Opus 5.5 just filed a pull request that changes... the streaming behavior in T3 code. It's so cool that I can send off a prompt with a vague idea of what I want, and the result is a ready-to-merge pull request with a video demo of the changes directly in the PR. The PRs I make with AI are significantly better than the ones I used to make by hand. The future is awesome.show more

I used Opus 5.5 to make a motion design... video about Haiku This is 100% motion graphics and code Short story about Opus delegating small tasks to Haiku Prompt in the commentsshow more

Okay, everybody is doing it, but I couldn't resist:... Here is Opus 5.5 one-shot of the prompt: "make a dynamic 15-second motion graphics video that shows what an incredible motion designer you are. Highlight the recent changes we made with the last few updates." Probably needs more time because we are shipping so many things 👀show more

New beta feature in T3 Code: "share with guest"... I'm so tired of copy pasting from a thread, sending it to a coworker, waiting for them to respond, screenshotting the context and sending it back to my agent. Now I just send them a link. It's a silly place to start, but I was heavily inspired by the Uber Eats/Doordash group order flow. If I send someone a link to my group order, they can add whatever they want, but ultimately I decide if the order goes through or not. Realized that flow would solve at least half the use cases I have for "shared threads", so it's now built into T3 Connect in T3 Code (nightly) Very curious how you guys feel about this flow. It's still early and I expect to adjust it a bunch (I left the ui bad so maria will come in to fix it sooner) Also s/o Opus 5.5 for making this lil video about the feature :)show more

I started with a simple prompt in Picsart, then... brought the concept to life with Seedance 2.5 through AI Playground/Flow. The level of detail, realism, and overall quality is honestly impressive. Check out the original idea and the final result — the transformation speaks for itself. Want 10% off? Comment CODE and I’ll send you the promo code. Here's the link to template #PicsartPartnershow more

#ChineseGP 🇨🇳 || Lewis Hamilton: “I had so much... fun! I mean these cars are a lot of fun to drive.” “The fact that there are the differences between us and Mercedes, make it challenging in the race, we’re able to be a little bit closer, which is fun.” “Obviously, not the result I wanted in the end but a lot learned. Gonna go and see if we make some changes.”show more

what beomgyu wants to challenge himself with in the... future: 🧸: i want to compose my own songs. i love the sound of bands, so i really want to make music with a band soundshow more

While building SEV0, I ran into moments where natural... language prompting just wasn't enough - too vague, too indirect. So I started using a method that bridges that gap. I call it Bridged Prompting - a technique where you temporarily step out of the prompt-response loop to manipulate something directly using an AI-generated UI, then step back in. Think of it like GenUI, but more user-driven and transient. AI generates a UI on-the-fly, tailored to your prompt, and lets you manipulate the artifact directly before resuming the conversation. Sure, you could build a full tool, switch tabs, wire it up and round-trip your data. But with Bridged Prompting, the AI just spins up a temporary interface right in the flow. In the video below, I used it to construct the hallway system to closely match the layout of the severed floor. This is something I needed to do for this one project, this one time - I didn't need to make a whole separate app. Bridged Prompting lets you: - Make precise edits visually or structurally - "Hit save" to persist changes to local storage or a backend - Return to your natural language promptshow more

Just the example itself is so fun to play... with! 🔆 I can't wait to pull the code and swap the rendering pipeline to achieve even more cool effects. This is the dream of TypeGPU, AI inference, complex compositing, all on the GPU in a seamless, type-safe pipeline.show more

I cracked the code. Most people struggle with AI... video prompts. The trick isn't writing more — it's writing structured. I use Claude to turn a simple idea into a full JSON-style prompt: scene, character, camera movement, timing, negative prompts, all mapped out. That structure is the difference between "obviously AI" and something that looks real. Once you have the format, it's stupidly easy to make consistently realistic videos, over and over. Want the exact JSON prompt structure I use? Comment "WANT" and I'll send it overshow more

I cracked the code. Most people struggle with AI... video prompts. The trick isn't writing more — it's writing structured. I use Claude to turn a simple idea into a full JSON-style prompt: scene, character, camera movement, timing, negative prompts, all mapped out. That structure is the difference between "obviously AI" and something that looks real. Once you have the format, it's stupidly easy to make consistently realistic videos, over and over. Want the exact JSON prompt structure I use? Comment "WANT" and I'll send it overshow more

These are raw clips in Kling AI Omni from... the website. I used a basic prompt that I I slightly tweaked for each scene with the girl. I'll attach the prompt in the comments because it's a custom multi-shot prompt so it's a little long. These are characters from my For Such A Time seriesshow more

50% cheaper Claude inference with just one line of... code change! - Remove → model="claude-opus-4-8" - Add → model="ship-like/claude-opus-4-8" I verified the cost saving in my own terminal by invoking the same Anthropic model with the same prompt. The underlying engineering by Ship is actually interesting, and the patterns can be used in any production LLM stack. Essentially, a trained model is a frozen artifact. Every request performs the same forward-pass, whether it extracts a date or refactors a module, because the compute decision was made at training time, before the request existed. Ship makes that decision at inference time instead. After seeing a request, it searches over executions, involving single models, cascades, ensembles, or harnesses with tools, and serves the cheapest one that will match the reference model's quality. This is not a basic router, because picking a cheaper model per query doesn't ensure the cheaper model preserves the original's behavior, like output shape, tool-call patterns, and refusals. Ship measures this equivalence directly. Outputs stay distributionally indistinguishable from the reference model, not token-identical, since two calls to the same model already differ, but they are indistinguishable in capability and behavior. Of course, some requests execute cheaply and some cost Ship more than the customer pays, but the price per request is still a flat 50% off either way, so the execution-cost variance moves off the application's bill entirely. The video below depicts the cost savings and output in my real invocation, and I partnered with the team to put this together.show more

It's kinda crazy that you can just use multitask... design mode to make a bunch of frontend UI changes, then ask for a shared link canvas with a recap of the changes in like 5 minshow more

Made this commercial demo entirely with Seedance 2.0 via... Yapper Everything you see here is done by one single prompt shot, from the cuts, edits, graphic effects, to the voice over. Basically within the prompt I gave detailed instructions on how many shots I wanted, the timestamps, the copywriting, visual and graphic effects, etc. The full prompt sample is available for my subscribers only in the comment section below ⏬ + + + There are so many use cases for Seedance 2.0 instead of just recreating existing IP. I think for me as a copywriter, what I like about it is that I can create a pre-visualization of an ad we're about to make, with its specific tone and style. Like I said before, the AI generated content here wasn't meant to be the final product, but rather a starting point for our creative direction regarding the potential style that will go into our ads. It's just that it's now so much faster to iterate ideas, and to test many different concepts with Gen-AI. Like I've always said, the technology is here, and it's up to you how you want to use it.show more

This is what DeepSeek v4.1 Flash can do with... OpenDesign Motion. From the first prompt to the finished video, no Opus 5.5 used. Just an idea, your chosen model, and OpenDesign. Demo 1 ↘️show more

If you ship with a coding agent and still... click through every PR by hand, this 40 second clip is worth watching. TestSprite picks up the pull request, runs Integration Tests against the running app in a real browser, and reports passed, failed, and blocked separately, so a broken test environment does not look like a broken product. Failures come back with a video of what happened and a fix prompt written for the agent rather than for you. There is a free tier, and the CLI is open source under Apache-2.0.show more

Dentist did a 3D X-ray of my jaw before... a root canal and said I wouldn't be able to open the raw data, it needs specialized software. It's 800 DICOM files. Asked Claude Code with Opus 5.5 to make me a viewer. A single prompt later... this is nicer than what he showed me on his screen, and even better than what Fable did a few weeks ago!show more

Control with Blender, imagine with Seedance 2.0 🎬 Same... reference video, different worlds. Here's the prompt I used to generate the video. The beginning is always the same only what happens in each scene changes.show more