GPT‑6 and Intelligent UI for everyone

I find the Sunday roast comparison of 5.6 vs 6 very interesting. I have no doubt most people will prefer 6, yet I am almost repulsed by all the images, so much needless whitespace, checklist and so on. Feels like I'm being condescended to and treated like a child.

Given that OpenAI is making noises about merging work with chat (a horrible idea imo), and Work is very similar to Codex... I dearly hope things like these won't have any meaningful cross-polination into the actual work tools.

Seeing that the chat is based on 6.0 and not 6.1 is disappointing. The "Visual and interactive explanations" seems genuinely useful, but 6.1 is just so much better. I wouldn't truly trust the 6.1 with the explanations, but I'd trust them a fair bit more than 6.0. I understand that compute isn't infinite, but tons of people only interact with the chat and having your "things-explainer" be as good as it can be is important when people increasingly treat AI models as the source of truth, or even use them for academic learning and whatnot.

Still, the models will improve, so the visual explainer seems pretty good as an idea / mvp.

Of everything that could be automated, Bartosz Ciechanowski really was the last on my list.

In all seriousness, his lovingly and expertly crafted explainers are still going to age like a handcrafted heirloom clock in a world of plastic-clad quartz movements. But it’s absolutely incredible that we are now in an age where a computer can manufacture a serviceable interactive explainer on whatever niche topic you desire.

I've had the most success with GPT explaining things to me by making it take a few sentences at a time back and forth, instead of reading full write-ups of whatever I asked. It also often poisons the conversation if it misunderstood some part of the question, and I can lead it better by continuously questioning its statements. It's also more engaging that way.

I've been learning music lately and it kept re-pasting the same one chord visualization throughout many conversations, almost randomly and often barely related to the question. So I at least hope this won't be as aggressive so I can prompt it away!

This seems like a way for them to surface ads in ChatGPT. They just came out with visual ad format option for advertisers a couple of days ago: https://openai.com/index/new-chatgpt-ads-format-and-measurem...

I'm not a fan of OpenAI / Sam Altman, but I love their blog posts. The team and whoever decides how to do these presentations, is on point. The only other company that has amazing release pages like this is Apple, I think I remember hearing that they probably hired someone from apple who used to do release blog posts there too.

What's funny about "Intelligent UI" is I said like 2 or more years ago, that these AI companies need to start thinking outside of these basic chat UIs, they do some things here and there, but its really depressing how little they do to innovate in these spaces. Same with the coding harnesses, the UI for all these things could be drastically superior.

I've been calling this "disposable UI" or "paper plate UI", eg something meant to be used once. One thing I'll be curious about is overzealousness to produce this, when sometimes what you want is just a simple response. Overall though I'm a big fan of it, if it can be provided fast enough. I'd be curious on how much impact it has on latency of a response.

I'm excited about generating UIs (and apps) on demand, because it's one step closer to devices just morphing to the interface you need. I want to talk to my phone and have it generate the app or interface I need. I could see Android adapting to this reality well before Apple.

Funny to see a blog post about UI from one of the most funded tech companies in the world, yet the player has about the worst UI possible:

- Audio volume has 2 levels: on and off

- Play button worked exactly once for me: it played and looped the video. Couldn't be stopped afterwards.

- The video progress bar has no visual indication of where it starts and where it ends..

Is this what Phind died for?

Great product idea. I have not paid OpenAI for a subscription for a couple of years, I’m tempted now. I do about 75% of my work using local models and most of the rest using the deepseek 4.1 flash API. That said $20 to experiment with this new product for a month sounds like a pretty fun idea.

Thank god. My primary use of ChatGPT is meal planning and while it’s great for recording, recipe lookup, etc I always just wanted it to be able to make checkable grocery lists.

I eventually just had it make a skill for work mode that would build a mini checklist app, but it was slow and felt janky needing to remember to switch to work mode.

This is already such a huge improvement.

GPT-6's design sense is kind of ridiculous imo.

I have explicit instructions to tone it down. Less taglines, eyebrow text, subheadings, decorative spacing, pills, cards.

Hopefully this doesn't bleed into the chat...

Burning question: why is this worth paying for as a layman? I can sometimes find a use for all these LLMs for software development, but I can never find a good use for any of this outside of "slightly better search engine".

I'm curious to see how useful this is. I feel like in practice the existing versions of this feel like they get in the way. While I'm sure I've had some situations where a visual would be helpful, there are two situations where I do not want it:

1) I want a quick answer, and I don't care for the boilerplate UI. For example, if I ask how to make pancakes, I make them all the time and just want to a quick reminder on the ratios, but it might trigger a full UI that I need to sort through to find information.

2) If I ask a to me unrelated to UI question and it triggers a big UI build that is completely off topic for my question (meaning I'm desperately pressing the stop button and prepping rewriting my query)

Or the other one I see, for example if I look up a unix command like:

"ls all hidden files in the /xxx directory"

And I get back:

"Sorry, I am am unable to find /xxx in my current environment"

Honestly it feels like AI companies are still searching for the killer idea that will attract the general public (beyond "be my AI bf" or "better google").

Getting a UI that explains the parts of a bike is ok I guess, but isn't it simpler to get an actual breakdown? Google "parts of bicycle breakout" gets tons of useful images instantly.

Getting a specialized app to split a bill? It was already trivial to put in a calculator if we cared to go item by item on the bill. Having to provide names and tag every item as I go is just more work. Usually real people just go $total divide by 5, I had more, let me chip in an extra $10.

Same with booking travel and wedding plans, these aren't things people would even delegate to a trusted friend usually, much less a one-off request to an AI bot or custom UI.

Most of the useful tasks it can do right now are research, technical question/answer, coding. In terms of "build a flexible ui that solves real-world problem", if existing mobile app isn't useful in this arena, then its unlikely a completely custom UI will do the job.

That said, I've done a few small ones like a quick one to practice alphabet of a foreign language, or prototyping a web game, and the like. But ultimately its nothing that is worth trillions of dollars.

I find it extremely strange that they're adding GPT-6 Sol to Chat over GPT-6.1 Sol which is significantly more capable.

I wrote something like this, though not quite as slick, by having the model use json schema to describe its results instead of text, and then use a json-schema to ui interface.

The medium is the message here. As others have said, chat output largely sucks for anything but the most basic responses and we've done little to improve upon that foundational UI in the last couple years. We've _added_ a lot for specific domains like coding and document editing, but the primary content normal users get back from the chats is verbose and uninteresting. This is a step in the right direction.

Gettin closer to fully dynamic interfaces for a lot of software. Hell, give me a mode in Google Docs that takes every pixel of chrome away then vibe the rest as I need it. Persist across new documents going forward.

Is this OpenAI catching up with Anthropic artifacts? At the same time they say "We’ve trained GPT‑6 to compose responses using text, visuals and interactive elements...", rather than a harness.

The irony really is that LLMs are partly responsible for the walls and walls of text as seen in the video in the first place.

And now we are asking LLMs to solve it.

gemini app kind of had that for a while I feel?

We are becoming more and more as a tool for sth to be done rather than the brain behind it. At least I start to feel this way. The joy of discovery, exploration and experiencing at first hand... It is slowly diminishing for the perfection of the quick outcome.

I wish things like bikes came with mostly-written manuals. Maybe a few diagrams. If anything, things are too pictorial these days.

I'm confused. Are they trying steamroll every developers B2C product or are they wanting these same developers to continue building MCP-App plugins on the platform?

"More than" 20% of the connected world uses ChatGPT each week eh? I guess if you add Anthropic who must also claim 20% and Google, Meta.. that does not sound realistic at all.

This seems like a step towards their plan for building a platform in competition of Google/Apple. Once the generative UIs are polished and more useful than individual apps, their hardware can now ship a device which circumvents the app store moat.

All those recipe blogs and sites that have figured out the most inefficient way to deliver information are finally cooked.

I am pretty convinced that businesses will be making custom internal software as a norm in the next few years, and this seems to be a slight push in that direction

AFAIK, they already had a simpler form of this. It was kind of an obvious next step. Now connect it up to tools so that we can again comfortably do the things that are more precise by hand! The “pick a color” or “select the width on a slider” use case is coming closer.

1.2B weekly active users? WAU!

They seem to be pitching something that pretty much all the decent models can already do..?

Obviously if your model is stuck inside a CLI terminal, then not so much. But in a GUI harness (shameless plug for my own one: https://juggler.studio, but I assume others can do this too), you just ask them to answer in HTML and they'll happily draw pretty pictures inline in the conversation. I've been doing this for ages with claude, GPT, Deepseek and others.

For once Gemini did it first. I never found those mini GUIs useful though. More like a waste of time and energy.

I think this means that the API "chat-latest" model is now serving a custom GPT-6 variant: https://developers.openai.com/api/docs/models/chat-latest

This seems like an expansion on something I was getting my agent to do which is use 'cards' to communicate using things like tables, rather than the ascii table stuff Claude code likes to do.

Unsure if this has been done already but the best thing I did was get it to create a list of next steps as quick buttons that it keeps updated in a docked card. It works well but occasionally gets stuck on some un related rabbit hole.

The intro video is just lame. Those things never happen in real life.

In the video, they showed examples of ChatGPT making interactive tutorials on how to fold origami, how to arrange colours/interior and how to assemble a bike.

Supposedly, people were struggling to follow written manuals and they needed an interactive explanations.

I'm not a mathematician and I would certainly love having a tool that would do ELI5 on some complex stuff, but I'm really worrying about using this too often and outsourcing my ability to do stuff to some mega corp.

I like how, whenever a new model releases, they not only make other companies' models seem worse, but even their own "oLdeR" models.

Sounds like Google's Generative UI (Nov 2025): https://research.google/blog/generative-ui-a-rich-custom-vis...

> The compiler allows the interface to appear progressively as the model generates it, without waiting for the entire response to be complete.

why not just stream html?

"But when will we recoup our investments?" Investor to Gavin Belson after he presents a whole zoo of animals for analogies.

This is now trying to steal YouTube repair and cooking videos. Here is news for you: People prefer YouTube repair and cooking videos.

Gemini had this UI thing before .

This seems like a natural progression of models becoming better at frontend coding in general.

"Here is a library of [svelte/react/whatever] components, use them to construct a helpful visual to demonstrate your point."

The deconstructed bike at the beginning was in a class of its own, however.

How would a user know whether a generated visualization to illustrate some process is accurate or not?

I noticed this change too! It is really game changer - to me ChatGPT output has no rivals here.

There have been recent developments that allow people to interpret Swift on device, live. With this new launch, will the AI be able to write native code and compile it on device? That would be super cool.

It makes sense they’re doing this - I’ve noticed lately when asking a more complex question involving a lot of nonlinear data using Codex work mode, Astra and Sol will write a fully html document to better display the info with a Cliff’s Notes version in chat.

I feel like I'm going mad looking at this page. The bike disassembly looks fake to me, like an alien would show presumed bike parts, but I can't tell why and don't know much about bikes. Maybe it's because there are no screws and nuts?

What is it supposed to demonstrate? That the model knows some kind of folk mereology?

A Chat AI creating on the fly UX widgets is like Amazon’s brick and mortar stores

So I guess it's going to nail the bicycle the Pelican rides on, right?

I'm also building something similar for an internal project, based on the vercel's json-render design. It hasn't been too challenging, especially since the release of faster models like 5.6 Luna.

Similar to https://www.monogram.ai/.

I guess the above is mostly mobile focused.