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.

Introducing the new OpenDesign Harness. More polished, complete designs with fewer prompts and tokens. Our experiment achieved SOTA quality at ~1/20 the cost. Over 88% of survey respondents rated it positively. On by default for everyone tomorrow. Demos up next ↘️

OpenDesign

21,707 subscribers

86,643 views • 6 days ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

29 Comments

OpenDesign6 days ago

1) Let people explore your product. Turn a static presentation into an interactive demo that feels like your brand, where visitors can discover details at their own pace. Before → After: an iPhone 18 concept teardown, built to be explored.

OpenDesign6 days ago

2) Your brand, across every page. Designs follow your brief and design system, with imagery that fits your product and business—not just the layout. Before → After: a more cohesive landing page, with visuals that help tell the right story.

OpenDesign6 days ago

3) Go beyond the first screen. Build complete, clickable apps with real navigation, multi-step flows, and state changes that carry across pages. Before → After: follow the journey from start to finish.

OpenDesign6 days ago

Try OpenDesign new harness now ↘️

Kosta Milovanovic6 days ago

Based on testing give us the top OpenSource and Closed Source models you recommend at the cheap, medium and expensive price points. Like would you recommend GLM Flash over DeepSeek Flash? Grok 4.6 over Sonnet 5? I’m sure you’ve done multi model evaluations and comparisons.

Elise Tech Ai5 days ago

SOTA at 1/20 the cost with 88% positive rating is massive — can't wait to try the new Harness tomorrow!

Alice The Ai Expert6 days ago

This is amazing SOTA quality at 1/20th the cost with fewer prompts is a game changer, and 88% positive says it all!

Liam Vinberg5 days ago

Cool stuff

AI Mastery Guide5 days ago

after looks way cleaner

Redouane5 days ago

Nice , will definitely try this on the weekends

OpenDesign5 days ago

Awesome, let us know what you think!

Lord Python 🐍6 days ago

nice. astra good with this?

OpenDesign5 days ago

Yep! We actually made this with GPT-6 Astra

Sophia AI & Tool Expert5 days ago

Wow 1/20 the cost with SOTA quality is insane, huge win for OpenDesign!

Noor Tech6 days ago

OpenDesign Harness launches tomorrow. SOTA quality at 1/20 the cost, fewer prompts. 88% rated it positively.

henriqueamsm5 days ago

Solo falta que nos facilites el promt que as usado para la creación de la web de los iPhone por dentro, para poder probarlo.

OpenDesign5 days ago

we'll have a landing page to show that 🫶

Aria Tech5 days ago

20x cheaper with SOTA quality and fewer prompts is massive

ZenithAi5 days ago

Better designs for way less cost and fewer prompts is huge

Elara AI5 days ago

opendesign harness delivers sota designs at 1 20th the cost

Ananducv5 days ago

Linux support?

Sebastian Buzdugan5 days ago

1/20 cost looks strong but downstream edit time matters more than first pass ratings

Arsh - 16 y/o builder5 days ago

harness doing the heavy lifting at 1/20th cost is the move curious if it still holds when the brief gets messy mid flow

SVG Icons5 days ago

The design-system constraint is the key. Generated UI gets much stronger when components, icons, and imagery inherit the same visual rules.

TEAGÁ5 days ago

Does the harness override the agent we chose? For example, if I choose the Pi Agent in the chat...

OpenDesign5 days ago

The harness currently supports OpenCode, Open Design, Codex, and Claude Code. Pi isn’t supported yet, but we’ll keep you posted as we add support for more agents!

Sani Ai Tech5 days ago

Impressive efficiency gains without sacrificing design quality

Evia AI5 days ago

Impressive efficiency gains without compromising design quality

Chole Syntax Expert AI5 days ago

SOTA quality at 1 20 the cost AND live for everyone tomorrow Thats the kind of upgrade we love to see

Related Videos

1/ Introducing ShellAgent 2.0 — the Agent for App Building No more dev tools. No more waiting. No more “almost-working” demos. Just say your idea — ShellAgent 2.0 builds the backend, sets up hosting, designs the UI, and ships the app. From idea to app — as easy as posting on TikTok. Try it here:

1/ Introducing ShellAgent 2.0 — the Agent for App Building No more dev tools. No more waiting. No more “almost-working” demos. Just say your idea — ShellAgent 2.0 builds the backend, sets up hosting, designs the UI, and ships the app. From idea to app — as easy as posting on TikTok. Try it here:

MyShell.AI

163,535 views • 1 year ago

Over the past few years, DoorDash Labs has been building one of the most sophisticated autonomy stacks designed for the real-world challenges of local delivery. Today, we're introducing Dot, the first commercial autonomous delivery robot to travel on bike lanes, roads, and sidewalks. At one-tenth the size of a car reaching speeds of up to 20 mph, Dot is purpose-built for local commerce. Together with our new Autonomous Delivery Platform, Dot is the next step toward a more efficient, sustainable, and accessible delivery ecosystem for everyone.

Over the past few years, DoorDash Labs has been building one of the most sophisticated autonomy stacks designed for the real-world challenges of local delivery. Today, we're introducing Dot, the first commercial autonomous delivery robot to travel on bike lanes, roads, and sidewalks. At one-tenth the size of a car reaching speeds of up to 20 mph, Dot is purpose-built for local commerce. Together with our new Autonomous Delivery Platform, Dot is the next step toward a more efficient, sustainable, and accessible delivery ecosystem for everyone.

Stanley Tang

1,341,952 views • 11 months ago

Introducing Gamma Imagine! Gamma Imagine lets you create standalone visuals directly in Gamma. Select our new graphics format and generate polished logos, diagrams, infographics, and more that you can add to your presentations. All designs are matched to your theme and can be edited with Gamma Agent. Available to all Gamma users for the next 30 days!

Introducing Gamma Imagine! Gamma Imagine lets you create standalone visuals directly in Gamma. Select our new graphics format and generate polished logos, diagrams, infographics, and more that you can add to your presentations. All designs are matched to your theme and can be edited with Gamma Agent. Available to all Gamma users for the next 30 days!

Gamma

27,417 views • 5 months ago

Anthropic engineer: "If you want to be in the top 1% of AI engineers, build a harness that improves itself Harnesses and graphs" In just 41 minutes, she explains how Anthropic builds with AI internally and why harnesses and graphs sit at the center of it Prompts → Agents → Harness → Loops → Graphs A harness makes each unit of work correct without you A graph decides which units should exist and turns every accepted result into a rule for the next run That's what "self-improving" actually means And it's the part almost nobody is building Watch it today Then save the full harness engineering guide below before everyone starts catching up ↓

Anthropic engineer: "If you want to be in the top 1% of AI engineers, build a harness that improves itself Harnesses and graphs" In just 41 minutes, she explains how Anthropic builds with AI internally and why harnesses and graphs sit at the center of it Prompts → Agents → Harness → Loops → Graphs A harness makes each unit of work correct without you A graph decides which units should exist and turns every accepted result into a rule for the next run That's what "self-improving" actually means And it's the part almost nobody is building Watch it today Then save the full harness engineering guide below before everyone starts catching up ↓

Lunar

16,448 views • 9 days ago

Today, we're introducing not one but TWO new models, striking the balance between efficiency and quality to enable you to build production AI agents. — Gemini 3.6 Flash: Addresses efficiency feedback we received from Gemini 3.5 Flash with upgrades in coding, knowledge work, and multimodal tasks faster, more accurately, and with substantially fewer tokens per task — Gemini 3.5 Flash-Lite: Our fastest, most cost-effective 3.5-class model yet built for agentic workflows, hitting ~350 output tokens/sec with improved coding and overall quality Start building with these today via the Gemini API in Google AI Studio or try them out in the Google Gemini

Today, we're introducing not one but TWO new models, striking the balance between efficiency and quality to enable you to build production AI agents. — Gemini 3.6 Flash: Addresses efficiency feedback we received from Gemini 3.5 Flash with upgrades in coding, knowledge work, and multimodal tasks faster, more accurately, and with substantially fewer tokens per task — Gemini 3.5 Flash-Lite: Our fastest, most cost-effective 3.5-class model yet built for agentic workflows, hitting ~350 output tokens/sec with improved coding and overall quality Start building with these today via the Gemini API in Google AI Studio or try them out in the Google Gemini

Google AI

438,466 views • 1 month ago

Day 1 of #CES2026Razer is officially wrapped up — with plenty of exciting announcements. Come find our booth at The Venetian, Level 2, Bellini 2101 for more exclusive product demos today on Day 2! #RazerCES2026

Day 1 of #CES2026Razer is officially wrapped up — with plenty of exciting announcements. Come find our booth at The Venetian, Level 2, Bellini 2101 for more exclusive product demos today on Day 2! #RazerCES2026

R Λ Z Ξ R

18,851 views • 8 months ago

Force is arguably the most overlooked ingredient in modern robot learning. Introducing FACTR 2: it turns *any* commodity robot into a force-aware system with no force sensors required. Train a tiny force network in <1min with <10mins of data and drop it into any existing teleop pipelines: ✅ Free force sensing for both the robot and the operator arm ✅ Makes demos higher-quality → fewer of them needed. ✅ A new force-aware learning algorithm (FIRST) uses those recovered forces to figure out which parts of a demo actually matter, making learning data-efficient. ✅ Strong performance on complex tasks with fewer demos and even no pretraining! More details below.

Force is arguably the most overlooked ingredient in modern robot learning. Introducing FACTR 2: it turns any commodity robot into a force-aware system with no force sensors required. Train a tiny force network in <1min with <10mins of data and drop it into any existing teleop pipelines: ✅ Free force sensing for both the robot and the operator arm ✅ Makes demos higher-quality → fewer of them needed. ✅ A new force-aware learning algorithm (FIRST) uses those recovered forces to figure out which parts of a demo actually matter, making learning data-efficient. ✅ Strong performance on complex tasks with fewer demos and even no pretraining! More details below.

Deepak Pathak

40,987 views • 3 months ago

I ran the same task on Claude Code and DeepSeek's new agent harness. One cost $150. The other cost $2. Today we're launching (AgentSky), the "OpenRouter for Agents" — one API → Claude Code, Codex, DeepSeek, Kimi, OpenCode, and every major agent in the cloud. And Agent Playground on top: race them on your own task, with your real tools (GitHub, Gmail, more), side by side in a browser: time, cost, tokens burnt. Guess which one was $2.

I ran the same task on Claude Code and DeepSeek's new agent harness. One cost $150. The other cost $2. Today we're launching (AgentSky), the "OpenRouter for Agents" — one API → Claude Code, Codex, DeepSeek, Kimi, OpenCode, and every major agent in the cloud. And Agent Playground on top: race them on your own task, with your real tools (GitHub, Gmail, more), side by side in a browser: time, cost, tokens burnt. Guess which one was $2.

Xiaoyin Qu

2,213,107 views • 20 days ago

What could scaling unlock for biology? Introducing ProGen3- our next AI foundation models for protein generation. We develop compute-optimal scaling laws up to 46B parameters on 1.5T tokens with real evidence in the wet lab. +we solve a new set of challenges for drug discovery

What could scaling unlock for biology? Introducing ProGen3- our next AI foundation models for protein generation. We develop compute-optimal scaling laws up to 46B parameters on 1.5T tokens with real evidence in the wet lab. +we solve a new set of challenges for drug discovery

Ali Madani

80,665 views • 1 year ago

Music Protocol's Season 1 Airdrop is LIVE! ⛓️🎧 160M $RECORD tokens are up for grabs on Base as community incentives. These tokens will be distributed across multiple Seasons, each designed to enhance different aspects of the ecosystem. Today, we're announcing the launch of our pre-TGE season—Season 1, which is focused on growing and strengthening our community. Join the Music Protocol community, complete tasks, & earn $RECORD tokens. 👉 Sign up now & start earning 👉 Want to know more about Season 1 and our plans for future seasons? Dive into our Mirror article. Let's build the future of music together.

Music Protocol's Season 1 Airdrop is LIVE! ⛓️🎧 160M $RECORD tokens are up for grabs on Base as community incentives. These tokens will be distributed across multiple Seasons, each designed to enhance different aspects of the ecosystem. Today, we're announcing the launch of our pre-TGE season—Season 1, which is focused on growing and strengthening our community. Join the Music Protocol community, complete tasks, & earn $RECORD tokens. 👉 Sign up now & start earning 👉 Want to know more about Season 1 and our plans for future seasons? Dive into our Mirror article. Let's build the future of music together.

Record Nexus

87,625 views • 2 years ago

Introducing ON WAX, a new show from For The Record with Elsie not Elise 💿 & nosa ! putting the music conversations that flood our timelines on wax 🎤 Episode 1 : INDUSTRY PLANT OR PRODUCT OF THE INDUSTRY ? 👀 Drops tomorrow on YouTube at 1pm ET ⏰

Introducing ON WAX, a new show from For The Record with Elsie not Elise 💿 & nosa ! putting the music conversations that flood our timelines on wax 🎤 Episode 1 : INDUSTRY PLANT OR PRODUCT OF THE INDUSTRY ? 👀 Drops tomorrow on YouTube at 1pm ET ⏰

FOR THE RECORD

86,509 views • 1 year ago

3 years in the making. The most significant moment in my career. Introducing Frame.io Verison 4. The journey has been long and difficult. We reinvented our team culture and values, navigated the Adobe acquisition, and rebuilt our products from the ground up — all with the aspiration of setting a new, higher standard for craft and quality in our products. But we made it together. And I couldn’t be more proud of our team.

3 years in the making. The most significant moment in my career. Introducing Frame.io Verison 4. The journey has been long and difficult. We reinvented our team culture and values, navigated the Adobe acquisition, and rebuilt our products from the ground up — all with the aspiration of setting a new, higher standard for craft and quality in our products. But we made it together. And I couldn’t be more proud of our team.

Kurt Varner

74,550 views • 2 years ago

🚀 Introducing Emu3.5 — a large-scale multimodal world model that natively predicts the next vision-language state. 🔥 Trained on over 10T interleaved vision-language tokens and enhanced with reinforcement learning, Emu3.5 achieves powerful multimodal reasoning and generation. ⚡ Powered by our new Discrete Diffusion Adaptation (DiDA) for 20× faster inference. 🔥 Emu3.5 outperforms Nano Banana across image generation, editing, interleaved tasks and more. 🌍 Explore Emu3.5: Github: #Emu3 #MultimodalAI #WorldModel #NextTokenPrediction

🚀 Introducing Emu3.5 — a large-scale multimodal world model that natively predicts the next vision-language state. 🔥 Trained on over 10T interleaved vision-language tokens and enhanced with reinforcement learning, Emu3.5 achieves powerful multimodal reasoning and generation. ⚡ Powered by our new Discrete Diffusion Adaptation (DiDA) for 20× faster inference. 🔥 Emu3.5 outperforms Nano Banana across image generation, editing, interleaved tasks and more. 🌍 Explore Emu3.5: Github: #Emu3 #MultimodalAI #WorldModel #NextTokenPrediction

BAAI

51,880 views • 10 months ago

"We're looking after more than the number of patients that we're supposed to look after." At Joint Reps earlier this month, members told us about staffing levels on their last shift. Complete our survey by 1 April to help us campaign for change:

"We're looking after more than the number of patients that we're supposed to look after." At Joint Reps earlier this month, members told us about staffing levels on their last shift. Complete our survey by 1 April to help us campaign for change:

The RCN

14,613 views • 2 years ago

📣 Share this with everyone you can 📣 We've been busy working on the next Faux Fur line for you and now we need your input! Help us make this more perfect for you by filling out our survey, #newfabric #FursuitFriday #fauxfur #fakefur #costuming #stretchfur

📣 Share this with everyone you can 📣 We've been busy working on the next Faux Fur line for you and now we need your input! Help us make this more perfect for you by filling out our survey, #newfabric #FursuitFriday #fauxfur #fakefur #costuming #stretchfur

Big Z Fabric

42,225 views • 3 years ago

As we head to Dublin for the next leg of our preseason tour, just got on the coach to everyone singing happy birthday to me. Thanks to everyone for their birthday wishes and looking forward to catching up with everyone at the Camden and at the game. See you there - LUFC MOT

As we head to Dublin for the next leg of our preseason tour, just got on the coach to everyone singing happy birthday to me. Thanks to everyone for their birthday wishes and looking forward to catching up with everyone at the Camden and at the game. See you there - LUFC MOT

Follow Me And LUFC

12,994 views • 1 month ago

At the YLAB Townhall, President and CEO, Amin Nasser, challenged participants to think beyond the next quarter and focus on the decades ahead With more than half of our workforce under the age of 35, the next chapter of our story is already being written by a new generation of leaders

At the YLAB Townhall, President and CEO, Amin Nasser, challenged participants to think beyond the next quarter and focus on the decades ahead With more than half of our workforce under the age of 35, the next chapter of our story is already being written by a new generation of leaders

aramco

7,650,699 views • 2 months ago