OpenAI is greatly enhancing ChatGPT’s powers to enable web browsing and more.

Social Media Plug-ins:

OpenAI is adding support for plug-ins to ChatGPT — an upgrade that massively expands the chatbot’s capabilities and gives it access for the first time to live data from the web.

Up until now, ChatGPT has been limited by the fact it can only pull information from its training data, which ends in 2021. OpenAI says plug-ins will not only allow the bot to browse the web but also interact with specific websites, potentially turning the system into a wide-ranging interface for all sorts of services and sites. In an announcement post, the company says it’s almost like letting other services be ChatGPT’s “eyes and ears.”

OpenAI says it’s rolling out plug-in access to “a small set of users.” Initially, there are 11 plug-ins for external sites, including Expedia, OpenTable, Kayak, Klarna Shopping, and Zapier. OpenAI is also providing some plug-ins of its own, one for interpreting code and one called “Browsing,” which lets ChatGPT get information from the internet.

As an example of what the browsing plug-in can accomplish, the company shows someone asking how the box office sales of this year’s Oscar winners compare to recently released movies, and the bot shows its work for what sources it’s looking at before spitting out an answer. This is something ChatGPT would have been unable to accomplish before.

This experimental feature is obviously similar to Microsoft’s Bing, which has custom tech that feeds GPT-4 (the language model underlying ChatGPT) information from the internet. However, OpenAI’s plug-in doesn’t just retrieve real-time information. It can also tie into APIs, letting it “perform actions on behalf of the user,” according to the company’s documentation. That could make it much more powerful — Bing could help you plan a vacation by telling you about flights and hotels, but ChatGPT could help you book it.

There are some obvious safety and security concerns with letting ChatGPT take actions on behalf of a user rather than just giving them information. Experts have already expressed worry about this in reaction to an experiment OpenAI conducted with GPT-4. When directed by a human tester, for example, the bot was able to generate instructions to employ a worker from TaskRabbit to complete a CAPTCHA it was unable to answer.

OpenAI says it’s taken threats posed by these plug-ins into consideration and has “implemented several safeguards,” including limiting availability of the plug-ins to a very small number of people to start. The company’s blog post says it’ll “initially prioritize a small number of developers and ChatGPT Plus users” to get plug-in access and offers a sign-up for a waitlist here.