Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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... show more

Theo - t3.gg

392,764 subscribers

92,627 views • 2 days ago •via X (Twitter)

Arts Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

#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.”

#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.”

sin ⁴⁴

234,236 views • 6 months ago

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 prompt

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 prompt

Chris Tate

42,558 views • 1 year ago

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.

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.

Iwo Plaza | TypeGPU

122,059 views • 1 month ago

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 over

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 over

Stijn Feijen

10,181 views • 17 days ago

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.

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.

Akshay 🚀

64,482 views • 2 months ago

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 min

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 min

John Bai

94,774 views • 4 months ago

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.

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.

MXVDXN // DAN

17,791 views • 6 months ago

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.

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.

Koldo Huici

25,052 views • 3 months ago

I built a pull up tracker for my livestream. When someone likes the stream it adds a pull up. It automatically subtracts when I do them. Coded this with opus 4.7 in 30 minutes. The future is now.

I built a pull up tracker for my livestream. When someone likes the stream it adds a pull up. It automatically subtracts when I do them. Coded this with opus 4.7 in 30 minutes. The future is now.

Max Blade

30,283 views • 5 months ago

I need a minute to process the result of this animation made with Opus 5.5 And I asked it to explain how it pulled it off, and my mind got blown all over again. I'll leave you the prompt too 👇

I need a minute to process the result of this animation made with Opus 5.5 And I asked it to explain how it pulled it off, and my mind got blown all over again. I'll leave you the prompt too 👇

Koldo Huici

67,794 views • 3 days ago

ode 🥺 "The reason why I, who used to cry because I didn't want to be in a band, ended up falling in love with it is because through music and the stage, whether in a small or big way, I can be part of it and make a sound."

ode 🥺 "The reason why I, who used to cry because I didn't want to be in a band, ended up falling in love with it is because through music and the stage, whether in a small or big way, I can be part of it and make a sound."

ten 🪐

65,434 views • 1 year ago

Vorflux has opened its new cloud platform, allowing users to run tasks from a plan to a merged PR on a dedicated machine. It can plan, build, test, and review on its own. > Diff reviews are done by a different model family than the one that wrote it by default. > First boot is saved as a snapshot, with all subsequent sessions waking up from that same starting point. > A browser agent walks through the real user flow, and the recording is included in the pull request. Video proof in the PR 👀

Vorflux has opened its new cloud platform, allowing users to run tasks from a plan to a merged PR on a dedicated machine. It can plan, build, test, and review on its own. > Diff reviews are done by a different model family than the one that wrote it by default. > First boot is saved as a snapshot, with all subsequent sessions waking up from that same starting point. > A browser agent walks through the real user flow, and the recording is included in the pull request. Video proof in the PR 👀

🚨 AI News | TestingCatalog

12,051 views • 1 month ago

If you prompt it right, Seedance 2.0 is the most powerful video model in the world. But it won't turn a vague idea into a cinematic shot. Here's the prompt I use to make scenes like this 👇

If you prompt it right, Seedance 2.0 is the most powerful video model in the world. But it won't turn a vague idea into a cinematic shot. Here's the prompt I use to make scenes like this 👇

NΞXUS

15,818 views • 3 months ago

As always everyone is blind staring at the progress of LLMs for coding and chat But meanwhile the new SOTA video model Seedance 2.5 has been slowly rolling out and it's really quite exceptional It's made by ByteDance (TikTok) who of course have lots of training data With just a few reference pics, it can get quite close to how you look IRL and you can do quite professional video shots with just a prompt I'd say it's the first video model that's now at the level of image models with the level of character likeness, cracking that in image models also took about 3 years (2022-2025) Generating 15 seconds takes about 4 minutes I put it live now on Photo AI, you can use it under [ Make video ] from the sidebar with just a prompt and your model selected! So you don't need to take an AI photo first and then turn that into a video! Saves lots of time :D It's more expensive than but I kept the credits the same (30 for 1 video) It also works inside the new video editor and you can make changes in your video with [ Magic edit ] in both the main app and the video editor Also a message for my server guy Daniel Lockyer (it can do voice too and you can even submit a voice sample of yourself, but I didn't here)

As always everyone is blind staring at the progress of LLMs for coding and chat But meanwhile the new SOTA video model Seedance 2.5 has been slowly rolling out and it's really quite exceptional It's made by ByteDance (TikTok) who of course have lots of training data With just a few reference pics, it can get quite close to how you look IRL and you can do quite professional video shots with just a prompt I'd say it's the first video model that's now at the level of image models with the level of character likeness, cracking that in image models also took about 3 years (2022-2025) Generating 15 seconds takes about 4 minutes I put it live now on Photo AI, you can use it under [ Make video ] from the sidebar with just a prompt and your model selected! So you don't need to take an AI photo first and then turn that into a video! Saves lots of time :D It's more expensive than but I kept the credits the same (30 for 1 video) It also works inside the new video editor and you can make changes in your video with [ Magic edit ] in both the main app and the video editor Also a message for my server guy Daniel Lockyer (it can do voice too and you can even submit a voice sample of yourself, but I didn't here)

@levelsio

711,384 views • 1 month ago

The part of PixVerse that stood out to me was not just the AI fan host, but the chance to turn a football cheer into something personal. Users can interact with Reina, create personalized cheer videos, and enter a lucky draw for PixVerse service credits. The credits can only be used on PixVerse. They are non transferable and have no cash value. It is a playful early experiment, but I like that it gives users a simple way to make something of their own and share it with others. That mix of creating a cheer moment and joining the credit draw is what I would want to try 👉

The part of PixVerse that stood out to me was not just the AI fan host, but the chance to turn a football cheer into something personal. Users can interact with Reina, create personalized cheer videos, and enter a lucky draw for PixVerse service credits. The credits can only be used on PixVerse. They are non transferable and have no cash value. It is a playful early experiment, but I like that it gives users a simple way to make something of their own and share it with others. That mix of creating a cheer moment and joining the credit draw is what I would want to try 👉

Amit

46,845 views • 2 months ago

“I just want to make people smile. It’s cool the power that thing has and what it can do for people…” A Stanley Cup champion only gets so much time with the Cup. Seth Jarvis began his day by bringing it to the Children’s Hospital of Winnipeg. Watch:

“I just want to make people smile. It’s cool the power that thing has and what it can do for people…” A Stanley Cup champion only gets so much time with the Cup. Seth Jarvis began his day by bringing it to the Children’s Hospital of Winnipeg. Watch:

Dave Minuk

58,693 views • 1 month ago