.0 Duo Review: Can’t Connect to the App

Testing fitness gear for WIRED means I work out six days a week, sometimes twice daily. So when I got my hands on the PowerDot 2.0 Duo, I was excited…

Read more

USPS suspends all packages from China, including e-commerce purchases

The United States Postal Service has temporarily stopped accepting inbound parcels from China and Hong Kong, and according to Wired, it’s already causing huge problems with e-commerce shipments to the…

Read more

Leave a Reply