ChatGPT Plugins

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. Plugin developers who have been invited off the waitlist can use the documentation 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. Access to Real-World and Recent Data Plugins can be “eyes and ears” for language models, giving them access to information that is too recent, too personal, or too specific to be included in the training data. In response to a user’s express request, plugins can also empower language models to undertake safe, constrained activities on their behalf, boosting the usefulness of the system overall. Plugins offer the possibility to tackle many issues connected with huge language models, including “hallucinations,” keeping up with recent events, and accessing (with permission) proprietary information sources. By adding explicit access to external data—such as up-to-date information online, code-based computations, or custom plugin-retrieved information—language models can reinforce their responses with evidence-based references. The first plugins have been produced by Expedia, FiscalNote, Instacart, KAYAK, Klarna, Milo, OpenTable, Shopify, Slack, Speak, Wolfram, and Zapier.