OpenAI is rolling out a feature called Intelligent UI in ChatGPT that lets the chatbot answer prompts with interactive visuals instead of plain text. The update ships globally alongside GPT-6 and gives ChatGPT the ability to combine written responses with diagrams, charts, forms, and tappable buttons rendered inline in the conversation.
OpenAI said in a blog post that it trained GPT-6 to decide when to generate interactive visuals over text and how to format them within a response. One example shows ChatGPT rendering a diagram of a seven-speed bicycle with buttons that highlight different parts; another walks users through Mahjong by generating visuals of each tile grouped into scrollable categories.
Users can also ask ChatGPT to build small tools directly in a reply, including a retirement savings calculator, a retro game, or a bill splitter. The tool appears in-line with the model's answer rather than as a separate app or canvas.
Key facts
- 01OpenAI launched Intelligent UI in ChatGPT on Oct 7, 2026, letting responses include diagrams, charts, forms, and tappable buttons.
- 02The feature ships alongside GPT-6 Sol for Plus, Pro, Business, and Enterprise users starting today, with Go and free tiers getting GPT-6 Luna on Thursday.
- 03ChatGPT can now generate in-line tools like a retirement savings calculator, a retro game, or a bill splitter inside its response.
- 04OpenAI says GPT-6 also improves web search, delivers partial answers faster, and 'showed stronger resistance to attempts to bypass its safety training.'
The rollout brings the Sol and Luna versions of GPT-6 into ChatGPT after OpenAI first announced the GPT-6 model family last month. Intelligent UI reaches ChatGPT Plus, Pro, Business, and Enterprise on Oct 7, 2026, and expands to the Go and free tiers on Thursday. Higher-tier subscribers get the mid-range GPT-6 Sol model, while Go and free users get the more efficient GPT-6 Luna.
Alongside the UI change, OpenAI said GPT-6 performs better web searches and can return partial answers more quickly while it continues gathering information. The company also said GPT-6 "showed stronger resistance to attempts to bypass its safety training" compared with prior models.
Working on something we should cover, or seeing a story we missed? Send leads, documents, or feedback to hello@aichatdaily.com. For sensitive tips, see our secure tips page for Signal and PGP options.
Spotted an error? Email hello@aichatdaily.com with the URL and the issue, or read our full corrections policy.
