> For the complete documentation index, see [llms.txt](https://metaverse-imagen.gitbook.io/ai-tools-research/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://metaverse-imagen.gitbook.io/ai-tools-research/large-language-models-llms/microsoft/bing-chat-microsoft.md). # Bing Chat (Microsoft) ![](/files/aSaKBz6XJiSNd3fB9Nb6) **To try Bing Chat, sign into Microsoft Edge and select the Bing chat icon** in the browser toolbar. Feature availability and functionality may vary by device type, market, and browser version. Bing is a web search engine owned and operated by Microsoft. It is the second largest search engine globally, with a query volume of 12%, behind Google's 79%; Baidu is at 5% and Yahoo! Search, which Bing largely powers, has 2%. Bing provides a variety of search services, including web, video, image and map search products. It is developed using ASP.NET. Bing offers a number of features that differentiate it from other search engines, including: * **Answers:** Bing provides summaries of factual queries, often pulling information from multiple sources. * **Image search:** Bing is known for its high-quality image search results. * **Maps:** Bing Maps offers a number of features that are not available on other mapping services, such as 3D imagery and Streetside views. * **Shopping:** Bing Shopping allows users to compare prices from different retailers and find coupons. * **Translate:** Bing Translate allows users to translate text between over 100 languages. Bing is also integrated with a number of Microsoft products, such as Microsoft Edge and Xbox. To use Bing, simply go to the Bing website or open the Bing app on your mobile device. Enter your search query and Bing will return a list of relevant results. You can then click on a result to view the associated web page. Bing is a good choice for users who are looking for a search engine that offers a variety of features and integration with Microsoft products. ### Bing Chat Bing is powered by an LLM. Microsoft announced in February 2023 that Bing Chat, a new chatbot interface for Bing, would be powered by a next-generation OpenAI large language model (LLM) customized specifically for search. Five weeks later, Microsoft revealed that Bing Chat runs on OpenAI's latest language model, GPT-4. GPT-4 is a more powerful and capable LLM than its predecessor, GPT-3. It is able to generate more realistic and coherent text, and it can also better understand and respond to natural language queries. Microsoft has not yet said how it is using GPT-4 in Bing Chat, but it is likely that the LLM is being used to generate more informative and engaging answers to user queries. For example, GPT-4 could be used to generate summaries of factual queries, or to create more conversational and interactive search experiences. It is possible that Microsoft will eventually use GPT-4 to power other aspects of Bing, such as its web search results or its image search results. However, Microsoft has not yet made any announcements about this. Overall, it is clear that Microsoft is investing heavily in LLM technology, and that it believes that LLMs have the potential to revolutionize the way that people search for information. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://metaverse-imagen.gitbook.io/ai-tools-research/large-language-models-llms/microsoft/bing-chat-microsoft.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.