ChatGPT’s ‘Intelligent UI’ update populates its responses with images, graphics and buttons

OpenAI is launching a new intelligent UI feature in ChatGPT that allows the chatbot to answer your questions with interactive visuals. The update, which is rolling out to all users alongside GPT-6, gives ChatGPT the ability to combine a text response with diagrams, graphs, forms, touch buttons, and more.

In a blog post explaining the change, OpenAI claims to have trained GPT-6 when to generate interactive visuals on text, as well as how to format them in its response. An example shared by OpenAI shows how ChatGPT can display a diagram of a seven-speed bicycle if you ask about its design, with interactive buttons highlighting different parts.

Another shows how ChatGPT can teach you how to play Mahjong by generating visuals of each tile and placing them into categories that you can browse. You can also have ChatGPT generate tools for different tasks, like a retirement savings calculator, retro game, or bill splitter. It will then generate the tool based on its response.

OpenAI announced its first GPT-6 models last month, but now offers Sol and Luna versions on ChatGPT. In addition to enabling intelligent UI, OpenAI claims its GPT-6 allows ChatGPT to perform better web searches and provide faster, partial responses to users while it collects information. The company notes that GPT-6 “has also demonstrated greater resistance to attempts to circumvent its security training.”

GPT-6 with Intelligent UI is rolling out globally to ChatGPT Plus, Pro, Business, and Enterprise users starting today, but will expand to Go and Free tiers on Thursday. While higher-tier subscribers will have access to the mid-range GPT-6 Sol model, Go and free users will be able to use the more efficient GPT-6 Luna.

Gn bussni

Scroll to Top