Skip to content
Bramble

Technology

OpenAI launches 'Intelligent UI' with interactive visuals in ChatGPT alongside GPT-6

OpenAI has launched an "Intelligent UI" for ChatGPT that generates interactive visual elements such as diagrams, calculators and charts in answers, rolling out with its GPT-6 model.

3 outlets · 2L · 1C · 0R First reported Account updated
Image: Wired
Image: TechCrunch

1 / 2

The story, neutrally told

Mixed · 2On Wednesday 7 October, OpenAI unveiled an "Intelligent UI" update for ChatGPT that generates visual, custom elements in answers when they are helpful. Mixed · 2The interface is powered by OpenAI's GPT-6 model and is rolling out with it: paid users get it first, and free users the next day. Centre · 1TechCrunch reports that OpenAI says many of the visuals will be interactive, including tappable buttons, customised calculators, interactive charts and editable graphs, with the stated goal of making "learning complex topics easier".

Centre · 1Aarush Selvan, an OpenAI product manager, said ChatGPT "has predominantly been a text-based interface" and that the most helpful answers aren't just text; in a demonstration for journalists he asked it to explore how an airplane wing generates lift, and it produced several diagrams. Left · 1In a pre-launch test, Wired's Reece Rogers generated an interactive slug anatomy diagram, a San Francisco apartment affordability calculator with sliders, and a tool comparing exit rows on four Alaska and Delta planes. Mixed · 2Not every answer will include visuals: Selvan said a design team worked out when a diagram, chart or buttons add value rather than clutter, and users can ask ChatGPT to produce fewer of them.

Mixed · 2Wired compares the feature to Google's "generative UI" for Search and says it signals a multimodal era for chatbots used by over a billion people, while warning that generative interfaces may spark an identity crisis for designers; TechCrunch adds that the feature may help ChatGPT reach a wider audience, though OpenAI did not say so directly.

Every sentence links to the reporting it rests on. The pill in front of each says where its sources sit: Left, Centre or Right when one side supplies at least half of them, Mixed when they are evenly split. The number is how many outlets it cites.

Left2 outlets

Framing
A first-person hands-on review that welcomes the visual shift and places it in the wider trend of generative interfaces.
Emphasis
Personal test results, comparison with Google's generative UI, and implications for designers.
Leaves out or plays down
Does not list the full tier rollout (Pro, Plus, Business, Enterprise, Go) or OpenAI's stated goal of making complex topics easier to learn.
Charged language
“Good riddance to walls of text”“identity crisis”
For example
“these visual elements felt like a welcome change” — Wired
“Good riddance to walls of text.” — Wired

Centre1 outlet

Framing
A product-launch report built on OpenAI's briefing and demo, with some analysis of the likely benefit to OpenAI.
Emphasis
Types of interactive elements, OpenAI's stated goals, tier-by-tier availability and the demo examples.
Leaves out or plays down
Does not mention Google's comparable feature or concerns for designers, and has no independent hands-on testing.
Charged language
“whip up”
For example
“In a call with journalists, OpenAI staff gave a brief demonstration of Intelligent UI’s capabilities” — TechCrunch
“ChatGPT is about to get a lot more visual” — TechCrunch

Right0 outlets

No right outlet in our sources has covered this story yet.