Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

The tool can generate an experimental, non-standard face tracking blendshape called "HaiXT_EyeClosedInverse_Smile". 😴😊 Tweak your animator blend trees (or ProtoFlux in Resonite) so that this shape plays when EyeClosed and MouthSmile are simultaneously running 😄

Haï~

13,683 subscribers

21,159 görüntüleme • 2 yıl önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

3 Yorum

Phasedragon (She/Her) profil fotoğrafı

Phasedragon (She/Her)2 yıl önce

Yes, I did this on my avatar! I also added a shader decal blush on smile, it's really cute😊 now I'm sad that I don't use mouth tracking anymore because it's too bulky

Livb@VRC profil fotoğrafı

Livb@VRC2 yıl önce

is this still using jerry's ft prefab or does it need a different one?

Haï~ profil fotoğrafı

Haï~2 yıl önce

At the moment I'm using the same face tracking animators from Jerry to keep it intact, and I've created a separate layer just to control that additional blendshape

Benzer Videolar

Most backend engineers are used to thinking that their job ends once they provide the API endpoints. But the real question is how well do those endpoints perform when a large number of users hit them repeatedly at the same time? And more importantly, how do you test that during the development phase? In the video above, I explain how engineers can properly test whether their endpoints can handle scale and repeated requests from multiple users simultaneously, using a tool called Apache JMeter. The video walks through everything—from installation to running the tool and finally testing your API. For this demo, I used a local service running on my laptop. Do well to watch, like, retweet, and bookmark so others can learn from it too.

Most backend engineers are used to thinking that their job ends once they provide the API endpoints. But the real question is how well do those endpoints perform when a large number of users hit them repeatedly at the same time? And more importantly, how do you test that during the development phase? In the video above, I explain how engineers can properly test whether their endpoints can handle scale and repeated requests from multiple users simultaneously, using a tool called Apache JMeter. The video walks through everything—from installation to running the tool and finally testing your API. For this demo, I used a local service running on my laptop. Do well to watch, like, retweet, and bookmark so others can learn from it too.

Akintola Steve

10,921 görüntüleme • 7 ay önce

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

forloop

226,544 görüntüleme • 7 ay önce

Grok Imagine can now generate amazing custom music directly for your videos... and it's incredibly easy to use 🎵 Here's how to add music: 1. Generate your video in Grok Imagine 2. Click the music icon at the top 3. Select “+ Add music” 4. Describe the music you want....mood, tempo, instruments, vocals or no vocals, or simply write your own prompt 5. Click Generate 6. Preview your generated music 7. Select the section that fits your video 8. Click Apply And the best part is that your generated music is automatically saved to your library, so you can reuse it in future videos too Video generation and custom soundtracks in the same workflow Grok Imagine is now an incredibly powerful tool for creators

Grok Imagine can now generate amazing custom music directly for your videos... and it's incredibly easy to use 🎵 Here's how to add music: 1. Generate your video in Grok Imagine 2. Click the music icon at the top 3. Select “+ Add music” 4. Describe the music you want....mood, tempo, instruments, vocals or no vocals, or simply write your own prompt 5. Click Generate 6. Preview your generated music 7. Select the section that fits your video 8. Click Apply And the best part is that your generated music is automatically saved to your library, so you can reuse it in future videos too Video generation and custom soundtracks in the same workflow Grok Imagine is now an incredibly powerful tool for creators

X Freeze

337,731 görüntüleme • 1 gün önce

A HUMAN INVENTED A TOOL THAT CAN BUILD A MILLION-DOLLAR COMPANY - AND IT'S FREE Vannevar Bush described this idea back in 1945 - a machine that expands the human brain to infinity, stores everything you know and connects every idea to every other one automatically. For 80 years nobody could build it. Now it's a free app on your laptop. One properly built Obsidian vault replaces an operations director, an analyst, a content strategist and a project manager simultaneously - running 24 hours a day with no days off, no salary and no Slack messages asking for clarification. The people who figured this out first are already running $15,000-$20,000/month businesses completely alone, no team, no office, no investors. The limits of this tool are the limits of your thinking. And judging by what the best users are doing with it - there are no limits.

A HUMAN INVENTED A TOOL THAT CAN BUILD A MILLION-DOLLAR COMPANY - AND IT'S FREE Vannevar Bush described this idea back in 1945 - a machine that expands the human brain to infinity, stores everything you know and connects every idea to every other one automatically. For 80 years nobody could build it. Now it's a free app on your laptop. One properly built Obsidian vault replaces an operations director, an analyst, a content strategist and a project manager simultaneously - running 24 hours a day with no days off, no salary and no Slack messages asking for clarification. The people who figured this out first are already running $15,000-$20,000/month businesses completely alone, no team, no office, no investors. The limits of this tool are the limits of your thinking. And judging by what the best users are doing with it - there are no limits.

Noisy

307,918 görüntüleme • 5 ay önce

Here are some tips for those who want to practice face acting: ➡️U motion: Move your head in a "U" Shape so it's never stuck in the same place. This will help your movements look more interesting. ➡️Key points: When practicing with your model, learn to get to a "Key point." This is when you can automatically get to an expression without using toggles. I use surprised and angry expressions a lot, so I know exactly how to move my face to achieve that look, mainly for clips or comedic effect. I practiced enough so I know what it will look like on the model. ➡️Head tilts: If you struggle with face acting, a simple head tilt will go a long way. Overall, the movement and face acting of your model does matter. It can help it look more interesting, but also, it's okay if you can't face acting all the time. Using just key animations when you're gaming will work perfectly. Example: You died in a game, and you go to the key point of surprise. You know, making this face will make your model look shocked, so you will do a dramatic eye open and mouth agape to achieve this, to reflect onto your model. Lastly. The way your model moves is usually 30% rigging artist,20% tracking (webcam/iPhone), and 50% you. Your rigging artist can give you the tools, but only you can make your models' results reflect your emotions. As always, DO YOUR PARAMETERS AND SETTINGS IN VTUBE STUDIO. It will not be perfect to your face and camera settings unless you adjust the model, (This is an old video I did on parameters) Holy Yapfest.

Here are some tips for those who want to practice face acting: ➡️U motion: Move your head in a "U" Shape so it's never stuck in the same place. This will help your movements look more interesting. ➡️Key points: When practicing with your model, learn to get to a "Key point." This is when you can automatically get to an expression without using toggles. I use surprised and angry expressions a lot, so I know exactly how to move my face to achieve that look, mainly for clips or comedic effect. I practiced enough so I know what it will look like on the model. ➡️Head tilts: If you struggle with face acting, a simple head tilt will go a long way. Overall, the movement and face acting of your model does matter. It can help it look more interesting, but also, it's okay if you can't face acting all the time. Using just key animations when you're gaming will work perfectly. Example: You died in a game, and you go to the key point of surprise. You know, making this face will make your model look shocked, so you will do a dramatic eye open and mouth agape to achieve this, to reflect onto your model. Lastly. The way your model moves is usually 30% rigging artist,20% tracking (webcam/iPhone), and 50% you. Your rigging artist can give you the tools, but only you can make your models' results reflect your emotions. As always, DO YOUR PARAMETERS AND SETTINGS IN VTUBE STUDIO. It will not be perfect to your face and camera settings unless you adjust the model, (This is an old video I did on parameters) Holy Yapfest.

♥️Cutiepierin | L2D RIG ARTIST

94,422 görüntüleme • 11 ay önce

Analyze sites with new tools in Google Earth. Every project starts with the same question: is this the right site? Now you can answer it in Google Earth, before resources are committed or field work begins. • Detect change: See exactly where and when a site changed over time with a saveable heatmap. • Terrain analysis tools: Evaluate elevation contours, slope, aspect, and cut and fill from your desk or the field, with point and click tools. These tools are available on all Google Earth plans. Standard allows you to generate one layer with a tool each month. Professional plans include expanded access and capabilities when you need more tools, a larger site, or both. Learn more:

Analyze sites with new tools in Google Earth. Every project starts with the same question: is this the right site? Now you can answer it in Google Earth, before resources are committed or field work begins. • Detect change: See exactly where and when a site changed over time with a saveable heatmap. • Terrain analysis tools: Evaluate elevation contours, slope, aspect, and cut and fill from your desk or the field, with point and click tools. These tools are available on all Google Earth plans. Standard allows you to generate one layer with a tool each month. Professional plans include expanded access and capabilities when you need more tools, a larger site, or both. Learn more:

Google Earth

27,151 görüntüleme • 22 gün önce

If you do not teach your child what is beautiful, the world will teach them what to admire. That choice will shape more than taste. It will shape desire, standards, and the kind of person they become. The article in the link below argues that beauty is one of the most neglected forces in parenting, because it quietly forms character long before a child can explain it. The takeaway is clear: when parents fill a child’s life with ritual, books, sacred spaces, strong language, and music, they give them an inner standard, so children are less likely to mistake vanity for beauty, stimulation for meaning, or popularity for worth.

If you do not teach your child what is beautiful, the world will teach them what to admire. That choice will shape more than taste. It will shape desire, standards, and the kind of person they become. The article in the link below argues that beauty is one of the most neglected forces in parenting, because it quietly forms character long before a child can explain it. The takeaway is clear: when parents fill a child’s life with ritual, books, sacred spaces, strong language, and music, they give them an inner standard, so children are less likely to mistake vanity for beauty, stimulation for meaning, or popularity for worth.

Culture Explorer

23,657 görüntüleme • 6 ay önce

New AI research from Meta – CoTracker3 Simpler and Better Point Tracking by Pseudo-Labelling Real Videos. More details ➡️ Demo on Hugging Face ➡️ Building on our previous work on CoTracker, this new model demonstrates impressive tracking results where points can be tracked for a long time even when they're occluded or leave the field of view. CoTracker3 achieves state-of-the-art, outperforming all recent point tracking approaches on standard benchmarks — often by a substantial margin. We've released the research paper, code and a demo on Hugging Face — along with models available under an A-NC license to support further research in this space.

New AI research from Meta – CoTracker3 Simpler and Better Point Tracking by Pseudo-Labelling Real Videos. More details ➡️ Demo on Hugging Face ➡️ Building on our previous work on CoTracker, this new model demonstrates impressive tracking results where points can be tracked for a long time even when they're occluded or leave the field of view. CoTracker3 achieves state-of-the-art, outperforming all recent point tracking approaches on standard benchmarks — often by a substantial margin. We've released the research paper, code and a demo on Hugging Face — along with models available under an A-NC license to support further research in this space.

AI at Meta

219,050 görüntüleme • 2 yıl önce

Over the past couple of years, you’ve heard us reference “agents” and “agentic capabilities,” nebulous concepts that are designed to help you with coding, booking trips, and other complex multi-step tasks. But, what actually IS an agent? We think of AI agents as systems that combine the intelligence of advanced AI models with access to tools so they can take actions on your behalf, under your control. Whether it’s a coding agent or our recently unveiled experimental tool Gemini Agent in the Google Gemini, these are systems that will meet you where you are, in the products that you love, to help take the tedious tasks you want off your plate.

Over the past couple of years, you’ve heard us reference “agents” and “agentic capabilities,” nebulous concepts that are designed to help you with coding, booking trips, and other complex multi-step tasks. But, what actually IS an agent? We think of AI agents as systems that combine the intelligence of advanced AI models with access to tools so they can take actions on your behalf, under your control. Whether it’s a coding agent or our recently unveiled experimental tool Gemini Agent in the Google Gemini, these are systems that will meet you where you are, in the products that you love, to help take the tedious tasks you want off your plate.

Google AI

120,897 görüntüleme • 10 ay önce

THIS IS F**KING INSANE FACELESS AI KIDS VIDEOS ARE BECOMING A SERIOUS CONTENT BUSINESS. grab a notebook and watch this one to the end. you don’t need a studio, animation team, or expensive equipment. a phone, laptop, or iPad is enough to start experimenting. here’s the workflow: → open ChatGPT and describe your character → generate a clean reference image → bring it into an AI video tool → animate the character’s movements and expressions → write a short 30-second story → generate a warm kids-style voiceover → combine the audio and visuals → publish on a dedicated faceless channel no camera. no animator. no complicated production setup. one person can build an entire library of short-form kids content while keeping the production almost entirely digital. and once you find a format that children actually watch and replay, you can keep producing variations without rebuilding the workflow every time. the real advantage isn’t making one cartoon. it’s building a repeatable system that can produce hundreds. bookmark this.

THIS IS F**KING INSANE FACELESS AI KIDS VIDEOS ARE BECOMING A SERIOUS CONTENT BUSINESS. grab a notebook and watch this one to the end. you don’t need a studio, animation team, or expensive equipment. a phone, laptop, or iPad is enough to start experimenting. here’s the workflow: → open ChatGPT and describe your character → generate a clean reference image → bring it into an AI video tool → animate the character’s movements and expressions → write a short 30-second story → generate a warm kids-style voiceover → combine the audio and visuals → publish on a dedicated faceless channel no camera. no animator. no complicated production setup. one person can build an entire library of short-form kids content while keeping the production almost entirely digital. and once you find a format that children actually watch and replay, you can keep producing variations without rebuilding the workflow every time. the real advantage isn’t making one cartoon. it’s building a repeatable system that can produce hundreds. bookmark this.

S 🫧

23,276 görüntüleme • 1 ay önce

*serim showing off his muscles* 🐺 taeyang should’ve grabbed them 🐺 they’re so.. kinda.. so.. “Are you into that kind of stuff? Is that your type? Later we can-“ ☀️ it’s just that there’s no one in our group like this 🐺 our team doesn’t really have anyone who’s particularly athletic or is in exceptionally good shape 🐺 i was kinda surprised, (serim’s biceps) was the size of your (taeyang’s) face

Sensitive content

serim showing off his muscles 🐺 taeyang should’ve grabbed them 🐺 they’re so.. kinda.. so.. “Are you into that kind of stuff? Is that your type? Later we can-“ ☀️ it’s just that there’s no one in our group like this 🐺 our team doesn’t really have anyone who’s particularly athletic or is in exceptionally good shape 🐺 i was kinda surprised, (serim’s biceps) was the size of your (taeyang’s) face

haebin

213,380 görüntüleme • 5 ay önce

WOW 🚨 TikTok just introduced a new feature that will generate realistic AI video of users TikTok and other services are capturing your biometric data and your voice and can now use that to generate videos of you saying things and doing things you haven’t done in real life, they will just take creative liberties to “extend your clips” if you choose it I added an example of what this looks like into the video and some more details But just to be clear, it absolutely uses your own face and body. The tool analyzes the end of your clip such a your pose, lighting, clothing, setting, facial features and generates new footage that continues “you” moving or acting in a similar style This is extremely dangerous, just imagine this being used for politics, like extending Donald Trump saying something he didn’t say Big Tech and the media would never do that….

WOW 🚨 TikTok just introduced a new feature that will generate realistic AI video of users TikTok and other services are capturing your biometric data and your voice and can now use that to generate videos of you saying things and doing things you haven’t done in real life, they will just take creative liberties to “extend your clips” if you choose it I added an example of what this looks like into the video and some more details But just to be clear, it absolutely uses your own face and body. The tool analyzes the end of your clip such a your pose, lighting, clothing, setting, facial features and generates new footage that continues “you” moving or acting in a similar style This is extremely dangerous, just imagine this being used for politics, like extending Donald Trump saying something he didn’t say Big Tech and the media would never do that….

Wall Street Apes

20,035 görüntüleme • 4 ay önce

HYDE: “This is you. This is your sister, your wife, your daughter, but this right here is you. This is their reaction when you are killed. This is the joy they feel when your sister is raped, when your children are castrated, brainwashed to hate you. This is their ecstasy when the floor of the subway car is awash in your blood. This is you. Make no mistake. That is a symbol. That is you. But this won't last long. They can't help themselves because they're so ugly and so low that the only joy they can experience, the only good that they can envision, is to take something beautiful or innocent down to their level. And when they can't do it, the next best thing is blood.”

Sensitive content

HYDE: “This is you. This is your sister, your wife, your daughter, but this right here is you. This is their reaction when you are killed. This is the joy they feel when your sister is raped, when your children are castrated, brainwashed to hate you. This is their ecstasy when the floor of the subway car is awash in your blood. This is you. Make no mistake. That is a symbol. That is you. But this won't last long. They can't help themselves because they're so ugly and so low that the only joy they can experience, the only good that they can envision, is to take something beautiful or innocent down to their level. And when they can't do it, the next best thing is blood.”

Grace Chong, MBI

392,442 görüntüleme • 1 yıl önce

Codex has become a real game engine... If you take the time to make it become one. You can do EVERYTHING in it. And I think I've cracked the perfect custom UX? I'd like to show you how I use it. See video below 4 steps: - Create a custom tool you need, like one to generate new buildings that matches you game art direction - Ask Codex to open this tool in a worktree (important) - Attach the browser view of your tool in the Thread - Use pinned thread to have easy access to the tool And there you go: you have what I call a "codex-augmented" tool, which it's incredibly powerful because - the tool will speed up your development immensely AND also: - you can improve the tool as you use it with codex For example, let's say I want to add a new button to my 3D building gen tool so I can generate a thumbnail of the 3D building. - I click on "Building Lab" - I prompt Codex "add a button to generate thumbnails" - I have my new button - I can use the tool right away in the pinned Thread You can then use the /yeet skill to commit, push and create a PR with the changes you made to your tool. I have tools for everything - To manage my tasks in Linear - To do content / social media / steam marketing - To localize the game in 9 languages - To manage sounds, musics and voice lines - To generate and fine tune buildings - To create and animate procedural zombies - To tweak environnement/decor and map design - To manage my analytics - To simulate late game perf I'll be honest it's incredibly powerful and easy!

Codex has become a real game engine... If you take the time to make it become one. You can do EVERYTHING in it. And I think I've cracked the perfect custom UX? I'd like to show you how I use it. See video below 4 steps: - Create a custom tool you need, like one to generate new buildings that matches you game art direction - Ask Codex to open this tool in a worktree (important) - Attach the browser view of your tool in the Thread - Use pinned thread to have easy access to the tool And there you go: you have what I call a "codex-augmented" tool, which it's incredibly powerful because - the tool will speed up your development immensely AND also: - you can improve the tool as you use it with codex For example, let's say I want to add a new button to my 3D building gen tool so I can generate a thumbnail of the 3D building. - I click on "Building Lab" - I prompt Codex "add a button to generate thumbnails" - I have my new button - I can use the tool right away in the pinned Thread You can then use the /yeet skill to commit, push and create a PR with the changes you made to your tool. I have tools for everything - To manage my tasks in Linear - To do content / social media / steam marketing - To localize the game in 9 languages - To manage sounds, musics and voice lines - To generate and fine tune buildings - To create and animate procedural zombies - To tweak environnement/decor and map design - To manage my analytics - To simulate late game perf I'll be honest it's incredibly powerful and easy!

Nicolas Zullo

80,166 görüntüleme • 1 ay önce

🚨End of Vehicle Privacy Your car is no longer your car. New vehicles come loaded with cameras pointed at your face, always-on microphones, and tracking tech that logs everywhere you go. People are pushing back hard—they want their vehicles to stay private sanctuaries, not rolling surveillance devices feeding data straight to governments and corporations. Traditional search and seizure protections are being erased. Warrants? Probable cause? Soon irrelevant when you’ve already “consented” by driving a modern car. This is the highway to technocracy—total tracking, total control, the death of privacy. Are you going to accept a camera in your face every time you drive? Or is this the line we draw?

🚨End of Vehicle Privacy Your car is no longer your car. New vehicles come loaded with cameras pointed at your face, always-on microphones, and tracking tech that logs everywhere you go. People are pushing back hard—they want their vehicles to stay private sanctuaries, not rolling surveillance devices feeding data straight to governments and corporations. Traditional search and seizure protections are being erased. Warrants? Probable cause? Soon irrelevant when you’ve already “consented” by driving a modern car. This is the highway to technocracy—total tracking, total control, the death of privacy. Are you going to accept a camera in your face every time you drive? Or is this the line we draw?

Tom Renz

32,135 görüntüleme • 5 ay önce

Building apps that actually make money is hard So I built a platform that validates app ideas for you Instead of spending months building an app that flops.. now you can validate your app ideas within a few days Just enter your app idea and this tool does the rest for you: → analyses your target market → generates the ads → creates an entire fake sales funnel to assess REAL purchase intent… to find out whether you should actually build the thing.. or try something else its called prelauncher and its available now

Building apps that actually make money is hard So I built a platform that validates app ideas for you Instead of spending months building an app that flops.. now you can validate your app ideas within a few days Just enter your app idea and this tool does the rest for you: → analyses your target market → generates the ads → creates an entire fake sales funnel to assess REAL purchase intent… to find out whether you should actually build the thing.. or try something else its called prelauncher and its available now

Adam Lyttle

100,688 görüntüleme • 4 ay önce

Karpathy’s Agentic Engineering finally has proper DevTools! When an agent stops working, the model is only one possible cause. The problem could be a failed tool, a lost connection, an interface update that never appeared, or something earlier in the conversation. CopilotKit🪁 has rebuilt its open-source Inspector around this problem. It sits inside the application and watches the full interaction between the user, the interface, and the agent. When something fails, the Inspector button turns red, names the failure, and opens the spot where it happened. But even a much harder problem is reproducing that failure. This is because agents do not always follow the same path twice. Running the same prompt again may trigger another tool, produce another response, or start with a different application state. Inspector handles this through saved Threads and an isolated Agent Playground. A developer can open the conversation where the problem occurred, choose "Try from here," and copy everything up to that point into the Playground. The original conversation remains unchanged while another response or tool path is tested. Threads can open inside the live application, while assistant messages can jump back to their matching context in Inspector. Everything runs underneath AG-UI, the protocol that carries messages, tool activity, state changes, and other events between the agent and the interface. Those interactions can also feed CopilotKit Intelligence so that when the same issue or useful behavior appears repeatedly, it can become an evidence-backed Insight and a proposed SKILL(.)md file. Developers can review, edit, and approve the improvement before the agent inherits it. The tool also helps developers find a problem, recreate its surrounding context, test another path, and turn repeated lessons into agent improvements. It is open source and included with CopilotKit development builds. Intelligence setup starts with one prompt. Here are the docs: I am testing this extensively and will cover this in more detail soon with a hands-on demo.

Karpathy’s Agentic Engineering finally has proper DevTools! When an agent stops working, the model is only one possible cause. The problem could be a failed tool, a lost connection, an interface update that never appeared, or something earlier in the conversation. CopilotKit🪁 has rebuilt its open-source Inspector around this problem. It sits inside the application and watches the full interaction between the user, the interface, and the agent. When something fails, the Inspector button turns red, names the failure, and opens the spot where it happened. But even a much harder problem is reproducing that failure. This is because agents do not always follow the same path twice. Running the same prompt again may trigger another tool, produce another response, or start with a different application state. Inspector handles this through saved Threads and an isolated Agent Playground. A developer can open the conversation where the problem occurred, choose "Try from here," and copy everything up to that point into the Playground. The original conversation remains unchanged while another response or tool path is tested. Threads can open inside the live application, while assistant messages can jump back to their matching context in Inspector. Everything runs underneath AG-UI, the protocol that carries messages, tool activity, state changes, and other events between the agent and the interface. Those interactions can also feed CopilotKit Intelligence so that when the same issue or useful behavior appears repeatedly, it can become an evidence-backed Insight and a proposed SKILL(.)md file. Developers can review, edit, and approve the improvement before the agent inherits it. The tool also helps developers find a problem, recreate its surrounding context, test another path, and turn repeated lessons into agent improvements. It is open source and included with CopilotKit development builds. Intelligence setup starts with one prompt. Here are the docs: I am testing this extensively and will cover this in more detail soon with a hands-on demo.

Akshay 🚀

12,206 görüntüleme • 1 ay önce

Porsche 911 Turbo, 930 or the Widowmaker. You instantly know this car when you're older. Whale tail spoiler. Wide rear arches. 930's 3.3L turbo flat-six or the rarer 3.0 version that came earlier. This is the shape people picture when they think “classic 911 Turbo”. Aggressive, simple and instantly recognisable. The sound of the flatsix during that time, that sound is so raw, and you can even hear the turbo whistle in the other clip. An icon before any sort of social media, not overhyped today.

Porsche 911 Turbo, 930 or the Widowmaker. You instantly know this car when you're older. Whale tail spoiler. Wide rear arches. 930's 3.3L turbo flat-six or the rarer 3.0 version that came earlier. This is the shape people picture when they think “classic 911 Turbo”. Aggressive, simple and instantly recognisable. The sound of the flatsix during that time, that sound is so raw, and you can even hear the turbo whistle in the other clip. An icon before any sort of social media, not overhyped today.

Autowelt

22,923 görüntüleme • 5 ay önce