OpenAI is rolling out GPT-6 alongside a new "Intelligent UI" feature that replaces ChatGPT's text-heavy responses with interactive visuals, including diagrams, charts, forms, and tappable buttons2,4. The update is available to all users.
OpenAI said it trained GPT-6 to decide when to generate interactive visuals instead of text and how to format them within a response. The result is a chatbot that can combine prose with editable graphs, customized calculators, and other elements users can manipulate directly. An example shared by OpenAI shows ChatGPT rendering a diagram of a seven-speed bicycle with interactive buttons that highlight different components.
Aarush Selvan, a product manager at OpenAI, said in a call with journalists that while ChatGPT has "predominantly been a text-based interface," the company wants to help users "get things done — from everyday things like planning a recipe or a trip or even trying to learn something — the most helpful answers aren't just text". Selvan cited the example of a college student asking how an airplane wing functions.
OpenAI described the primary goal as making complex topics easier to learn. The company demonstrated the feature in a media briefing, showing how the chatbot can generate diagrams and visuals for abstract subjects on the fly3. OpenAI Group PBC framed the shift as moving ChatGPT away from "traditional wall-of-text responses" toward a more interactive interface.
Wired characterized the update as "more show than tell"1. ANALYSIS By training the model itself to choose between text and visual output, OpenAI is embedding interface decisions inside the foundation model rather than layering them on as a separate product feature, tying the UI overhaul directly to the GPT-6 release.
The rollout lands on the same day Anthropic cut Haiku pricing by up to 90% and introduced effort controls on its smallest model[1], a busy stretch for the two leading chatbot providers.