ChatGPT plugins

OpenAI

We’ve implemented initial support for plugins in ChatGPT. Plugins are tools designed specifically for language models with safety as a core principle, and help ChatGPT access up-to-date information, run computations, or use third-party services.

In line with our iterative deployment philosophy, we are gradually rolling out plugins in ChatGPT so we can study their real-world use, impact, and safety and alignment challenges—all of which we’ll have to get right in order to achieve our mission.

Users have been asking for plugins since we launched ChatGPT (and many developers are experimenting⁠(opens in a new window) with⁠(opens in a new window) similar⁠(opens in a new window) ideas⁠(opens in a new window)) because they unlock a vast range of possible use cases. We’re starting with a small set of users and are planning to gradually roll out larger-scale access as we learn more (for plugin developers, ChatGPT users, and after an alpha period, API users who would like to integrate plugins into their products). We’re excited to build a community shaping the future of the human–AI interaction paradigm.

Plugin developers who have been invited off our waitlist can use our documentation⁠(opens in a new window) to build a plugin for ChatGPT, which then lists the enabled plugins in the prompt shown to the language model as well as documentation to instruct the model how to use each. The first plugins have been created by Expedia⁠(opens in a new window), FiscalNote⁠(opens in a new window), Instacart⁠(opens in a new window), KAYAK⁠(opens in a new window), Klarna⁠(opens in a new window), Milo⁠(opens in a new window), OpenTable⁠(opens in a new window), Shopify⁠(opens in a new window), Slack⁠(opens in a new window), Speak⁠(opens in a new window), Wolfram⁠(opens in a new window), and Zapier⁠(opens in a new window).

Overview

Safety and broader implications

Connecting language models to external tools introduces new opportunities as well as significant new risks⁠(opens in a new window).