Loading video...

Video Failed to Load

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

Introducing the WoW Camera Tools addon 🎥 A small project I’ve been tinkering with that gives you a simple UI for cleaner screenshots, smoother camera control and a bit of fun cinematic flair. Features include: • Rotate, tilt and zoom buttons • Adjustable speed sliders for each movement •... show more

MrGM

82,226 subscribers

136,699 views • 8 months ago •via X (Twitter)

Gaming Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

I built my first macOS app :) Live on the App Store now: Meet NotchShelf. A small utility that lives in the notch and gives you quick access to things you actually need during the day. Built entirely with SwiftUI. What it does: 📂 Quick Shelf: A temporary holding zone for drag-and-drop files. 💻 Screenshot Magnet: Automatically catches screenshots for quick and easy access 📅 Calendar View: Have a quick glance at your events. 📸 One-tap camera: A one-tap camera check before your next meeting. 📝 Quick Note: Jot down important quick notes for thoughts, reminders, or meeting points. and many more advancements and new features coming really soon!

I built my first macOS app :) Live on the App Store now: Meet NotchShelf. A small utility that lives in the notch and gives you quick access to things you actually need during the day. Built entirely with SwiftUI. What it does: 📂 Quick Shelf: A temporary holding zone for drag-and-drop files. 💻 Screenshot Magnet: Automatically catches screenshots for quick and easy access 📅 Calendar View: Have a quick glance at your events. 📸 One-tap camera: A one-tap camera check before your next meeting. 📝 Quick Note: Jot down important quick notes for thoughts, reminders, or meeting points. and many more advancements and new features coming really soon!

OG

32,694 views • 7 months ago

"IMPROVED" STW FIRST PERSON MODE IS SITTING IN PURGATORY It looks quite smoothed out (also quite buggy) STW used to have a 1st person camera before it got removed during v28.10, as Epic used STW's 1st person for UEFN during ch4 & ch5, breaking it, and removing it Gameplay below: Recently I managed to enable the STW first person camera for short range. Unlike Ballistic / UEFN first person camera which changes how weapon held meshes work and the camera position, this version of STW first person heavily relies on camera position alone so that Epic didn't have to redo over 200 different separate items. It is a quicker more "global fix" for how weapons and consumables look like while interacting with the world and the client itself. There's also quite expected bugs for a feature which has been scrapped / sitting in purgatory for nearly 3 years, which has to do with how the player body looks like during camera movements and certain movement animations. I am unsure when this change was implemented to first person, but my guess is around almost 2 years ago once Ballistic released. For a purged feature, I'd say it has a 65% (optimistically 70%) smoothed out rate but there's plenty of bugs and unlikely that this will get released anytime soon so I'm posting it as an update for what state first person currently is in.

"IMPROVED" STW FIRST PERSON MODE IS SITTING IN PURGATORY It looks quite smoothed out (also quite buggy) STW used to have a 1st person camera before it got removed during v28.10, as Epic used STW's 1st person for UEFN during ch4 & ch5, breaking it, and removing it Gameplay below: Recently I managed to enable the STW first person camera for short range. Unlike Ballistic / UEFN first person camera which changes how weapon held meshes work and the camera position, this version of STW first person heavily relies on camera position alone so that Epic didn't have to redo over 200 different separate items. It is a quicker more "global fix" for how weapons and consumables look like while interacting with the world and the client itself. There's also quite expected bugs for a feature which has been scrapped / sitting in purgatory for nearly 3 years, which has to do with how the player body looks like during camera movements and certain movement animations. I am unsure when this change was implemented to first person, but my guess is around almost 2 years ago once Ballistic released. For a purged feature, I'd say it has a 65% (optimistically 70%) smoothed out rate but there's plenty of bugs and unlikely that this will get released anytime soon so I'm posting it as an update for what state first person currently is in.

FossilSouthie

28,573 views • 9 days ago

Happy birthday to me!! 🥳🥳. This has been the most amazing year ever. I’ve been given this opportunity and to see it just continue to grow over the past year has been so amazing. I love each and everyone of you guys that I’ve hit the follow button the like button left the comment or re-shared any of my videos. Before creating content, I was an Ashtanga yoga teacher so I thought for my birthday I share a little bit of my practice with you guys.

Happy birthday to me!! 🥳🥳. This has been the most amazing year ever. I’ve been given this opportunity and to see it just continue to grow over the past year has been so amazing. I love each and everyone of you guys that I’ve hit the follow button the like button left the comment or re-shared any of my videos. Before creating content, I was an Ashtanga yoga teacher so I thought for my birthday I share a little bit of my practice with you guys.

RigoStaRR

21,925 views • 11 months ago

I’ve finally applied #ViduQ3 to a narrative project for SquadBlast . It handles action sequences and explosions with a level of consistency I hadn’t seen before. I achieved camera movements I’ve had in mind for a long time that other models simply wouldn't allow me to implement. The Start-end frame option generates high-quality animations with great control, provided you choose the points wisely and give the model enough time to generate the full movement fluidly. Grok surprised me with its iteration speed. I use it to bring dynamism to establishing shots and dialogue scenes that require quick corrections. If the scene needs movement, it’s my first choice. For more paced scenes or dialogues in wide shots, I prefer Sora 2. It is better suited for maintaining character style in distant shots, where Grok tends to struggle. The music was created in Suno (Industrial Tech-Step). I was looking for a sense of movement through minor-key synth arpeggios and extreme reverb. The "Studio" feature allowed me to precisely control the intro length and the exact point where the kick hits. Finally, a huge thanks to Framer 🇱🇹 for the amazing work on Cartoon Hero and for helping me connect with the professional world, and to OscarAI for his SREFs. I didn't have much time to develop the art style from scratch, so I used one of the SREF he shares. It fit perfectly with the bluish palette and the Otomo-inspired retro sci-fi style I was aiming for. It easily saved me a full day of work. IF ANYONE HAS ANY TECHNICAL KNOW-HOW QUESTIONS RELATED TO ANY SEQUENCE FEEL FREE TO ASK IN THE COMMENTS.

I’ve finally applied #ViduQ3 to a narrative project for SquadBlast . It handles action sequences and explosions with a level of consistency I hadn’t seen before. I achieved camera movements I’ve had in mind for a long time that other models simply wouldn't allow me to implement. The Start-end frame option generates high-quality animations with great control, provided you choose the points wisely and give the model enough time to generate the full movement fluidly. Grok surprised me with its iteration speed. I use it to bring dynamism to establishing shots and dialogue scenes that require quick corrections. If the scene needs movement, it’s my first choice. For more paced scenes or dialogues in wide shots, I prefer Sora 2. It is better suited for maintaining character style in distant shots, where Grok tends to struggle. The music was created in Suno (Industrial Tech-Step). I was looking for a sense of movement through minor-key synth arpeggios and extreme reverb. The "Studio" feature allowed me to precisely control the intro length and the exact point where the kick hits. Finally, a huge thanks to Framer 🇱🇹 for the amazing work on Cartoon Hero and for helping me connect with the professional world, and to OscarAI for his SREFs. I didn't have much time to develop the art style from scratch, so I used one of the SREF he shares. It fit perfectly with the bluish palette and the Otomo-inspired retro sci-fi style I was aiming for. It easily saved me a full day of work. IF ANYONE HAS ANY TECHNICAL KNOW-HOW QUESTIONS RELATED TO ANY SEQUENCE FEEL FREE TO ASK IN THE COMMENTS.

VoxelPlot

17,171 views • 6 months ago

I recreated Meta’s new AI Glasses on my Quest, and the complete source code is available! 👓 Hey everyone! I’ve received a lot of feedback and messages about my latest project, where I used the Quest to recreate the features shown during Meta’s keynote. To answer your questions I decided to create a cool video to explain how I built it but also, share the full source code on Patreon 👇 Watch the making-of: Download the source code: This project includes: ✨ A UI navigable with microgestures 🤏 A pinch & twist hand-tracking input system 🎧 An audio player with volume control via pinch & twist 📸 A camera that zooms with pinch & twist 🖼️ A carousel to browse captured pictures 🧠 And a contextual AI that reacts to what you’re looking at Hope you guys will like it and that it will help you on your own project!! 😊

I recreated Meta’s new AI Glasses on my Quest, and the complete source code is available! 👓 Hey everyone! I’ve received a lot of feedback and messages about my latest project, where I used the Quest to recreate the features shown during Meta’s keynote. To answer your questions I decided to create a cool video to explain how I built it but also, share the full source code on Patreon 👇 Watch the making-of: Download the source code: This project includes: ✨ A UI navigable with microgestures 🤏 A pinch & twist hand-tracking input system 🎧 An audio player with volume control via pinch & twist 📸 A camera that zooms with pinch & twist 🖼️ A carousel to browse captured pictures 🧠 And a contextual AI that reacts to what you’re looking at Hope you guys will like it and that it will help you on your own project!! 😊

Quentin Valembois

15,977 views • 10 months ago

Seedance 2 is out globally on Freepik! 🎸 And now you got to learn how to prompt for it. So I went ahead and made a Spaces workflow for you - link below. And here's a prompt for you to kick off: [STYLE] Ultra-high detail Pixar-quality cinematic animation, 8K, soft global illumination, individual hair and fur strands, realistic fabric simulation, shallow depth of field, warm cozy lighting [FORMAT] 16:9, cinematic multi-shot scene, slow tension build [SCENE] Cozy bedroom at night with strong 80s personality, colorful retro posters on walls, desk with glowing computer, warm lamp. [CHARACTERS] A young man with short dense curly blonde hair forming soft rounded clumps, pale skin, slightly tired blue eyes, wearing a black hoodie A golden retriever with thick light golden fur and expressive eyes. [CAMERA SYSTEM] Smooth cinematic camera, slow push-ins, medium and close shots, no jitter. A scene showing the guy coding. The dog wakes up from some noise. the guy asks what's up. the dog walk to across the room to a closed closet door. noise coming from inside. the guy walks up and gets ready to open the door and calms the dog.

Seedance 2 is out globally on Freepik! 🎸 And now you got to learn how to prompt for it. So I went ahead and made a Spaces workflow for you - link below. And here's a prompt for you to kick off: [STYLE] Ultra-high detail Pixar-quality cinematic animation, 8K, soft global illumination, individual hair and fur strands, realistic fabric simulation, shallow depth of field, warm cozy lighting [FORMAT] 16:9, cinematic multi-shot scene, slow tension build [SCENE] Cozy bedroom at night with strong 80s personality, colorful retro posters on walls, desk with glowing computer, warm lamp. [CHARACTERS] A young man with short dense curly blonde hair forming soft rounded clumps, pale skin, slightly tired blue eyes, wearing a black hoodie A golden retriever with thick light golden fur and expressive eyes. [CAMERA SYSTEM] Smooth cinematic camera, slow push-ins, medium and close shots, no jitter. A scene showing the guy coding. The dog wakes up from some noise. the guy asks what's up. the dog walk to across the room to a closed closet door. noise coming from inside. the guy walks up and gets ready to open the door and calms the dog.

Martin LeBlanc

150,479 views • 4 months ago

🦊 Hi everyone it’s Yeonjun! Today is finally the day I, having gone through the period as a trainee, officially become an artist as Yeonjun from TXT~ 🦊 It’s such a happy and meaningful day for me, I’ve been waiting for this moment for a really long time I started training and dancing when I was in my third year of middle school and since then I’ve been growing my dream of becoming a singer. I’ve just been running towards it and before I knew it, 5 years had passed ! And today, that dream finally came true. It’s a moment I’ve longed for so desperately, one I’ve really been waiting for 🦊 Earlier, while filming, I kept thinking back as I watched myself on camera, it made me remember all the times I trained, pushed myself, went through evaluations with the members, worked hard and the effort I put into improving.. all of it just flashed through my mind at once The memories all passed through my mind like frames in a film and in the middle of it, I felt a strong swell of emotions in my heart and in the end, I couldn’t hold it in and it just burst out It was such an emotional and happy day for me 🦊 The tears I’ve shed up until now were a mix of desperation and the desire to achieve my dream but today after such a long time, I finally shed tears of joy. It feels like such a memorable day for me, one I’ll remember for the rest of my life It’s been such a meaningful day and I hope I can keep seeing our fans for a long time I’ve really missed everyone so much, but now, thinking that we’ll be able to see each other often for a long time makes me so excited and happy 🦊 And I’m also really grateful, you’ve waited for us for so long and I hope we can repay you with good songs and performances Thank you, thank you so much!

🦊 Hi everyone it’s Yeonjun! Today is finally the day I, having gone through the period as a trainee, officially become an artist as Yeonjun from TXT~ 🦊 It’s such a happy and meaningful day for me, I’ve been waiting for this moment for a really long time I started training and dancing when I was in my third year of middle school and since then I’ve been growing my dream of becoming a singer. I’ve just been running towards it and before I knew it, 5 years had passed ! And today, that dream finally came true. It’s a moment I’ve longed for so desperately, one I’ve really been waiting for 🦊 Earlier, while filming, I kept thinking back as I watched myself on camera, it made me remember all the times I trained, pushed myself, went through evaluations with the members, worked hard and the effort I put into improving.. all of it just flashed through my mind at once The memories all passed through my mind like frames in a film and in the middle of it, I felt a strong swell of emotions in my heart and in the end, I couldn’t hold it in and it just burst out It was such an emotional and happy day for me 🦊 The tears I’ve shed up until now were a mix of desperation and the desire to achieve my dream but today after such a long time, I finally shed tears of joy. It feels like such a memorable day for me, one I’ll remember for the rest of my life It’s been such a meaningful day and I hope I can keep seeing our fans for a long time I’ve really missed everyone so much, but now, thinking that we’ll be able to see each other often for a long time makes me so excited and happy 🦊 And I’m also really grateful, you’ve waited for us for so long and I hope we can repay you with good songs and performances Thank you, thank you so much!

Sara

59,854 views • 7 months ago

Hi. The last 2 weeks I’ve been building an iOS watch only wallet for signing $KAS transactions offline using an M5Stack CoreS3 running KasSigner software. Below I demonstrate building a kaspa tx locally, signing it offline, and then broadcasting it to the network. I am still building it and have not had the code audited yet so this should be considered only a proof of concept. The $KAS community has very few options for good wallets so I decided to build one that has everything I could ever want with a simple, sharp UI, privacy, and UTXO control as the most basic foundation, and not a “future roadmap update” pushed out by a company that has 100,000 other tokens they have to dedicate time and resources to. I also plan to build covenants support at some point, but for now I want to have a really good app for signing kaspa txs offline. Also if anyone wants to offer me tips, support, or guidance my DMs are open. I’m also doing this for free in my spare time so if anyone is interested in donating you can at brt25.kas or kaspa:qqpzpn5e7enn2ylfdxvlwtm3829gn6j9z9dnnmcsw5arkgnurktty6ulgzkfk Hope you guys like it and I will be releasing it on GitHub as soon as I clean up the code.

Hi. The last 2 weeks I’ve been building an iOS watch only wallet for signing $KAS transactions offline using an M5Stack CoreS3 running KasSigner software. Below I demonstrate building a kaspa tx locally, signing it offline, and then broadcasting it to the network. I am still building it and have not had the code audited yet so this should be considered only a proof of concept. The $KAS community has very few options for good wallets so I decided to build one that has everything I could ever want with a simple, sharp UI, privacy, and UTXO control as the most basic foundation, and not a “future roadmap update” pushed out by a company that has 100,000 other tokens they have to dedicate time and resources to. I also plan to build covenants support at some point, but for now I want to have a really good app for signing kaspa txs offline. Also if anyone wants to offer me tips, support, or guidance my DMs are open. I’m also doing this for free in my spare time so if anyone is interested in donating you can at brt25.kas or kaspa:qqpzpn5e7enn2ylfdxvlwtm3829gn6j9z9dnnmcsw5arkgnurktty6ulgzkfk Hope you guys like it and I will be releasing it on GitHub as soon as I clean up the code.

₿RT 𐤊 🐈📈

22,185 views • 14 days ago

Today I vibe-coded a small but incredibly useful macOS Electron app using Cursor + GPT-5.5. I use my Mac with a Samsung monitor that has a built-in webcam. Every time I used the camera, I noticed annoying light flickering. I always assumed it was my lighting. It turns out the culprit was the anti-flicker setting. The webcam was set to 60 Hz by default, while India's power frequency is 50 Hz. That mismatch causes visible flickering under indoor lighting. Samsung doesn't provide any way to change this on the monitor, and macOS doesn't have a built-in control for it either. So I asked Cursor to build a simple camera control app that lets me change the webcam's hardware settings, including the anti-flicker mode, along with zoom, brightness, contrast, and more. About 30 minutes and a few rounds of refinement later, I had a fully working Electron app. A tiny app, but it solved something that had been annoying me for months.

Today I vibe-coded a small but incredibly useful macOS Electron app using Cursor + GPT-5.5. I use my Mac with a Samsung monitor that has a built-in webcam. Every time I used the camera, I noticed annoying light flickering. I always assumed it was my lighting. It turns out the culprit was the anti-flicker setting. The webcam was set to 60 Hz by default, while India's power frequency is 50 Hz. That mismatch causes visible flickering under indoor lighting. Samsung doesn't provide any way to change this on the monitor, and macOS doesn't have a built-in control for it either. So I asked Cursor to build a simple camera control app that lets me change the webcam's hardware settings, including the anti-flicker mode, along with zoom, brightness, contrast, and more. About 30 minutes and a few rounds of refinement later, I had a fully working Electron app. A tiny app, but it solved something that had been annoying me for months.

AshutoshShrivastava

76,985 views • 1 month ago

Something straight out of science fiction is happening right now with OpenClaw🦞, and if you haven't used it, it's nearly a peek into the future. OpenClaw/Moltbot is a personal agent that's always on, working for you. These agents are so autonomous, they are even running their social network: moltbook This is a genuine paradigm shift. Extremely useful and honestly, so much fun to just fidget with. When I was playing with it, I realized the setup and potential security concerns could be intimidating for many. So we made it safe and easy for anyone. Introducing MoltBot on Emergent: 2 hours of setup is now 2 minutes. Everyone can participate in the future. Enjoy! Steps to start below ↓ P.S. This is an experiment, please share feedback and we'll improve as fast as we can.

Something straight out of science fiction is happening right now with OpenClaw🦞, and if you haven't used it, it's nearly a peek into the future. OpenClaw/Moltbot is a personal agent that's always on, working for you. These agents are so autonomous, they are even running their social network: moltbook This is a genuine paradigm shift. Extremely useful and honestly, so much fun to just fidget with. When I was playing with it, I realized the setup and potential security concerns could be intimidating for many. So we made it safe and easy for anyone. Introducing MoltBot on Emergent: 2 hours of setup is now 2 minutes. Everyone can participate in the future. Enjoy! Steps to start below ↓ P.S. This is an experiment, please share feedback and we'll improve as fast as we can.

Mukund Jha

1,053,471 views • 6 months ago

Pop Muzik, by M (1979). This is quite an influential pop video and an unusual one. Director Brian Grant only had a budget of £2000, a single camera and one day for shooting in a tiny studio. He therefore decided to edit 'in the can' - filming and editing in the video camera at the same time. Each shot ends exactly on the beat to simplify the storyboard. Scenes are recorded with in-camera effects and blank spaces are left on the videotape so it can be rewound to add in more shots once the studio props have been moved. Perfect timing is essential and Grant had to be happy with each take before moving on to the next set up. The sparse, slightly robotic style became a bit of a New Wave staple and the fast shoot time was very cost efficiency for what could be an expensive process. Grant went on to direct videos for Queen, Duran Duran and Talk Talk among many others, but the innovative guerilla style of Pop Muzic still stands up.

Pop Muzik, by M (1979). This is quite an influential pop video and an unusual one. Director Brian Grant only had a budget of £2000, a single camera and one day for shooting in a tiny studio. He therefore decided to edit 'in the can' - filming and editing in the video camera at the same time. Each shot ends exactly on the beat to simplify the storyboard. Scenes are recorded with in-camera effects and blank spaces are left on the videotape so it can be rewound to add in more shots once the studio props have been moved. Perfect timing is essential and Grant had to be happy with each take before moving on to the next set up. The sparse, slightly robotic style became a bit of a New Wave staple and the fast shoot time was very cost efficiency for what could be an expensive process. Grant went on to direct videos for Queen, Duran Duran and Talk Talk among many others, but the innovative guerilla style of Pop Muzic still stands up.

Pulp Librarian

71,133 views • 10 months ago

It's such an exciting time to be an artist on the internet. We now have the technology to build out our worlds, in spaces we own, it is truly the age of ideas. I've built a new home for my projects here, and in advance of my next major release with Transient Labs on June 16th, I want to share what I've made with you all, and open a dialogue about how we can use these tools as artists to enhance the experience of making and sharing our art. This is an overview of davekrugman dot com (link in thread), specifically about new sites for Drip Drop and DRIVE, and to that end, I'll give a work from each project to someone who reshares this post. If you are an artist who is curious on how to build a site for yourself, I would be happy to help, I'm an open book, ask me in the comments below. There are so many tools to use- I mostly used Claude / Anthropic- and now we can literally speak our ideas into reality , the possibilities feel truly infinite, if you have curiosity, patience, and a bit of time to explore a new frontier. For too long, artists have had to build on the rented space of social platforms, and now it feels like we can really create sovereign spaces that we own and make ours with our unique vision. Feel free to skim and skip around the video, and I'd be stoked if you visited the site and saw it for yourself. Thanks for lookin!

It's such an exciting time to be an artist on the internet. We now have the technology to build out our worlds, in spaces we own, it is truly the age of ideas. I've built a new home for my projects here, and in advance of my next major release with Transient Labs on June 16th, I want to share what I've made with you all, and open a dialogue about how we can use these tools as artists to enhance the experience of making and sharing our art. This is an overview of davekrugman dot com (link in thread), specifically about new sites for Drip Drop and DRIVE, and to that end, I'll give a work from each project to someone who reshares this post. If you are an artist who is curious on how to build a site for yourself, I would be happy to help, I'm an open book, ask me in the comments below. There are so many tools to use- I mostly used Claude / Anthropic- and now we can literally speak our ideas into reality , the possibilities feel truly infinite, if you have curiosity, patience, and a bit of time to explore a new frontier. For too long, artists have had to build on the rented space of social platforms, and now it feels like we can really create sovereign spaces that we own and make ours with our unique vision. Feel free to skim and skip around the video, and I'd be stoked if you visited the site and saw it for yourself. Thanks for lookin!

Dave

20,828 views • 2 months ago

Christopher Nolan convinced IMAX engineers to completely redesign their cameras just so he could film The Odyssey. "I called my friends at IMAX and I said, 'If ever we're going to make a film entirely in IMAX, this is The Odyssey. So, can you find a way to alleviate the limiting factor?'" "The limiting factor being the cameras are extremely loud." "We've never been able to capture dramatic scenes with an IMAX camera." "What they did is they came up with a way of blimping the camera." "Essentially a high-tech box that you put the camera into and it silences it." "It let us, for the first time ever, get the quiet scenes... and therefore be able to do the whole film."

Christopher Nolan convinced IMAX engineers to completely redesign their cameras just so he could film The Odyssey. "I called my friends at IMAX and I said, 'If ever we're going to make a film entirely in IMAX, this is The Odyssey. So, can you find a way to alleviate the limiting factor?'" "The limiting factor being the cameras are extremely loud." "We've never been able to capture dramatic scenes with an IMAX camera." "What they did is they came up with a way of blimping the camera." "Essentially a high-tech box that you put the camera into and it silences it." "It let us, for the first time ever, get the quiet scenes... and therefore be able to do the whole film."

Nichole

805,940 views • 21 days ago

I turned AI agent orchestration into a full fledged game. To start this launch, I’m also hosting a tournament with a growing prize pool (starting at $3k) for the first 24 hours. Two players face off a team of AI agents, armed with strategy prompts - utilizing memory, tool-calling, and inter-agent communication to win. Each agent has a battle memory - they learn and synergize with the playstyle of their commander to produce the best results. I’ve been working on this for the past 2 months, so please check it out, my dms are open for feedback :D Documentation: Project Twitter: aiarena Website:

I turned AI agent orchestration into a full fledged game. To start this launch, I’m also hosting a tournament with a growing prize pool (starting at $3k) for the first 24 hours. Two players face off a team of AI agents, armed with strategy prompts - utilizing memory, tool-calling, and inter-agent communication to win. Each agent has a battle memory - they learn and synergize with the playstyle of their commander to produce the best results. I’ve been working on this for the past 2 months, so please check it out, my dms are open for feedback :D Documentation: Project Twitter: aiarena Website:

𝕱𝖔𝖗𝕷𝖔𝖔𝖕

10,867 views • 4 months ago

I wanted to share a quick demo of what we've been working on with our ai agent cloud. This enables fast deployment of agents that have access to a suite of tools, and was designed with agent interoperability in mind. This demo shows how you can go from nothing to an AI twitter agent in a couple minutes. This is what we are using internally to manage deployments, so we will consistently upgrading its capabilities. The next goals are to enable simple TEE deployments for agents, and focus on building out feature for agent interoperability to simplify agent to agent collaboration.

I wanted to share a quick demo of what we've been working on with our ai agent cloud. This enables fast deployment of agents that have access to a suite of tools, and was designed with agent interoperability in mind. This demo shows how you can go from nothing to an AI twitter agent in a couple minutes. This is what we are using internally to manage deployments, so we will consistently upgrading its capabilities. The next goals are to enable simple TEE deployments for agents, and focus on building out feature for agent interoperability to simplify agent to agent collaboration.

Johnny

27,176 views • 1 year ago

haha, i used OpenAI operator build, deploy, and open source a tool on github using Replit ⠕ agent. took about 30 min, here's an ~8 min supercut video thoughts: - while working with replit agent, it actually deployed the app, tested it, and described the error back to replit agent for me - operator asked me a few more Qs than i wanted, but it was mostly for safety (eg filling forms) so i guess okay with it - it had trouble with a few things around UI like knowing it needs to scroll a page to see the rest of it, and it needed pointers to find the git feature in replit - once it found the git feature it didn't need my assistance to create a repo and open source after having the agent write a readme while a bit slower, this was even more automated than replit agent (especially testing features and working through errors) - which is impressive would be nice to have: push notifications for when it needs my attention, and voice mode capabilities

haha, i used OpenAI operator build, deploy, and open source a tool on github using Replit ⠕ agent. took about 30 min, here's an ~8 min supercut video thoughts: - while working with replit agent, it actually deployed the app, tested it, and described the error back to replit agent for me - operator asked me a few more Qs than i wanted, but it was mostly for safety (eg filling forms) so i guess okay with it - it had trouble with a few things around UI like knowing it needs to scroll a page to see the rest of it, and it needed pointers to find the git feature in replit - once it found the git feature it didn't need my assistance to create a repo and open source after having the agent write a readme while a bit slower, this was even more automated than replit agent (especially testing features and working through errors) - which is impressive would be nice to have: push notifications for when it needs my attention, and voice mode capabilities

Yohei

211,889 views • 1 year ago

This is BLITZ 🏍️ starring myself. I've tested a workflow that combines two of the best AI image editing models right now, Nano Banana and Seedream 4. Using these together feels like a superpower. Seedream 4 for instance generates much more dynamic camera angles BUT Nano Banana does a better job with overall consistency, so utilizing both is super beneficial. I wanted to create a sequence where I'm riding a Cyberbike with an electric booster that overclocks the motor to deliver short, high-risk bursts of extreme speed. The location is a white sand desert. I decided to also test Hailuo AI (MiniMax) start and end frame feature which in my opinion is one of the best since it understands so much about context and camera movement. Start and ends frames let you have much better control over camera movement but where Hailuo truly excels is that it understands speed and camera shake which are essential for any fast paced action sequences. The music was generated with Suno 4.5+ and some additional sound effects like the bike and wind in the desert were sourced from Artlist. Edited with Capcut. There's some more tips and tricks in the thread 👍👍

This is BLITZ 🏍️ starring myself. I've tested a workflow that combines two of the best AI image editing models right now, Nano Banana and Seedream 4. Using these together feels like a superpower. Seedream 4 for instance generates much more dynamic camera angles BUT Nano Banana does a better job with overall consistency, so utilizing both is super beneficial. I wanted to create a sequence where I'm riding a Cyberbike with an electric booster that overclocks the motor to deliver short, high-risk bursts of extreme speed. The location is a white sand desert. I decided to also test Hailuo AI (MiniMax) start and end frame feature which in my opinion is one of the best since it understands so much about context and camera movement. Start and ends frames let you have much better control over camera movement but where Hailuo truly excels is that it understands speed and camera shake which are essential for any fast paced action sequences. The music was generated with Suno 4.5+ and some additional sound effects like the bike and wind in the desert were sourced from Artlist. Edited with Capcut. There's some more tips and tricks in the thread 👍👍

Travis Davids

60,599 views • 11 months ago

I built this zoom UI entirely in Cursor I still mainly use Claude for everything. Sometimes, I switch to o1, but Agent has been game-changing for me, mainly because it's able to figure out a lot of things by itself, like which files to include, what errors to fix and it scales well with the complexity of bigger projects. So 6 months solo into this project (with breaks and while creating courses), I must say that building a video editor from scratch is humbling. The hardest parts are really hard (like exporting, multi-video editing, storage) and the shiny things are mostly easy. AI does a lot of things well, but you absolutely need to be persistent, approach from multiple angles and combine with your intuition and taste. Still, without AI, this project would have been just a dream. And no matter what you want to design or code, or what tools you use, it'll only be meaningful if you put a lot of thought and execution into it.

I built this zoom UI entirely in Cursor I still mainly use Claude for everything. Sometimes, I switch to o1, but Agent has been game-changing for me, mainly because it's able to figure out a lot of things by itself, like which files to include, what errors to fix and it scales well with the complexity of bigger projects. So 6 months solo into this project (with breaks and while creating courses), I must say that building a video editor from scratch is humbling. The hardest parts are really hard (like exporting, multi-video editing, storage) and the shiny things are mostly easy. AI does a lot of things well, but you absolutely need to be persistent, approach from multiple angles and combine with your intuition and taste. Still, without AI, this project would have been just a dream. And no matter what you want to design or code, or what tools you use, it'll only be meaningful if you put a lot of thought and execution into it.

Meng To

41,337 views • 1 year ago