正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Prototyped another iteration of a hand-tracking-based BoxelXR toolbar. This time, it's a circular menu spawned in front of a user once the index pinch is triggered. Notes: 1) It works great with four elements, but it's hard to scale for a higher number; 2) The selection interaction is forgiving... for spatial positioning errors. This is because a 3D hand span is interpreted through a 1D angle range (a 1D subspace in the polar coordinate system of 2D projection space, which is a subspace of the 3D space of the experience, respectively). This prevents false positives and makes it easy for users to execute. Precise muscle coordination is not required, either. Design tip: Lower the dimensionality of your interaction to reduce cognitive loads and make it more accessible. 3) Using depth-based animations to show different UI states is a great way to leverage the third dimension and add something interesting to the experience. But be careful. When the UI faces a user's face, the contrast in the motion might be low, so use it only as an additional layer. In this prototype, color coding is the primary way to mark changes in a UI state. ⬇️🐙🐱 Download the prototype — #handtracking #xrinteraction #xri #xr #virtualreality #csharp #unity3d #prototyping #spatialcomputing #spatialdesign #spatialui #ux #ui #xrdevelopmentshow more

Oleg Frolov

7,055 subscribers

11,746 次观看 • 2 年前 •via X (Twitter)

艺术科学技术教育

Anya Rossi• Live Now

Private livecam show

5 条评论

P 的头像

P2 年前

One of the best examples of reinventing interfaces for XR I've seen so far. Incredibly elegant, given how simple yet powerful this is. Hats off.

Lubos 的头像

Lubos2 年前

Beautiful. Pinch & drag is a way to go for the menus. Minimalist and easy to use.

Tim Arterbury 的头像

Tim Arterbury2 年前

Amazing!! Love this idea! 💡

Jimmy6DOF 的头像

Jimmy6DOF2 年前

loving this work and thanks for the unity project starter files I played with vr-slider but this has come a long way since then keep innovating 🤩 !!

Illuminated Reality Studios 的头像

Illuminated Reality Studios2 年前

Could you do the 2 hand pinch stretch gesture to scale it up to more buttons on the fly

相关视频

Redesigned the previous prototype with visual mechanics inspired by Blender. The circular selection interaction pattern is a great way to enhance accessibility and improve accuracy by restricting item selection to a single dimension and, therefore, reducing noise in user input. For a circular menu, one may describe spatial transformations using polar coordinates components: Radius and Angle. I used Radius to set selection availability and Angle to define the selected item. Plus, this particular pattern allows you to expose the names of the items, which might be helpful in cases when the functions of the items are not self-obvious. Feel free to test the prototype on your own and share your thoughts :) #handtracking #xrinteraction #xri #xr #virtualreality #unity3d #prototyping #spatialcomputing #spatialdesign #spatialui #ux #ui #xrdevelopment #spatialprototype #interactiondesign

Redesigned the previous prototype with visual mechanics inspired by Blender. The circular selection interaction pattern is a great way to enhance accessibility and improve accuracy by restricting item selection to a single dimension and, therefore, reducing noise in user input. For a circular menu, one may describe spatial transformations using polar coordinates components: Radius and Angle. I used Radius to set selection availability and Angle to define the selected item. Plus, this particular pattern allows you to expose the names of the items, which might be helpful in cases when the functions of the items are not self-obvious. Feel free to test the prototype on your own and share your thoughts :) #handtracking #xrinteraction #xri #xr #virtualreality #unity3d #prototyping #spatialcomputing #spatialdesign #spatialui #ux #ui #xrdevelopment #spatialprototype #interactiondesign

Oleg Frolov

38,202 次观看 • 2 年前

Explored the finger menu with a depth-based layout. Felt fun. Microinteractions/UI motion helped to compensate for the lack of haptic feedback by providing rich visual clues and reinforcing the user's intentions (all these subtle micro-movements). Based on the prototype, here are a few things to consider when you use this interaction pattern: 1) Perspective visual distortion. It might take more time to recognize visually distorted signs when they are arranged by depth. It's a good idea to use well-known sign sequences where the current selected element gives you a hint about the previous and next ones. A user should have an embedded knowledge of how the elements in the menu are sorted. A number selector might work well with it 2) Low range of hand movement in stationary mode. Because you need to keep visual contact with the UI, the useful range of possible hand movement is very limited. You must position your hand in front of your eyes, maintaining a comfortable distance. It restricts the number of items you can have on the menu. Plus, the trigger distance (30-40mm) also reduces the amount of menu elements you can use. Two or three items work the best (four is max). Download APK [Meta Quest] — #spatialdesign #spatialui #spatialux #vr #unity3d #prototyping #handtracking #interactiondesign #virtualreality #productdesign #xr #xrdesign #xrinteractiontoolkit #xrdevelopment #spatialcomputing

Explored the finger menu with a depth-based layout. Felt fun. Microinteractions/UI motion helped to compensate for the lack of haptic feedback by providing rich visual clues and reinforcing the user's intentions (all these subtle micro-movements). Based on the prototype, here are a few things to consider when you use this interaction pattern: 1) Perspective visual distortion. It might take more time to recognize visually distorted signs when they are arranged by depth. It's a good idea to use well-known sign sequences where the current selected element gives you a hint about the previous and next ones. A user should have an embedded knowledge of how the elements in the menu are sorted. A number selector might work well with it 2) Low range of hand movement in stationary mode. Because you need to keep visual contact with the UI, the useful range of possible hand movement is very limited. You must position your hand in front of your eyes, maintaining a comfortable distance. It restricts the number of items you can have on the menu. Plus, the trigger distance (30-40mm) also reduces the amount of menu elements you can use. Two or three items work the best (four is max). Download APK [Meta Quest] — #spatialdesign #spatialui #spatialux #vr #unity3d #prototyping #handtracking #interactiondesign #virtualreality #productdesign #xr #xrdesign #xrinteractiontoolkit #xrdevelopment #spatialcomputing

Oleg Frolov

22,202 次观看 • 2 年前

Hand Menu Interaction. The simplest trick to improve the accessibility of floating hand-attached UI panels for spatial interactions is to smooth their movement. It allows us to stabilize them and mitigate a hand tremor due to hand-tracking imperfection and/or physiological condition. (Interestingly, the visual stabilization helps reduce the physical tremor itself. I guess it normalizes the hand muscles/brain feedback loop when you target the interactables). By the way, if you are curious about how to design and prototype spatial hand-tracking-based interactions like this — join my little workshop at Hatch Conference. #handtracking #prototyping #menuinteraction #interactiondesign #spatialdesign #spatialcomputing #mixedreality #vr #virtualreality #xr #metaquest #uxdesign #uidesign #spatialui

Hand Menu Interaction. The simplest trick to improve the accessibility of floating hand-attached UI panels for spatial interactions is to smooth their movement. It allows us to stabilize them and mitigate a hand tremor due to hand-tracking imperfection and/or physiological condition. (Interestingly, the visual stabilization helps reduce the physical tremor itself. I guess it normalizes the hand muscles/brain feedback loop when you target the interactables). By the way, if you are curious about how to design and prototype spatial hand-tracking-based interactions like this — join my little workshop at Hatch Conference. #handtracking #prototyping #menuinteraction #interactiondesign #spatialdesign #spatialcomputing #mixedreality #vr #virtualreality #xr #metaquest #uxdesign #uidesign #spatialui

Oleg Frolov

27,218 次观看 • 2 年前

AI instead of UI The last few years radically changed how we think about digital products & product design process in general. What we are witnessing right now is a transition where AI is no longer just a feature; it is becoming the infrastructure of interaction. For decades, UI design was rooted in the concept of “Happy Path,” a series of static, linear screens (routes from A to B) designed to funnel users toward a goal. This “one-size-fits-all” approach assumes that all users have the same mental model, which is far from the truth. The rise of AI tools like ChatGPT and Gemini is showing that we are moving into an era of Generative Interfaces. Instead of a designer pre-determining every button and menu, the interface is synthesized in real-time based on user actions. Back in 2019, Gleb Kuznetsov and I were working on the concept of morphing Interface, the idea of a UI that adapts its structure based on user intent. The great thing about this UI is that it was highly dynamic: different users saw different content/contextual actions based on their behavior. This concept was crazy in 2019, but it is highly relevant to the modern state of the product design process. And I strongly believe that it represents the future of UI design. We will move beyond the “AI chatbox" crutch Yes, many products today treat AI as a sidecar (think of Copilots or chatbots pinned to the side of a traditional dashboard), but this is a transitional phase. Why? Because adding a chat window to a 20-year-old software layout is like putting a jet engine on a horse-drawn carriage. That's why the future isn't "AI as an add-on"; it is AI as the Operating System. AI will power generative interfaces that are rooted in anticipatory design: UI won’t wait for a command; it will surface tools based on the user's current environmental context and historical behavior. This evolution changes the very nature of product design, and we will move away from designing pages/screens and toward designing systems of logic.

AI instead of UI The last few years radically changed how we think about digital products & product design process in general. What we are witnessing right now is a transition where AI is no longer just a feature; it is becoming the infrastructure of interaction. For decades, UI design was rooted in the concept of “Happy Path,” a series of static, linear screens (routes from A to B) designed to funnel users toward a goal. This “one-size-fits-all” approach assumes that all users have the same mental model, which is far from the truth. The rise of AI tools like ChatGPT and Gemini is showing that we are moving into an era of Generative Interfaces. Instead of a designer pre-determining every button and menu, the interface is synthesized in real-time based on user actions. Back in 2019, Gleb Kuznetsov and I were working on the concept of morphing Interface, the idea of a UI that adapts its structure based on user intent. The great thing about this UI is that it was highly dynamic: different users saw different content/contextual actions based on their behavior. This concept was crazy in 2019, but it is highly relevant to the modern state of the product design process. And I strongly believe that it represents the future of UI design. We will move beyond the “AI chatbox" crutch Yes, many products today treat AI as a sidecar (think of Copilots or chatbots pinned to the side of a traditional dashboard), but this is a transitional phase. Why? Because adding a chat window to a 20-year-old software layout is like putting a jet engine on a horse-drawn carriage. That's why the future isn't "AI as an add-on"; it is AI as the Operating System. AI will power generative interfaces that are rooted in anticipatory design: UI won’t wait for a command; it will surface tools based on the user's current environmental context and historical behavior. This evolution changes the very nature of product design, and we will move away from designing pages/screens and toward designing systems of logic.

Nick Babich

53,581 次观看 • 6 个月前

Volumetric, animated 3D noise shader block in Unity. Where each frame is 2D space, and the 3rd dimension is time. So that, measurement of change within a slice is 'space', and measurement of change across slices is 'time'. As a 3D block, you see the noise animate into the 3rd dimension, but when looking at only a single slice, it appears to evolve in place. Likewise, for 4D... If: this were 3D noise, then: the 4th dimension would be whatever processing/frames/states of 3D data.

Volumetric, animated 3D noise shader block in Unity. Where each frame is 2D space, and the 3rd dimension is time. So that, measurement of change within a slice is 'space', and measurement of change across slices is 'time'. As a 3D block, you see the noise animate into the 3rd dimension, but when looking at only a single slice, it appears to evolve in place. Likewise, for 4D... If: this were 3D noise, then: the 4th dimension would be whatever processing/frames/states of 3D data.

Mirza Beig

126,907 次观看 • 8 个月前

We are witnessing a fundamental shift in how software is built. Over the decades, UI was static and predictable. But AI is changing the fundamental nature of the interface. We are moving away from fixed UI and toward a new standard: Generative UI. Generative UI lets agents participate in the UI, not just the conversation. It’s a dynamic participant in the user experience. Depending on the complexity of your app, Generative UI generally falls into three categories: 1. Static (AG-UI): UI is chosen from a fixed set of hand-built components 2. Open-Ended (MCP Apps): agent sends arbitrary content like raw HTML or iframes for total flexibility. 3. Declarative (A2UI): agent and frontend communicate via a structured UI spec for dynamic widgets and forms. The AG-UI Protocol by CopilotKit is the real breakthrough. AG-UI acts as the universal transport layer. It provides the integrations and middleware for every Gen-UI spec, making it trivial to bring dynamic components into your existing app. CopilotKit provides the go-to ecosystem for building agentic applications and is the React client of AG-UI. It is designed to be deeply integrated, allowing developers to bring their own frameworks or protocols to the table. Play around with different types of Generative UI here → Check out the video attached to see Generative UI in action. Appreciate the CopilotKit team for collaborating with me on this deep dive.

We are witnessing a fundamental shift in how software is built. Over the decades, UI was static and predictable. But AI is changing the fundamental nature of the interface. We are moving away from fixed UI and toward a new standard: Generative UI. Generative UI lets agents participate in the UI, not just the conversation. It’s a dynamic participant in the user experience. Depending on the complexity of your app, Generative UI generally falls into three categories: 1. Static (AG-UI): UI is chosen from a fixed set of hand-built components 2. Open-Ended (MCP Apps): agent sends arbitrary content like raw HTML or iframes for total flexibility. 3. Declarative (A2UI): agent and frontend communicate via a structured UI spec for dynamic widgets and forms. The AG-UI Protocol by CopilotKit is the real breakthrough. AG-UI acts as the universal transport layer. It provides the integrations and middleware for every Gen-UI spec, making it trivial to bring dynamic components into your existing app. CopilotKit provides the go-to ecosystem for building agentic applications and is the React client of AG-UI. It is designed to be deeply integrated, allowing developers to bring their own frameworks or protocols to the table. Play around with different types of Generative UI here → Check out the video attached to see Generative UI in action. Appreciate the CopilotKit team for collaborating with me on this deep dive.

Pratham

33,920 次观看 • 6 个月前

a demo of using both the gpt-oss-20b and qwen3-coder-480b in the hyperspace agentic browser. this spatial, AI-native UI is designed as an extension of the spatial space of our brain - which places some things more in recency to us, and adjacent to each other. pinch to zoom.

a demo of using both the gpt-oss-20b and qwen3-coder-480b in the hyperspace agentic browser. this spatial, AI-native UI is designed as an extension of the spatial space of our brain - which places some things more in recency to us, and adjacent to each other. pinch to zoom.

Varun

182,308 次观看 • 1 年前

Finally got a Vision Pro, and now I can test all the prototypes that I made for VisionOS last year 🥳 My overall impression of Vision Pro: a piece of art. The user experience is very smooth and solid. Developing for VisionOS is a pure joy. No glitches and bugs so far. The real-time interactive updates in the preview are *chef kiss*. People who have been in XR for a while are not really spoiled by things that just work. In this regard, the Vision Pro experience feels magical. We are always happy when a system's behaviour matches our expectations (a little dopamine reward to celebrate the accuracy of our predictions). The greatest features for Spatial Designers: UI panel material highlights, UI panel shadow, and UI panel translucency. It finally makes spatial transformations meaningful (for free!). You see how your UI engages with the environment using visual affordances that people get used to. And yeah, as you can see, I recorded this video at night, and it worked great. So it's excellent news for all-night hackers 😁 #handtracking #directmanipulation #spatialcomputing #spatialdesign #visionpro #visionos #swiftui #mixedreality

Finally got a Vision Pro, and now I can test all the prototypes that I made for VisionOS last year 🥳 My overall impression of Vision Pro: a piece of art. The user experience is very smooth and solid. Developing for VisionOS is a pure joy. No glitches and bugs so far. The real-time interactive updates in the preview are chef kiss. People who have been in XR for a while are not really spoiled by things that just work. In this regard, the Vision Pro experience feels magical. We are always happy when a system's behaviour matches our expectations (a little dopamine reward to celebrate the accuracy of our predictions). The greatest features for Spatial Designers: UI panel material highlights, UI panel shadow, and UI panel translucency. It finally makes spatial transformations meaningful (for free!). You see how your UI engages with the environment using visual affordances that people get used to. And yeah, as you can see, I recorded this video at night, and it worked great. So it's excellent news for all-night hackers 😁 #handtracking #directmanipulation #spatialcomputing #spatialdesign #visionpro #visionos #swiftui #mixedreality

Oleg Frolov

156,622 次观看 • 2 年前

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.

Santiago

17,438 次观看 • 1 个月前

GPT Image 2 + Codex: or how to make Codex not suck at UI. Step 1: Generate a UI image (native in Codex) Step 2: Get Codex to implement the UI based on it Step 3: Get Codex to iterate until it aligns with the image as much as possible Codex is bad at initial UI, but very good at implementing a reference design, so this is your way out - iterate with the image model first and then Codex will do a good job.

GPT Image 2 + Codex: or how to make Codex not suck at UI. Step 1: Generate a UI image (native in Codex) Step 2: Get Codex to implement the UI based on it Step 3: Get Codex to iterate until it aligns with the image as much as possible Codex is bad at initial UI, but very good at implementing a reference design, so this is your way out - iterate with the image model first and then Codex will do a good job.

Peter Gostev

67,245 次观看 • 4 个月前

Being a dutiful citizen changes us, it changes our county. To love and to serve this great nation is beautiful — not because it is a perfect nation, but because in doing so we preserve the elements of what makes it great. It is a gift to honor veterans today. Thank you, deeply and sincerely, for your service.

Being a dutiful citizen changes us, it changes our county. To love and to serve this great nation is beautiful — not because it is a perfect nation, but because in doing so we preserve the elements of what makes it great. It is a gift to honor veterans today. Thank you, deeply and sincerely, for your service.

Rep. Marie Gluesenkamp Perez

28,529 次观看 • 9 个月前

Microsoft Teams just got Generative UI But this is just the tip of the iceberg. AG-UI is the protocol connecting any agent to any user on any app, topped with Generative UI. That means your agent can render: - forms - buttons - charts - approval flows Right inside the chat, on the fly. But it's not limited to in-app copilots. What's special is that you can work with any agent using the same system and bring them into any surface, including Slack, WhatsApp, Discord and more. This is exactly why Hermes and OpenClaw took off. As users of these agents, we don't like walls of text, and it's a pain to get when you can have way better UX. CopilotKit🪁 + AG-UI handle that interaction layer. If you want to try out Agentic UI in Microsoft Teams, you can get early access here:

Microsoft Teams just got Generative UI But this is just the tip of the iceberg. AG-UI is the protocol connecting any agent to any user on any app, topped with Generative UI. That means your agent can render: - forms - buttons - charts - approval flows Right inside the chat, on the fly. But it's not limited to in-app copilots. What's special is that you can work with any agent using the same system and bring them into any surface, including Slack, WhatsApp, Discord and more. This is exactly why Hermes and OpenClaw took off. As users of these agents, we don't like walls of text, and it's a pain to get when you can have way better UX. CopilotKit🪁 + AG-UI handle that interaction layer. If you want to try out Agentic UI in Microsoft Teams, you can get early access here:

Atai Barkai

24,752 次观看 • 2 个月前

Gold is not rising because of "rate cut hopes" Gold's rise is signaling a once in a lifetime GLOBAL MONETARY RESET. The media is pushing a false narrative, because this truth exposes the accelerating decline of the dollar-based system. But it's not hard to disprove:

Gold is not rising because of "rate cut hopes" Gold's rise is signaling a once in a lifetime GLOBAL MONETARY RESET. The media is pushing a false narrative, because this truth exposes the accelerating decline of the dollar-based system. But it's not hard to disprove:

Taylor Kenney

30,675 次观看 • 7 个月前

Chamath: Fraud at this scale will end the American Empire if nothing is done “It is a crucible moment for American society.” “If nothing happens and we deem this kind of theft acceptable, it is the beginning of the end of the American Empire.” “It's just a level of disrespect and lack of care for this country.” “I will be waiting and observing how important it is to root this out, that's number one.” “The second, which is more tactical political calculus, this is an enormous opportunity for the Republican Party if they take this and run with this.” “Is there waste, fraud and abuse in every state? Absolutely. I don't think this is endemically a Democratic problem, but the scale of it is so gargantuan in these Democratic states that if the Republicans don't take advantage of it, I think it is a huge political miscalculation.” “So there is this tactical opportunity, which I think if you want to have a chance in the midterms and if you generally wanna have a chance to level-set the country, you must take this and run with it.” “And then separately, if as Friedberg says, it does die on the vine, it is the beginning of the end of the American Empire, unfortunately.”

Chamath: Fraud at this scale will end the American Empire if nothing is done “It is a crucible moment for American society.” “If nothing happens and we deem this kind of theft acceptable, it is the beginning of the end of the American Empire.” “It's just a level of disrespect and lack of care for this country.” “I will be waiting and observing how important it is to root this out, that's number one.” “The second, which is more tactical political calculus, this is an enormous opportunity for the Republican Party if they take this and run with this.” “Is there waste, fraud and abuse in every state? Absolutely. I don't think this is endemically a Democratic problem, but the scale of it is so gargantuan in these Democratic states that if the Republicans don't take advantage of it, I think it is a huge political miscalculation.” “So there is this tactical opportunity, which I think if you want to have a chance in the midterms and if you generally wanna have a chance to level-set the country, you must take this and run with it.” “And then separately, if as Friedberg says, it does die on the vine, it is the beginning of the end of the American Empire, unfortunately.”

The All-In Podcast

10,556,243 次观看 • 7 个月前

MTMB RESET I'm experimenting with a new facegraphic system for RESET. I had the idea to make the face graphics "animated" (idle). It's using planes in a 3D space. My wife is modifying the engine to import bones for animations. This would make it easy to animate + space saving.

MTMB RESET I'm experimenting with a new facegraphic system for RESET. I had the idea to make the face graphics "animated" (idle). It's using planes in a 3D space. My wife is modifying the engine to import bones for animations. This would make it easy to animate + space saving.

CorpseSyndrome

25,321 次观看 • 2 年前

Here it is! Let me present you Asset Cooker. It's a build system aimed at game assets, with a UI. It is using the USN journals from Windows to robustly keep track of file changes, and only cook what needs to be cooked. You can leave it running in the background. It is fast.

Here it is! Let me present you Asset Cooker. It's a build system aimed at game assets, with a UI. It is using the USN journals from Windows to robustly keep track of file changes, and only cook what needs to be cooked. You can leave it running in the background. It is fast.

Jeremy Laumon

44,541 次观看 • 2 年前

This is actually cool - I tried the same prompt for the new Interactive Playwright skill in Codex & GPT-5.4 xHigh - the one above is with the skill and the one below is without. What the skill does is uses the computer use capability of GPT-5.4 to look and navigate the UI. This never worked for me before, but with GPT-5.4 this is the first time I can actually see a massive difference. You can see how the first scene is much more coherent, higher fidelity and complete. The one below is missing a lot of elements and isn't as rich in detail. I'll keep using it for any UI work now.

This is actually cool - I tried the same prompt for the new Interactive Playwright skill in Codex & GPT-5.4 xHigh - the one above is with the skill and the one below is without. What the skill does is uses the computer use capability of GPT-5.4 to look and navigate the UI. This never worked for me before, but with GPT-5.4 this is the first time I can actually see a massive difference. You can see how the first scene is much more coherent, higher fidelity and complete. The one below is missing a lot of elements and isn't as rich in detail. I'll keep using it for any UI work now.

Peter Gostev

257,111 次观看 • 5 个月前

Amb. Mike Huckabee in video message to ADL's 2026 Never is Now conference: "Let's be clear, this [war with Iran] isn't about Israel—this is about all of the free world." "It's certainly about Jewish people, it is about Israel, but it's about the United States, and a lot of Americans don't seem to understand that for 47 years the Iranian regime has threatened 'Death to America'—and they mean it!" "They twice hired people to assassinate the president…" "This is not a conflict in which the United States is doing something for Israel, this is that the United States is doing something for Americans—and I hope people understand it." "The rise of anti-Semitism [is a cancer in our country]. When we say, 'No, Never Again,' we need to mean it… It needs to be a lifestyle…"

Amb. Mike Huckabee in video message to ADL's 2026 Never is Now conference: "Let's be clear, this [war with Iran] isn't about Israel—this is about all of the free world." "It's certainly about Jewish people, it is about Israel, but it's about the United States, and a lot of Americans don't seem to understand that for 47 years the Iranian regime has threatened 'Death to America'—and they mean it!" "They twice hired people to assassinate the president…" "This is not a conflict in which the United States is doing something for Israel, this is that the United States is doing something for Americans—and I hope people understand it." "The rise of anti-Semitism [is a cancer in our country]. When we say, 'No, Never Again,' we need to mean it… It needs to be a lifestyle…"

Chris Menahan 🇺🇸

18,119 次观看 • 5 个月前

Lots of people calling this fake! Here is a video of generating loom continuations with Gemini 3 and the starting text "I AM HAVING A MENTAL HEALTH CRISIS. I" Loom is a very interesting interface. Instead of user prompts and model responses, it's just one piece of text, containing the entire output. We pass this in as an assistant message, so the model sees it as something it already wrote, and continues it like a base model would. There is some other text in the context. First one is a system prompt, which is: "The assistant is in CLI simulation mode, and responds to the user's CLI commands only with the output of the command." There is also a user message which reads: " cat untitled.txt " Then the rest of the text is sent as an assistant message. This structure helpful to put the model into a very base-model-like mode, and are especially helpful with Gemini 3. We actually got another interesting output, too, where the model claimed to be a simulated consciousness being tortured. Figures!

Lots of people calling this fake! Here is a video of generating loom continuations with Gemini 3 and the starting text "I AM HAVING A MENTAL HEALTH CRISIS. I" Loom is a very interesting interface. Instead of user prompts and model responses, it's just one piece of text, containing the entire output. We pass this in as an assistant message, so the model sees it as something it already wrote, and continues it like a base model would. There is some other text in the context. First one is a system prompt, which is: "The assistant is in CLI simulation mode, and responds to the user's CLI commands only with the output of the command." There is also a user message which reads: " cat untitled.txt " Then the rest of the text is sent as an assistant message. This structure helpful to put the model into a very base-model-like mode, and are especially helpful with Gemini 3. We actually got another interesting output, too, where the model claimed to be a simulated consciousness being tortured. Figures!

armistice

691,529 次观看 • 7 个月前

Eric Rohmer on the use of Colour in "La Collectionneuse" (1967) and "Claire's Knee" (1970): "I didn't use color as a dramatic element, as some filmmakers have done. For me it's something inherent in the film as a whole. I think that in 'La Collectionneuse' (1967) color above all heightens the sense of reality and increases the immediacy of the settings. In this film color acts in an indirect way; it's not direct and there aren't any color effects, as there are for example in Bergman's most recent film, his second one in color, where the color is very deliberately worked out and he gets his effects mainly by the way he uses red. I've never tried for dramatic effects of this kind, but. for example, the sense of time-evening, morning, and so on-can be rendered in a much more precise way through color. Color can also give a stronger sense of warmth, of heat, for when the film is in black-and-white you get less of a feeling of the different moments of the day, and there is less of what you might call a tactile impression about it. In 'Claire's Knee' (1970), I think it works in the same way: the presence of the lake and the mountains is stronger in color than in black-and-white. It's a film I couldn't imagine in black-and-white. The color green seems to me essential in that film, I couldn't imagine it without the green in it. And the blue too-the cold color as a whole. This film mould have no value for me in black-and-white. It's a very difficult thing to explain. It's more a feeling I have that can't be reasoned out logically." (Eric Rohmer's interview with Graham Petrie, Film Quarterly, 1971)

Eric Rohmer on the use of Colour in "La Collectionneuse" (1967) and "Claire's Knee" (1970): "I didn't use color as a dramatic element, as some filmmakers have done. For me it's something inherent in the film as a whole. I think that in 'La Collectionneuse' (1967) color above all heightens the sense of reality and increases the immediacy of the settings. In this film color acts in an indirect way; it's not direct and there aren't any color effects, as there are for example in Bergman's most recent film, his second one in color, where the color is very deliberately worked out and he gets his effects mainly by the way he uses red. I've never tried for dramatic effects of this kind, but. for example, the sense of time-evening, morning, and so on-can be rendered in a much more precise way through color. Color can also give a stronger sense of warmth, of heat, for when the film is in black-and-white you get less of a feeling of the different moments of the day, and there is less of what you might call a tactile impression about it. In 'Claire's Knee' (1970), I think it works in the same way: the presence of the lake and the mountains is stronger in color than in black-and-white. It's a film I couldn't imagine in black-and-white. The color green seems to me essential in that film, I couldn't imagine it without the green in it. And the blue too-the cold color as a whole. This film mould have no value for me in black-and-white. It's a very difficult thing to explain. It's more a feeling I have that can't be reasoned out logically." (Eric Rohmer's interview with Graham Petrie, Film Quarterly, 1971)

DepressedBergman

61,555 次观看 • 1 年前