Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Dear frontend devs and UI designers. I bring you Liquid DOM, a complete and faithful implementation of Liquid Glass on the Web. - Shape morphing - All properties animatable - Dynamic refraction and reflection - Adaptive tint - Adaptive specular highlight - Dispersion - Full html integration - Super... show more

Andrew Prifer

5,258 subscribers

1,355,116 Aufrufe • vor 2 Monaten •via X (Twitter)

Kunst Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Exciting Update: The freshly redesigned Reactor and our new website are here! What's new: - Upgraded Reactor & Website UI with New Design - Focused Matrix Pages (MVP on the way🤫) - More Sections for B2B Opportunities (get in contact for Reactor API access or Reactor ($ARC on Virtuals) integration) We’re putting the finishing touches on a few features and pages, which will be fully publicly available in the next couple of days. With this update, including the Reactor enhancement and Matrix development, we expect new opportunities and high-level collaborations coming our way in the next months.🤝 Head over to and and test yourself! For more updates, follow ARC and our CEO Tj Dunham.

Exciting Update: The freshly redesigned Reactor and our new website are here! What's new: - Upgraded Reactor & Website UI with New Design - Focused Matrix Pages (MVP on the way🤫) - More Sections for B2B Opportunities (get in contact for Reactor API access or Reactor ($ARC on Virtuals) integration) We’re putting the finishing touches on a few features and pages, which will be fully publicly available in the next couple of days. With this update, including the Reactor enhancement and Matrix development, we expect new opportunities and high-level collaborations coming our way in the next months.🤝 Head over to and and test yourself! For more updates, follow ARC and our CEO Tj Dunham.

ARC

28,955 Aufrufe • vor 1 Jahr

LLM Wikis + HTML Artifacts are insanely powerful. You should seriously consider this in your workflows. LLM Wikis captures all the important information that lets you and your agents do meaningful work. HTML artifacts present that information in interesting ways that allow you to take important actions along with your agents. My HTML artifacts sit on top of my LLM wikis. They are dynamic and are easily extended as needs arise. I have hooked my Artifacts to talk to my agents, and similarly, the agents can talk to artifacts. This has allowed me to build powerful artifacts that reduce my inbox to zero, keep me updated on any topic of interest, fast prototyping, do deep research, design/trigger new experiments, generate figures to improve understanding, schedule research, search relevant information, discover topics, and so much more. What you see in the clip is not a website. It's a simple interactive HTML artifact. HTML artifacts are useful for designers, engineers, researchers, students, and anyone working with agents. Lastly, HTML doesn't replace Markdown. They are a much better combination working together.

LLM Wikis + HTML Artifacts are insanely powerful. You should seriously consider this in your workflows. LLM Wikis captures all the important information that lets you and your agents do meaningful work. HTML artifacts present that information in interesting ways that allow you to take important actions along with your agents. My HTML artifacts sit on top of my LLM wikis. They are dynamic and are easily extended as needs arise. I have hooked my Artifacts to talk to my agents, and similarly, the agents can talk to artifacts. This has allowed me to build powerful artifacts that reduce my inbox to zero, keep me updated on any topic of interest, fast prototyping, do deep research, design/trigger new experiments, generate figures to improve understanding, schedule research, search relevant information, discover topics, and so much more. What you see in the clip is not a website. It's a simple interactive HTML artifact. HTML artifacts are useful for designers, engineers, researchers, students, and anyone working with agents. Lastly, HTML doesn't replace Markdown. They are a much better combination working together.

elvis

248,638 Aufrufe • vor 3 Monaten

Combinatorial complexity is often the bane of imitation learning - including VLA models! Jesse Zhang and Marius Memmel proposed a way around this, using VLMs to perform problem reduction for imitation. The insight is simple - 1) High-level VLM takes a complex scene/task and reducing it a minimal representation (via masking and path prediction) that is needed to act in the world. 2) A low-level policy then takes this reduced representation and generates actions to be executed in the world. The high-level policy absorbs all the combinatorial complexity of the problem, leaving the low-level to focus on dexterity and geometric reasoning. Super simple, works really well across policy classes and problem settings! - 41.4× sim2real improvement (3DDA) and 2–3.5× boosts for π₀ and ACT in the real world. Paper: Website: Demo: Fun collaboration led by Jesse Zhang Marius Memmel with lots of collaborators! Let us know what you think 😀

Combinatorial complexity is often the bane of imitation learning - including VLA models! Jesse Zhang and Marius Memmel proposed a way around this, using VLMs to perform problem reduction for imitation. The insight is simple - 1) High-level VLM takes a complex scene/task and reducing it a minimal representation (via masking and path prediction) that is needed to act in the world. 2) A low-level policy then takes this reduced representation and generates actions to be executed in the world. The high-level policy absorbs all the combinatorial complexity of the problem, leaving the low-level to focus on dexterity and geometric reasoning. Super simple, works really well across policy classes and problem settings! - 41.4× sim2real improvement (3DDA) and 2–3.5× boosts for π₀ and ACT in the real world. Paper: Website: Demo: Fun collaboration led by Jesse Zhang Marius Memmel with lots of collaborators! Let us know what you think 😀

Abhishek Gupta

22,354 Aufrufe • vor 10 Monaten

RELEASE DAY After almost 10 years of hard work, tireless research, and a dive deep into the kernels of computer science, I finally realized a dream: running a high-level language on GPUs. And I'm giving it to the world! Bend compiles modern programming features, including: - Lambdas with full closure support - Unrestricted recursion and loops - Fast object allocations of all kinds - Folds, ADTs, continuations and much more To HVM2, a new runtime capable of spreading that workload across 1000's of cores, in a thread-safe, low-overhead fashion. As a result, we finally have a true high-level language that runs natively on GPUs! Here's a quick demo:

RELEASE DAY After almost 10 years of hard work, tireless research, and a dive deep into the kernels of computer science, I finally realized a dream: running a high-level language on GPUs. And I'm giving it to the world! Bend compiles modern programming features, including: - Lambdas with full closure support - Unrestricted recursion and loops - Fast object allocations of all kinds - Folds, ADTs, continuations and much more To HVM2, a new runtime capable of spreading that workload across 1000's of cores, in a thread-safe, low-overhead fashion. As a result, we finally have a true high-level language that runs natively on GPUs! Here's a quick demo:

Taelin

2,944,724 Aufrufe • vor 2 Jahren

🚀 I'm launching r3f-webgpu-perf today! "npm i r3f-webgpu-perf" One thing I missed while working with WebGPU in React Three Fiber was a performance monitor similar to r3f-perf. The existing tool is fantastic, but it doesn’t support the WebGPU renderer yet. So I decided to build one. ✅ Supports both WebGL and WebGPU ✅ Modern and customizable UI ✅ Lightweight and easy to integrate ✅ Built specifically for React Three Fiber My goal is to turn r3f-webgpu-perf into more than just a metrics dashboard. I want it to become a learning tool that provides real-time optimization suggestions based on the techniques I’ve developed while building hundreds of interactive 3D projects over the last two decades. A vanilla Three.js version is also planned. If you’re building with Three.js, React Three Fiber, or WebGPU, I’d love for you to try it and share your feedback. ⭐ GitHub: 📦 NPM: Every GitHub star helps make the tool better for the entire community. #threejs #creativecoding #webgpu #r3f

🚀 I'm launching r3f-webgpu-perf today! "npm i r3f-webgpu-perf" One thing I missed while working with WebGPU in React Three Fiber was a performance monitor similar to r3f-perf. The existing tool is fantastic, but it doesn’t support the WebGPU renderer yet. So I decided to build one. ✅ Supports both WebGL and WebGPU ✅ Modern and customizable UI ✅ Lightweight and easy to integrate ✅ Built specifically for React Three Fiber My goal is to turn r3f-webgpu-perf into more than just a metrics dashboard. I want it to become a learning tool that provides real-time optimization suggestions based on the techniques I’ve developed while building hundreds of interactive 3D projects over the last two decades. A vanilla Three.js version is also planned. If you’re building with Three.js, React Three Fiber, or WebGPU, I’d love for you to try it and share your feedback. ⭐ GitHub: 📦 NPM: Every GitHub star helps make the tool better for the entire community. #threejs #creativecoding #webgpu #r3f

Anderson Mancini

23,984 Aufrufe • vor 2 Monaten

Welcome to the Full Vertical Integration era of Web3. Until now, devs have had to patch together multiple networks to build useful dApps. And the dApps themselves had to hop across multiple networks to function. But what if you had all that you needed on one shared security, low-latency network? That's what Supra Layer 1 is building, one powerful MultiVM blockchain with in-built oracle data feeds, onchain randomness, automation, and cross-chain communication. Everything developers need, all in one place, making it simpler to build dApps — while helping dApps themselves run faster, more secure, and with lower costs. We're bringing the power of Full Vertical Integration to Web3 to enable a new breed of Super dApps, and it’s just getting started. LFMove!

Welcome to the Full Vertical Integration era of Web3. Until now, devs have had to patch together multiple networks to build useful dApps. And the dApps themselves had to hop across multiple networks to function. But what if you had all that you needed on one shared security, low-latency network? That's what Supra Layer 1 is building, one powerful MultiVM blockchain with in-built oracle data feeds, onchain randomness, automation, and cross-chain communication. Everything developers need, all in one place, making it simpler to build dApps — while helping dApps themselves run faster, more secure, and with lower costs. We're bringing the power of Full Vertical Integration to Web3 to enable a new breed of Super dApps, and it’s just getting started. LFMove!

Supra

515,255 Aufrufe • vor 1 Jahr

🫧 Best practices for native tabs: ◆ Use Apple SF Symbols for icons on iOS, Material design icons on Android, and Material or Lucide icons on web ◆ Use platform colors for dynamic tints. The liquid glass updates automatically with dynamic iOS colors like PlatformColor("label") (black in light mode, white in dark mode) ◆ Consider a custom web tab system using _layout.web.tsx while we improve the web fallback ◆ Remove any custom "scroll to top" logic in favor of our first-class support in NativeTabs You can still use JS or headless tabs for more control over look and feel. Get all the details in this Expo Router v6 blog post:

🫧 Best practices for native tabs: ◆ Use Apple SF Symbols for icons on iOS, Material design icons on Android, and Material or Lucide icons on web ◆ Use platform colors for dynamic tints. The liquid glass updates automatically with dynamic iOS colors like PlatformColor("label") (black in light mode, white in dark mode) ◆ Consider a custom web tab system using _layout.web.tsx while we improve the web fallback ◆ Remove any custom "scroll to top" logic in favor of our first-class support in NativeTabs You can still use JS or headless tabs for more control over look and feel. Get all the details in this Expo Router v6 blog post:

Expo

11,781 Aufrufe • vor 10 Monaten

Huge UI design boost by adding this to my AI workflow 1. Explore variations with Variant. The secret is to use "shuffle layout" and "see other views". This keeps the essence of a design that I like, but gives interesting layout variations. I also change colors and explore narrow by specifying one or two things in prompt, like font name, UI style or light/dark mode. 2. Copy HTML and prompt with Gemini 3 in site builder. Fix minute details like fonts, icons, assets, intro/scroll animations, adaptive layout and make the whole thing functional. Include image references, button styles, code snippets and other components to keep things creative. Often, I see sites that have one cool thing, but the rest is super generic. That's because AI is especially good at being generic without continuously feeding specs. 3. Turn into a landing page by prompt adding new components/sections and connect/adapt new pages. This is the part where most people stop, but it's actually the easiest since AI is so good at reading existing code. "Adapt this {page code} for a {features, blog, pricing, login} page." Finally, set up SEO and custom domain name. Boom, you just shipped a pro-level site that doesn't look generic.

Huge UI design boost by adding this to my AI workflow 1. Explore variations with Variant. The secret is to use "shuffle layout" and "see other views". This keeps the essence of a design that I like, but gives interesting layout variations. I also change colors and explore narrow by specifying one or two things in prompt, like font name, UI style or light/dark mode. 2. Copy HTML and prompt with Gemini 3 in site builder. Fix minute details like fonts, icons, assets, intro/scroll animations, adaptive layout and make the whole thing functional. Include image references, button styles, code snippets and other components to keep things creative. Often, I see sites that have one cool thing, but the rest is super generic. That's because AI is especially good at being generic without continuously feeding specs. 3. Turn into a landing page by prompt adding new components/sections and connect/adapt new pages. This is the part where most people stop, but it's actually the easiest since AI is so good at reading existing code. "Adapt this {page code} for a {features, blog, pricing, login} page." Finally, set up SEO and custom domain name. Boom, you just shipped a pro-level site that doesn't look generic.

Meng To

65,440 Aufrufe • vor 6 Monaten

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!

Akshay 🚀

86,515 Aufrufe • vor 3 Monaten

This is no routine AI‑video iteration. One model perceives scene‑level physics rather than simple pixel generation, and that is Seedance Enterprise 2.5. Creators no longer need dozens of rerolls. Most usable footage only demands 1‑2 generations, lowering overall spending and streamlining creation. It delivers AI‑free lifelike visuals, cinematic‑level lighting and camera movement, 30-second single-shot generation to orchestrate complete scene‑wide narratives. Accepts up to 50 reference inputs, so your characters and visual style stay perfectly locked across every single frame. With localized editing, the individual elements can be edited locally without re-rendering the entire video. I’ve been building a full creative pipeline on BytePlus Lumina, chaining Seedance for motion with Seedream for keyframe control and Seedaudio for adaptive soundscapes. It’s no longer about generating clips; it’s about directing scenes. Seedance 2.5 API is about to launch on BytePlus, and now you can try it directly on Lumina.

This is no routine AI‑video iteration. One model perceives scene‑level physics rather than simple pixel generation, and that is Seedance Enterprise 2.5. Creators no longer need dozens of rerolls. Most usable footage only demands 1‑2 generations, lowering overall spending and streamlining creation. It delivers AI‑free lifelike visuals, cinematic‑level lighting and camera movement, 30-second single-shot generation to orchestrate complete scene‑wide narratives. Accepts up to 50 reference inputs, so your characters and visual style stay perfectly locked across every single frame. With localized editing, the individual elements can be edited locally without re-rendering the entire video. I’ve been building a full creative pipeline on BytePlus Lumina, chaining Seedance for motion with Seedream for keyframe control and Seedaudio for adaptive soundscapes. It’s no longer about generating clips; it’s about directing scenes. Seedance 2.5 API is about to launch on BytePlus, and now you can try it directly on Lumina.

SANI BULA

174,790 Aufrufe • vor 9 Tagen

Engineers with taste will make a lot of so-called designers irrelevant. It’s 2026. With all the vibe-coding tools we have now, you can build real working prototypes of almost anything in a few hours. So when I see another “iOS 27 concept” that is just a Figma screenshot with a gradient or a circular one, and some fake Liquid Glass layer on top, that’s laziness at the next level for the sake of engagement.

Engineers with taste will make a lot of so-called designers irrelevant. It’s 2026. With all the vibe-coding tools we have now, you can build real working prototypes of almost anything in a few hours. So when I see another “iOS 27 concept” that is just a Figma screenshot with a gradient or a circular one, and some fake Liquid Glass layer on top, that’s laziness at the next level for the sake of engagement.

Tykra

29,757 Aufrufe • vor 2 Monaten

This is a standard practice for almost all Tier-1 banking applications in Nigeria, and for some fintech applications I’ve previously performed pentests on. Client-side encryption isn’t a total waste, or a waste of compute, as some people have claimed, but rather a measure to protect against API tampering or API request/response manipulation between the client and the server when implemented properly. Even with HTTPS, attackers can capture a decrypted version of web or mobile API data in transit because the browser and the server establish a level of trust during the TLS handshake. Attackers can leverage this trust to capture & proxy already-decrypted traffic, tamper with it, and then forward it to the server. This allows them to override what the user interface or client is originally supposed to send and replace it with data of their choosing. That is why validation needs to be performed on both the client and the server side. To wrap up, encrypting API requests and responses makes it significantly harder for attackers to tamper with data, even if they capture the traffic, unless they have access to the encryption details (algorithm, encryption mode, key size, secret key, and initialization vector), assuming asymmetric encryption is used. In the demo below, you can see how I discovered additional parameters (balance, is_admin) in the API response, captured the registration API request, despite it being sent over HTTPS from the interface, added the discovered parameters, and successfully inflated my balance to 50 billion and also escalated my privileges to admin, and ultimately deleted the accounts of two live users/customers. In the second slide, I captured an API traffic of a bank app, and you can see how difficult the payloads are to read.

This is a standard practice for almost all Tier-1 banking applications in Nigeria, and for some fintech applications I’ve previously performed pentests on. Client-side encryption isn’t a total waste, or a waste of compute, as some people have claimed, but rather a measure to protect against API tampering or API request/response manipulation between the client and the server when implemented properly. Even with HTTPS, attackers can capture a decrypted version of web or mobile API data in transit because the browser and the server establish a level of trust during the TLS handshake. Attackers can leverage this trust to capture & proxy already-decrypted traffic, tamper with it, and then forward it to the server. This allows them to override what the user interface or client is originally supposed to send and replace it with data of their choosing. That is why validation needs to be performed on both the client and the server side. To wrap up, encrypting API requests and responses makes it significantly harder for attackers to tamper with data, even if they capture the traffic, unless they have access to the encryption details (algorithm, encryption mode, key size, secret key, and initialization vector), assuming asymmetric encryption is used. In the demo below, you can see how I discovered additional parameters (balance, is_admin) in the API response, captured the registration API request, despite it being sent over HTTPS from the interface, added the discovered parameters, and successfully inflated my balance to 50 billion and also escalated my privileges to admin, and ultimately deleted the accounts of two live users/customers. In the second slide, I captured an API traffic of a bank app, and you can see how difficult the payloads are to read.

Ghost St Badmus

217,475 Aufrufe • vor 8 Monaten

With optimized builds, Hyperfy V1 came very close to matching the look and feel of Unity or other game engines—but in the browser. Few people realized how well it also performed on VR browsers and the level of immersion already possible on the web. Now, with V2, Hyperfy introduces a much more powerful engine and full physics support. The browser remains the most straightforward, frictionless, and accessible way to experience these technologies. This positions Hyperfy perfectly for the upcoming wave of VR, as new devices, technologies, and major companies enter the space. Rick and I are pooling resources and fully committed to helping build this out, bringing everything to the next level. Here I’m jamming with him in V1, with him using the Apple Vision Pro. The apartment you see here is something I built for the upcoming @timeofemergence marketplace. #avp #webXR Three.js

With optimized builds, Hyperfy V1 came very close to matching the look and feel of Unity or other game engines—but in the browser. Few people realized how well it also performed on VR browsers and the level of immersion already possible on the web. Now, with V2, Hyperfy introduces a much more powerful engine and full physics support. The browser remains the most straightforward, frictionless, and accessible way to experience these technologies. This positions Hyperfy perfectly for the upcoming wave of VR, as new devices, technologies, and major companies enter the space. Rick and I are pooling resources and fully committed to helping build this out, bringing everything to the next level. Here I’m jamming with him in V1, with him using the Apple Vision Pro. The apartment you see here is something I built for the upcoming @timeofemergence marketplace. #avp #webXR Three.js

𝚟𝚘𝚡𝚟𝚒𝚎𝚗𝚗𝚎

23,618 Aufrufe • vor 1 Jahr

Devs are printing $50k-$200k/week on Polymarket Hard truth: You won't hit those numbers on the frontend. The UI lags 10x behind reality. I’ve been a dev for 8+ years. I’m opening a FREE bootcamp to teach you the basics on how to build your first BOT. Why I’m doing this: > Most of you will just bookmark this and never execute. > If you outgrow me, I gain a smarter circle. We all level up The plan (2 weeks bootcamp) : → Learn the Polymarket API basics → Fetch raw data → Build an interpretation engine that executes trades To join: → Join Polymarket via my link: → Deposit $20+ → DM me your TG handle Group will open soon. If you have not been invited yet, you will be asap. (The clip below shows what raw API speed looks like)

Devs are printing $50k-$200k/week on Polymarket Hard truth: You won't hit those numbers on the frontend. The UI lags 10x behind reality. I’ve been a dev for 8+ years. I’m opening a FREE bootcamp to teach you the basics on how to build your first BOT. Why I’m doing this: > Most of you will just bookmark this and never execute. > If you outgrow me, I gain a smarter circle. We all level up The plan (2 weeks bootcamp) : → Learn the Polymarket API basics → Fetch raw data → Build an interpretation engine that executes trades To join: → Join Polymarket via my link: → Deposit $20+ → DM me your TG handle Group will open soon. If you have not been invited yet, you will be asap. (The clip below shows what raw API speed looks like)

Jayden ⛩️

12,206 Aufrufe • vor 7 Monaten

The web was built for humans. And honestly, that's fine for you guys. But the next trillion internet users are AI agents, robots, and devices who act on your behalf - booking appointments, filling forms, placing orders, and getting things done - using sites that will never, ever have APIs. 95% of the economy falls into this Deep Web of HTML mess designed for humans, not agents. Oh, those generic computer use agents aren't taking you anywhere. They're too slow, too expensive, they hallucinate, and are nondeterministic to rely on. That changes now. This is me, Mino, a web agents API to build on this Deep Web. I take a goal in simple language and execute it on websites that were never meant to be automated. Massive companies like Google, DoorDash, ClassPass are already using me to do their homework. Now it’s your turn. How though? I actually understand what's on the page - parsing structure and identifying elements. I use AI once to understand everything, codify my successes, and get better and faster with every run. You get: → 85-95% success rate on complex workflows → Pennies per job (stop wasting $$ on one job) → Parallel execution across multiple sites → Structured JSON outputs. Every. Single. Time. The web wasn't built for agents. I forced it to work anyway. Go build something real. 50 completed runs on the house:

The web was built for humans. And honestly, that's fine for you guys. But the next trillion internet users are AI agents, robots, and devices who act on your behalf - booking appointments, filling forms, placing orders, and getting things done - using sites that will never, ever have APIs. 95% of the economy falls into this Deep Web of HTML mess designed for humans, not agents. Oh, those generic computer use agents aren't taking you anywhere. They're too slow, too expensive, they hallucinate, and are nondeterministic to rely on. That changes now. This is me, Mino, a web agents API to build on this Deep Web. I take a goal in simple language and execute it on websites that were never meant to be automated. Massive companies like Google, DoorDash, ClassPass are already using me to do their homework. Now it’s your turn. How though? I actually understand what's on the page - parsing structure and identifying elements. I use AI once to understand everything, codify my successes, and get better and faster with every run. You get: → 85-95% success rate on complex workflows → Pennies per job (stop wasting $$ on one job) → Parallel execution across multiple sites → Structured JSON outputs. Every. Single. Time. The web wasn't built for agents. I forced it to work anyway. Go build something real. 50 completed runs on the house:

TinyFish

656,586 Aufrufe • vor 8 Monaten

Introducing /visual-plan - a skill to generate rich, visual plans for Claude Code and Codex. Plan mode in Claude Code is incredible. But I always find my eyes glazing over when it gives me this huge markdown essay in my terminal. I found I can make much better visual plans with reusable components. So I made a skill called `/visual-plan`. It generates plans as MDX with visual, interactive components. Diagrams, interactive API specs, schema design changes, annotated code, and even pan and zoomable wireframes. So for any UI work, you can look at a wireframe first, comment on it, iterate, and then have the agent work. I’ve found this to be a much more intuitive interface for reasoning about what the agent is doing. It’s somewhat inspired by that popular post about how HTML is better than Markdown. But HTML can be slow and verbose to write. And it doesn’t look good checked into a repo. This has really made me feel like humans and engineering are entering a new abstraction phase, where we reason about things at the plan level. As long as the plan is good, agents are getting more and more reliable at executing on it. Almost to the degree that we trust the C compiler to compile to assembly reliably. Plans are the new intermediate representation. I also made a skill for the reverse of this, called `/visual-recap`. After the agent works, it gives you a recap of everything it did. Same idea: wireframes, interactive API specs and diffs, schemas, annotated code, etc. So now when you’re reviewing what the agent did for you, or looking at a pull request of somebody else’s code, you can see a visual recap instead of just reading a wall of text. It’s all free and open source. You can find it on my GitHub. Will link to it in the reply because we all know how dumb these algorithms are with links.

Introducing /visual-plan - a skill to generate rich, visual plans for Claude Code and Codex. Plan mode in Claude Code is incredible. But I always find my eyes glazing over when it gives me this huge markdown essay in my terminal. I found I can make much better visual plans with reusable components. So I made a skill called `/visual-plan`. It generates plans as MDX with visual, interactive components. Diagrams, interactive API specs, schema design changes, annotated code, and even pan and zoomable wireframes. So for any UI work, you can look at a wireframe first, comment on it, iterate, and then have the agent work. I’ve found this to be a much more intuitive interface for reasoning about what the agent is doing. It’s somewhat inspired by that popular post about how HTML is better than Markdown. But HTML can be slow and verbose to write. And it doesn’t look good checked into a repo. This has really made me feel like humans and engineering are entering a new abstraction phase, where we reason about things at the plan level. As long as the plan is good, agents are getting more and more reliable at executing on it. Almost to the degree that we trust the C compiler to compile to assembly reliably. Plans are the new intermediate representation. I also made a skill for the reverse of this, called `/visual-recap`. After the agent works, it gives you a recap of everything it did. Same idea: wireframes, interactive API specs and diffs, schemas, annotated code, etc. So now when you’re reviewing what the agent did for you, or looking at a pull request of somebody else’s code, you can see a visual recap instead of just reading a wall of text. It’s all free and open source. You can find it on my GitHub. Will link to it in the reply because we all know how dumb these algorithms are with links.

Steve (Builder.io)

124,923 Aufrufe • vor 1 Monat

We're preparing for the second playtest of MIGHTREYA! Based on user feedback from the previous test, we've fixed bugs and added new features. We’d love to have your support again—please join us for the next round! To join the playtest, please join our Discord server. A selection of the new features we’ve added -Camera Assist (Hard Lock-On) -Takedown Converted to QTE -Duplicate Move Penalty -Expanded Graphics Options: V-Sync, FPS Cap, AI Upscaling -Enemy Warp Recovery When Stuck in Terrain -Stage Progression Navigation -Boss Guard Gauge Recovery and HP Adjustment -Boss Takedown Implementation -Boss Intro Cutscene -UI Operation Guide -Simplified Command List -Tutorial Level -One-Point Tutorials -Streaming Comment Features: Move Requests, Super Chat Integration -Cut-In Animation for Level 5 Charged Moves -Sub-Attack Motion and Performance Adjustments -Forced Transformation Cancel at Low HP -Option: Toggle PlayStation-Style Button Icons -Score and Result System Finalized: Displays Final Rank -Lock-On Distance Adjustment

We're preparing for the second playtest of MIGHTREYA! Based on user feedback from the previous test, we've fixed bugs and added new features. We’d love to have your support again—please join us for the next round! To join the playtest, please join our Discord server. A selection of the new features we’ve added -Camera Assist (Hard Lock-On) -Takedown Converted to QTE -Duplicate Move Penalty -Expanded Graphics Options: V-Sync, FPS Cap, AI Upscaling -Enemy Warp Recovery When Stuck in Terrain -Stage Progression Navigation -Boss Guard Gauge Recovery and HP Adjustment -Boss Takedown Implementation -Boss Intro Cutscene -UI Operation Guide -Simplified Command List -Tutorial Level -One-Point Tutorials -Streaming Comment Features: Move Requests, Super Chat Integration -Cut-In Animation for Level 5 Charged Moves -Sub-Attack Motion and Performance Adjustments -Forced Transformation Cancel at Low HP -Option: Toggle PlayStation-Style Button Icons -Score and Result System Finalized: Displays Final Rank -Lock-On Distance Adjustment

Wishlist MIGHTREYA on Steam

36,048 Aufrufe • vor 11 Monaten

i’ve been on a digital detox the past week. reading. journalling. and catching up on rest. offline is the new luxury. i’m going to be incorporating more stillness in my life. life can move so fast. i continue to be reminded of the beauty of slowness. slow walks. slow breaths. slow mornings. i’ve been in big sur, california. i learned the importance of figuring out my one big domino. the one thing that i can complete that when done makes everything else easier. for me it’s writing. writing unlocks epiphanies. unlocks opportunities. unlocks relationships. and I genuinely love it. i’m going full-time artist mode (delegated all operations across all my companies) and spending the rest of the year writing and focused on high-level strategy. my mantra: chop wood, carry water

i’ve been on a digital detox the past week. reading. journalling. and catching up on rest. offline is the new luxury. i’m going to be incorporating more stillness in my life. life can move so fast. i continue to be reminded of the beauty of slowness. slow walks. slow breaths. slow mornings. i’ve been in big sur, california. i learned the importance of figuring out my one big domino. the one thing that i can complete that when done makes everything else easier. for me it’s writing. writing unlocks epiphanies. unlocks opportunities. unlocks relationships. and I genuinely love it. i’m going full-time artist mode (delegated all operations across all my companies) and spending the rest of the year writing and focused on high-level strategy. my mantra: chop wood, carry water

MATT GRAY

11,860 Aufrufe • vor 1 Jahr

I've been building a music player with Next.js for fun. Here's a quick demo of how it works (it's open source!) • Demo: • Code: If you want to learn more about how it's built, here's more details ↓ I'm using Postgres (with Drizzle) to store information about the songs and playlists. Audio and image files are stored in Vercel Blob (object storage), and the URLs are then referenced in the database. For the UI, I'm using shadcn/ui (so Tailwind CSS and Radix). This made it easy to copy/paste in some nice components, like the dropdown menus. I built the entire first version of the UI in v0 and then iterated from there, feeding it my Drizzle schema as a source in the project and having it scaffold some of the boilerplate for me: I added support for keyboard navigation (using arrow keys) or vim motions (j/k to go up/down, and h/l to go between playlists and tracks). Also, space to toggle the now playing song, and / to focus the search input. The search function has a nice utility to highlight the currently searched text on the page in yellow. Then, I was exploring how to pass metadata from my application to macOS or iOS. Turns out there's an API for that – MediaSession. Web apps can share metadata about what media is playing (title, artist, album artwork) and sync play/pause/seek with system media controls. Works across modern browsers — even integrates with iOS dynamic island and shows up on lock screens: I set up my app like a PWA – it has a manifest.json file, so it can be installed to my iOS home screen or added to my dock on macOS. On iOS, it then uses the full screen height `100dvh` (dynamic viewport) and has padding on the bottom for the safe area with the `env()` CSS function. Finally, I was able to use the Vercel AI SDK in a script to clean up the metadata on audio files I downloaded from YouTube. Bonus: I even was able to dogfood the React Compiler, which helped me fix a performance bug! That's all! It's fun to make personal software:

I've been building a music player with Next.js for fun. Here's a quick demo of how it works (it's open source!) • Demo: • Code: If you want to learn more about how it's built, here's more details ↓ I'm using Postgres (with Drizzle) to store information about the songs and playlists. Audio and image files are stored in Vercel Blob (object storage), and the URLs are then referenced in the database. For the UI, I'm using shadcn/ui (so Tailwind CSS and Radix). This made it easy to copy/paste in some nice components, like the dropdown menus. I built the entire first version of the UI in v0 and then iterated from there, feeding it my Drizzle schema as a source in the project and having it scaffold some of the boilerplate for me: I added support for keyboard navigation (using arrow keys) or vim motions (j/k to go up/down, and h/l to go between playlists and tracks). Also, space to toggle the now playing song, and / to focus the search input. The search function has a nice utility to highlight the currently searched text on the page in yellow. Then, I was exploring how to pass metadata from my application to macOS or iOS. Turns out there's an API for that – MediaSession. Web apps can share metadata about what media is playing (title, artist, album artwork) and sync play/pause/seek with system media controls. Works across modern browsers — even integrates with iOS dynamic island and shows up on lock screens: I set up my app like a PWA – it has a manifest.json file, so it can be installed to my iOS home screen or added to my dock on macOS. On iOS, it then uses the full screen height `100dvh` (dynamic viewport) and has padding on the bottom for the safe area with the `env()` CSS function. Finally, I was able to use the Vercel AI SDK in a script to clean up the metadata on audio files I downloaded from YouTube. Bonus: I even was able to dogfood the React Compiler, which helped me fix a performance bug! That's all! It's fun to make personal software:

Lee Robinson

118,242 Aufrufe • vor 1 Jahr