it turns out the hardest part of generative UI isn't generating the UI. models have been able to generate good-looking HTML for a while. the more interesting challenge is getting it to feel like it actually belongs in chatgpt. one of our big bets with Intelligent UI was that you didn't have to choose -- that you could keep ~all of the power of HTML and still have it feel fast and native, like it was always part of chat the other half of the problem is model judgement. how do we post-train gpt-6 to know when an interface would actually help? what should it show or let you do? how do we make it useful and beautiful without taking over the conversation? none of this was obvious when we started, and there's plenty we're still figuring out. luckily, one of my favorite things about openai is that if you believe in an idea, you can just go build it, even if it takes a lot of prototypes to get there really excited this is finally out, and incredibly proud of the team. onwards!