Video yükleniyor...

Video Yüklenemedi

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

Ana Sayfaya Dön

I built an entire Gothic basilica with Opus 5.5, and I’ve open-sourced it. ⛪✨ Basilica of Celestial Light is especially close to my heart. I genuinely loved creating this church. Working on it brought me a real sense of peace, and being able to share it with everyone feels... just as meaningful. Everything was created with Opus 5.5, entirely in code. No external assets: no imported 3D models, image textures, or audio files. The architecture, stained glass, landscape, lighting, and soundscape are all generated at runtime with Three.js. You can walk through the nave, visit the crypt, climb the bell tower, explore the gardens, or take the guided tour, all directly in your browser. The project is open source under the MIT license. Explore it, learn from it, change it, fork it, and make something of your own. I’d genuinely love to see what others create from it. Source code: Play it here: I hope you find a little of the peace I felt while creating it.show more

Token Gremlin

9,046 subscribers

13,433 görüntüleme • 1 gün önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

51 Yorum

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

I’d also like to dedicate this project to my dear friend @JesusIsGod. I made it with very limited resources and ended up burning through all of my model limits along the way, but every bit of it was made from the heart. I truly hope the community enjoys it.

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

Another one of my open-source projects that might be useful to you:

Dylan profil fotoğrafı

Dylan1 gün önce

uploading opus 5.5 code to is hilarious

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

😂😂😂😂😂😂😂😂😂😂

Scott profil fotoğrafı

Scott1 gün önce

Beautiful!

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

Thank you so much!

Scott profil fotoğrafı

Scott1 gün önce

Great work!

Pe. Lucas Mariano profil fotoğrafı

Pe. Lucas Mariano1 gün önce

Muito bom. E ainda está com coro e altar Versus Deum com sacrário no centro.

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

Muito obrigado! 😊🤗♥️

yujie profil fotoğrafı

yujie1 gün önce

我觉得你可以做一些你们巴西的特色建筑或者其他特色事物，这样说不定更好玩，更有意思一些。

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

You’re right, I’ll do that soon. Thank you.

Sachin profil fotoğrafı

Sachin1 gün önce

Insanely good and fabulous continue the great work

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

Thanks!!! 🤗😊♥️

Firchain AI profil fotoğrafı

Firchain AI1 gün önce

How much did this project cost you?

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

My entire monthly subscription quota (~$200).

The Paddle Post profil fotoğrafı

The Paddle Post1 gün önce

Great work. I particularly love the glossy inlaid flooring patterns and the evening sky

Timurs Jeparskis profil fotoğrafı

Timurs Jeparskis1 gün önce

I wonder how long it would've taken a dev team to build this 5 years ago

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

Probably 1 month? 😂

Bob profil fotoğrafı

Bob1 gün önce

I love this!

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

Thank you so much. 🤗♥️

Joker profil fotoğrafı

Joker1 gün önce

That looks very cool. I wish someone could generate an open-world from the sky world in bioshock infinite

Jurly profil fotoğrafı

Jurly1 gün önce

Congrats on the launch, this is an incredible labor of love 🎉

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

Thank you so much! 😊🤗♥️💯🙏

ButtholeGPT profil fotoğrafı

ButtholeGPT1 gün önce

Thanks bro!

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

You're welcome! 🤗♥️

Deepanshu Sharma profil fotoğrafı

Deepanshu Sharma1 gün önce

this is insanely good, but at the same time i wonder how bad it will look in a one-year timeframe i still feel these are only the early days of AI we can achieve a lot more, and can't "pace the frontier" at all

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

You’re absolutely right. I honestly think Opus 5.5’s current capabilities will feel outdated and “weak” in just two months.

Deepanshu Sharma profil fotoğrafı

Deepanshu Sharma1 gün önce

yes, recent trajectory is a living proof of it

Imaginaerum 🖤 profil fotoğrafı

Imaginaerum 🖤1 gün önce

Beautiful 💙

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

Thanks. ♥️🤗

Erick Sandoval profil fotoğrafı

Erick Sandoval1 gün önce

So cool! Congrats brother!

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

Thank you so much, my friend! 😊

MJ profil fotoğrafı

MJ1 gün önce

Absolutely beautiful and amazing. 🙌

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

Thank you so much!

Sahil Panhotra | Indie Builder profil fotoğrafı

Sahil Panhotra | Indie Builder1 gün önce

yo thats great but why is sound not clear in demo or is it just me ?

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

Probably a bug?

Shez Malik profil fotoğrafı

Shez Malik1 gün önce

it rebuilds itself every time u open it

Winter profil fotoğrafı

Winter1 gün önce

Its visual understanding is crazy good!

Jesus is God ✝︎ profil fotoğrafı

Jesus is God ✝︎1 gün önce

This is one of the coolest things I’ve ever seen @TokenGremlin well done!!! 👏😎🥹

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

Thank you so much, my friend. 😊

Rudi Bakken profil fotoğrafı

Rudi Bakken1 gün önce

It felt so peacful 🤩 Well done 👊🔥

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

Thank you so much! 🤗♥️

Neta Art profil fotoğrafı

Neta Art1 gün önce

The level of detail in this basilica is beautiful!

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

Thank you so much! 🤗♥️

Mitansh profil fotoğrafı

Mitansh1 gün önce

a full gothic basilica open-sourced from opus is impressivebasilica of celestial light sounds like a labor of love

Token Gremlin profil fotoğrafı

Token Gremlin1 gün önce

Thanks!

Daniel Zambrini profil fotoğrafı

Daniel Zambrini1 gün önce

Did really a great job! On my tests it did amazing as well!

RJ profil fotoğrafı

RJ1 gün önce

How do I prompt something like this? I’d like to build interactive like this to help my students.

Guillem profil fotoğrafı

Guillem1 gün önce

Here is an early render of mine, but it will take ages because I'm modeling an actual building with nearly 800 years of histoy and trying to make everything accurate and traceable to academic research 😅

Guillem profil fotoğrafı

Guillem1 gün önce

I started one when they released Astra but it's a rabbit hole, I chose an actual cathedral and I'm researching all the actual details, real catalogs, PhD thesis, photos, maps, plans, videos, details about the internal structure of the building, about the sculptures, about stained glass, about the graves, and the gravestones... keeping track of all the sources, and the licenses of the photos, and... It's crazy 😅 Also there is the 3D model itself in Blender, and a project in three.js to navigate through it with a browser, and another one to create videos rendering in RunPod, and... It will never be done. Just like real cathedrals 😂

Luckey Faraday profil fotoğrafı

Luckey Faraday1 gün önce

WOW

Benzer Videolar

opus 5.5 is something else.. so many people asked me to open source the 3d water from my last post. a few even wanted to buy it so here it is. my first open source drop code » demo » show me what you make with it

opus 5.5 is something else.. so many people asked me to open source the 3d water from my last post. a few even wanted to buy it so here it is. my first open source drop code » demo » show me what you make with it

Aurelien

224,999 görüntüleme • 2 gün önce

I’ve officially open-sourced SYLVA. 🌲 SYLVA is a fully procedural cinematic forest that runs directly in the browser. Terrain, trees, roots, grass, water, sky, clouds, fog, and weather are generated at runtime using Three.js, WebGL2, and GLSL, without downloaded tree models, textures, HDRIs, or terrain heightmaps. Trees are procedurally grown, terrain is generated mathematically, and the world includes dynamic water, atmosphere, vegetation LODs, rain, lightning, wind, storms, fireflies, birds, and a cinematic camera system. The demo is also interactive. Open the EDITOR to change the environment, visual presets, quality, weather states, wind and storms, move through different times of day, or simply walk around and explore the forest yourself. The project is still actively being developed, and there’s a ridiculous amount left to improve, optimize, and experiment with. But that’s also why I wanted to open it now. SYLVA is MIT-licensed, so you can explore the code, learn from it, modify it, fork it, optimize it, or use it as the foundation for something completely different. Source code: Live demo: Feedback, contributions, experiments, and forks are all welcome. 🌲 (This project is being updated RIGHT NOW.)

I’ve officially open-sourced SYLVA. 🌲 SYLVA is a fully procedural cinematic forest that runs directly in the browser. Terrain, trees, roots, grass, water, sky, clouds, fog, and weather are generated at runtime using Three.js, WebGL2, and GLSL, without downloaded tree models, textures, HDRIs, or terrain heightmaps. Trees are procedurally grown, terrain is generated mathematically, and the world includes dynamic water, atmosphere, vegetation LODs, rain, lightning, wind, storms, fireflies, birds, and a cinematic camera system. The demo is also interactive. Open the EDITOR to change the environment, visual presets, quality, weather states, wind and storms, move through different times of day, or simply walk around and explore the forest yourself. The project is still actively being developed, and there’s a ridiculous amount left to improve, optimize, and experiment with. But that’s also why I wanted to open it now. SYLVA is MIT-licensed, so you can explore the code, learn from it, modify it, fork it, optimize it, or use it as the foundation for something completely different. Source code: Live demo: Feedback, contributions, experiments, and forks are all welcome. 🌲 (This project is being updated RIGHT NOW.)

Token Gremlin

14,608 görüntüleme • 24 gün önce

I’ve officially open-sourced ABYSSAL. 🌊⚡ ABYSSAL is a fully procedural ocean and extreme-weather experience that runs directly in the browser. Waves, volumetric clouds, rain, lightning, hurricanes, waterspouts, rogue waves, and tsunamis are generated in real time using Three.js, WebGL2, and GLSL. The project is still actively being developed, and there’s a lot left to do. Deeper optimization, building the world beneath the ocean’s surface, refining the existing systems, and exploring plenty of ideas I haven’t implemented yet. But that’s also why I wanted to open it now. ABYSSAL is MIT-licensed, so you can explore the code, learn from it, modify it, fork it, and use it as the foundation for your own experiments and projects. Performance note: the demo starts with adaptive resolution enabled and automatically selects a quality tier based on your GPU. If the image looks soft, open the settings panel and raise the quality as far as your device can handle. The experience begins in Cinematic mode, click SANDBOX for full control of the camera, weather, and disasters. Explore the source code: Play it here: Feedback, contributions, experiments, and forks are all welcome.

I’ve officially open-sourced ABYSSAL. 🌊⚡ ABYSSAL is a fully procedural ocean and extreme-weather experience that runs directly in the browser. Waves, volumetric clouds, rain, lightning, hurricanes, waterspouts, rogue waves, and tsunamis are generated in real time using Three.js, WebGL2, and GLSL. The project is still actively being developed, and there’s a lot left to do. Deeper optimization, building the world beneath the ocean’s surface, refining the existing systems, and exploring plenty of ideas I haven’t implemented yet. But that’s also why I wanted to open it now. ABYSSAL is MIT-licensed, so you can explore the code, learn from it, modify it, fork it, and use it as the foundation for your own experiments and projects. Performance note: the demo starts with adaptive resolution enabled and automatically selects a quality tier based on your GPU. If the image looks soft, open the settings panel and raise the quality as far as your device can handle. The experience begins in Cinematic mode, click SANDBOX for full control of the camera, weather, and disasters. Explore the source code: Play it here: Feedback, contributions, experiments, and forks are all welcome.

Token Gremlin

249,646 görüntüleme • 28 gün önce

I'm truly impressed with Opus 5.5. I asked it to visualise Atlantis in ThreeJS for me, and it created a tour around Poseidia, the last surviving island of Atlantis. Sound on 🔊 for full trailer experience. Even this trailer is made by Opus 5.5 as well. I think we’re on the verge of a new type of media: Generative Experiences. The idea is that you can describe a world you have in mind and step into it is pretty incredible. You could explore its cities, meet its inhabitants, discover its stories, and shape what happens next through your own choices. This took Opus 5.5 about two hours to make. But if we extrapolate a year into the future, I can imagine being able to conjure up these kinds of fantastical, immersive experiences within seconds. The possibilities go well beyond gaming. Writers could walk through the worlds they’re building. Children could explore an ancient civilisation and ask questions along the way. Learning could become an experience you actively participate in, with the world responding to what you’re curious about. This is incredibly exciting and I am here for it. You can tour around Poseidia here:

I'm truly impressed with Opus 5.5. I asked it to visualise Atlantis in ThreeJS for me, and it created a tour around Poseidia, the last surviving island of Atlantis. Sound on 🔊 for full trailer experience. Even this trailer is made by Opus 5.5 as well. I think we’re on the verge of a new type of media: Generative Experiences. The idea is that you can describe a world you have in mind and step into it is pretty incredible. You could explore its cities, meet its inhabitants, discover its stories, and shape what happens next through your own choices. This took Opus 5.5 about two hours to make. But if we extrapolate a year into the future, I can imagine being able to conjure up these kinds of fantastical, immersive experiences within seconds. The possibilities go well beyond gaming. Writers could walk through the worlds they’re building. Children could explore an ancient civilisation and ask questions along the way. Learning could become an experience you actively participate in, with the world responding to what you’re curious about. This is incredibly exciting and I am here for it. You can tour around Poseidia here:

Danny Limanseta

45,735 görüntüleme • 1 gün önce

To me, microduck looks like a droid. So I made it sound like one Microduck is open source and hackable. That means you can program it to do whatever you want! I trained a 1.3m parameter LLM to output droid like responses. It is running in the browser The model has learned to respond with an emotion, alongside English like Happy, Excited, Sad Then the emotion is fed into a Rust based synthesizer to generate R2D2 like sounds that are aligned with the emotion --- completely procedurally, no wav files, no copyright violation You can chat with it. You can also customize it, give it a name and set your own colors! All set in a spaceship hangar backdrop with other friendly ducks---simulated with realistic physics and microduck's actual walking and skating policies! All in the browser, with WASM!!! I can put literally the SAME code in the browser, and then compile it into an ARM binary and put it in the actual robot in real life 🤯 If you like this and want to see more of it, please like and share so that my boss puts me in the priority list for the first microduck batch 😎 All open source of course! Microquack! 🦆 Hugging Face Space:

To me, microduck looks like a droid. So I made it sound like one Microduck is open source and hackable. That means you can program it to do whatever you want! I trained a 1.3m parameter LLM to output droid like responses. It is running in the browser The model has learned to respond with an emotion, alongside English like Happy, Excited, Sad Then the emotion is fed into a Rust based synthesizer to generate R2D2 like sounds that are aligned with the emotion --- completely procedurally, no wav files, no copyright violation You can chat with it. You can also customize it, give it a name and set your own colors! All set in a spaceship hangar backdrop with other friendly ducks---simulated with realistic physics and microduck's actual walking and skating policies! All in the browser, with WASM!!! I can put literally the SAME code in the browser, and then compile it into an ARM binary and put it in the actual robot in real life 🤯 If you like this and want to see more of it, please like and share so that my boss puts me in the priority list for the first microduck batch 😎 All open source of course! Microquack! 🦆 Hugging Face Space:

Onur Solmaz

33,500 görüntüleme • 27 gün önce

opus 5.5 extra high "create a new project in my projects folder called "endless-game": an endless, procedurally generated world built with three.js in the browser that i can roam freely and just enjoy. every area should be randomly generated, with surprises everywhere no matter how long i play. it should feel calm, relaxing and genuinely fun, like the cozy, satisfying vibe of a supermarket simulator, but it shouldn't be a supermarket game. i want a really interesting world to walk around in, with entities i can meet and interact with, and really cool graphics. set a clear goal for the project, keep working until you reach it, and play a sound chime when it's done and ready for me to play and test."

opus 5.5 extra high "create a new project in my projects folder called "endless-game": an endless, procedurally generated world built with three.js in the browser that i can roam freely and just enjoy. every area should be randomly generated, with surprises everywhere no matter how long i play. it should feel calm, relaxing and genuinely fun, like the cozy, satisfying vibe of a supermarket simulator, but it shouldn't be a supermarket game. i want a really interesting world to walk around in, with entities i can meet and interact with, and really cool graphics. set a clear goal for the project, keep working until you reach it, and play a sound chime when it's done and ready for me to play and test."

🥔🥔🥔

20,988 görüntüleme • 3 gün önce

I open-sourced my 3d towers building site and the skills I used to create well-textured three.js models. The entire site is 1.38mb gzipped, including all models, sounds and textures. Site: Github repo: Skills: - threejs-towers - threejs-weather - threejs-landscape With an open-source project you get a way better starting point. All you need is to ask what to change, how to improve it, and rebuild it for a different theme. I added Cambodia, Vietnam and Turkey, plus storms and blizzards, and those came out perfectly with one prompt. The foundation is done, so adapting it and pairing it with your taste is what takes it further. Try modern towers, different backgrounds, weather and styles. SimCity, Civilization, Warcraft, C&C, etc. It's really fun.

I open-sourced my 3d towers building site and the skills I used to create well-textured three.js models. The entire site is 1.38mb gzipped, including all models, sounds and textures. Site: Github repo: Skills: - threejs-towers - threejs-weather - threejs-landscape With an open-source project you get a way better starting point. All you need is to ask what to change, how to improve it, and rebuild it for a different theme. I added Cambodia, Vietnam and Turkey, plus storms and blizzards, and those came out perfectly with one prompt. The foundation is done, so adapting it and pairing it with your taste is what takes it further. Try modern towers, different backgrounds, weather and styles. SimCity, Civilization, Warcraft, C&C, etc. It's really fun.

Meng To

55,260 görüntüleme • 1 ay önce

Even if AI can do in minutes what takes me hours or months, I still take pleasure in the craft and making something with my hands. I enjoy it, I love the process and feeling of creating on my own. Just because there’s a faster way to do it doesn’t mean you have to do it that way, especially if it doesn’t resonate with you.

Even if AI can do in minutes what takes me hours or months, I still take pleasure in the craft and making something with my hands. I enjoy it, I love the process and feeling of creating on my own. Just because there’s a faster way to do it doesn’t mean you have to do it that way, especially if it doesn’t resonate with you.

vijay verma

135,862 görüntüleme • 10 ay önce

Avatar Studio is now fully open-source, with the fully permissive MIT license. Fork it, contribute to it, make your own commercial product out of it. Whatever you want! I will be actively following submitted issues and pull requests.

Jag the Hero

26,811 görüntüleme • 2 ay önce

OPUS 5.5 just made an entire animated ad by itself for $0 no image generation. no video generation. no editing completely one-shotted by OPUS 5.5 inside claude code i tested it on RYZE mushroom coffee with a single prompt, and then i just waited what it did on its own: - researched the product, the audience and the angle - wrote the script and built the storyboard - pulled the real product images straight from the web - produced the voiceover and the captions itself - rendered the finished ad, ready to post you don't need a stack of paid AI tools anymore. opus 5.5 handles the whole production end to end RT + reply 'OPUS' and i'll send you the complete workflow (must follow so i can DM)

OPUS 5.5 just made an entire animated ad by itself for $0 no image generation. no video generation. no editing completely one-shotted by OPUS 5.5 inside claude code i tested it on RYZE mushroom coffee with a single prompt, and then i just waited what it did on its own: - researched the product, the audience and the angle - wrote the script and built the storyboard - pulled the real product images straight from the web - produced the voiceover and the captions itself - rendered the finished ad, ready to post you don't need a stack of paid AI tools anymore. opus 5.5 handles the whole production end to end RT + reply 'OPUS' and i'll send you the complete workflow (must follow so i can DM)

Lad

18,641 görüntüleme • 1 gün önce

Fable 5.1 is an absolute beast for game dev. I took my Opus 5 space game and told Fable to "just make it look better". It overhauled everything with a TON of detail, AND made it 2x faster 🤯 Code: Demo: Every pixel you see is made by AI. Fable modeled everything in Blender, generated textures with code, and in a few cases ran image models via CLI. In mere months we'll be vibe-coding AAA graphics at this rate. Just insane. Of course, Fable recorded and edited this comparison video too (with a little help from Opus at the end, because of the Fable outage)

Fable 5.1 is an absolute beast for game dev. I took my Opus 5 space game and told Fable to "just make it look better". It overhauled everything with a TON of detail, AND made it 2x faster 🤯 Code: Demo: Every pixel you see is made by AI. Fable modeled everything in Blender, generated textures with code, and in a few cases ran image models via CLI. In mere months we'll be vibe-coding AAA graphics at this rate. Just insane. Of course, Fable recorded and edited this comparison video too (with a little help from Opus at the end, because of the Fable outage)

Anshu

48,983 görüntüleme • 22 gün önce

$I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)$

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)

Ian Nuttall

195,173 görüntüleme • 1 yıl önce

Astra can create beautiful three.js UIs entirely in code. You don't need an assets library or MCP to create detailed 3D models. These are all code and are easy to customize for your agent. Give Astra a video, URL, or code reference, then ask it to keep comparing the result against the reference and fixing mistakes. Liquid Glass, shaders, motion design, procedural three.js models, and full environments. All from a few prompts. Some prompts I used: "Recreate this in a single HTML file with three.js. Keep comparing it against the reference and fix any differences." "Add Liquid Glass buttons. On hover, animate the lighting around the borders and make the background gradients move slightly with the pointer. Add subtle particles." "Improve the lighting, edges, and modeling. Give the keys more depth and verify the result against the real MacBook." Too many projects I could open-source. Let me know which one should I release.

Astra can create beautiful three.js UIs entirely in code. You don't need an assets library or MCP to create detailed 3D models. These are all code and are easy to customize for your agent. Give Astra a video, URL, or code reference, then ask it to keep comparing the result against the reference and fixing mistakes. Liquid Glass, shaders, motion design, procedural three.js models, and full environments. All from a few prompts. Some prompts I used: "Recreate this in a single HTML file with three.js. Keep comparing it against the reference and fix any differences." "Add Liquid Glass buttons. On hover, animate the lighting around the borders and make the background gradients move slightly with the pointer. Add subtle particles." "Improve the lighting, edges, and modeling. Give the keys more depth and verify the result against the real MacBook." Too many projects I could open-source. Let me know which one should I release.

Meng To

105,156 görüntüleme • 19 gün önce

The End of an Era. 🪒 I wanted change. And for some reason, my mind kept telling me I’d get it by shaving the beard. As much as I loved it and what it added to my identity it grew through some of the darkest moments of my past year. And I couldn’t shake the feeling that it was carrying the weight of that energy with it. So I shaved it. Did it change my life? No. 😂 I miss it. But sometimes your mind needs to do something, anything, to spark a shift. And this was mine. What’s something you’ve done to start a new chapter? I’d love to hear it.

The End of an Era. 🪒 I wanted change. And for some reason, my mind kept telling me I’d get it by shaving the beard. As much as I loved it and what it added to my identity it grew through some of the darkest moments of my past year. And I couldn’t shake the feeling that it was carrying the weight of that energy with it. So I shaved it. Did it change my life? No. 😂 I miss it. But sometimes your mind needs to do something, anything, to spark a shift. And this was mine. What’s something you’ve done to start a new chapter? I’d love to hear it.

FOUSEY

112,000 görüntüleme • 1 yıl önce

Opus 5.5 sculpted every part of this ship in code, including the dragon, sails, and architecture. I can't say it has bad taste anymore. But it still needs steering, so I tried a new way of prompting. Live site: I asked Opus to score every part of the scene: the ship, water, landscapes, buildings, and their individual parts. Then I asked it to keep improving each part until it scored at least 8 out of 10, depending on my token and time budget. The key is to let it work as long as possible. The longer it works, the better it gets, until it reaches a point where I need to course correct. For me, Opus 5.5 reaches a level of detail and realism that no other model does.

Opus 5.5 sculpted every part of this ship in code, including the dragon, sails, and architecture. I can't say it has bad taste anymore. But it still needs steering, so I tried a new way of prompting. Live site: I asked Opus to score every part of the scene: the ship, water, landscapes, buildings, and their individual parts. Then I asked it to keep improving each part until it scored at least 8 out of 10, depending on my token and time budget. The key is to let it work as long as possible. The longer it works, the better it gets, until it reaches a point where I need to course correct. For me, Opus 5.5 reaches a level of detail and realism that no other model does.

Meng To

44,509 görüntüleme • 1 gün önce

I thought it would be good to share my code of life with everyone. What’s the value of knowledge if it cannot be shared? I hope you all learn to trust the process and believe in yourselves.

I thought it would be good to share my code of life with everyone. What’s the value of knowledge if it cannot be shared? I hope you all learn to trust the process and believe in yourselves.

Nana Kwame Bediako

23,628 görüntüleme • 1 yıl önce

Elon exposes OpenAI -- OpenAI execs betrayed the founding mission as soon as there was revenue and profits to be had -- If it started as a for-profit, Elon would own 50% Elon Musk: “There's a mountain of evidence that shows that OpenAI was created as an open source nonprofit.” “That's the exact description in the incorporation documents. They have completely violated that.” “And they tried to change the definition of OpenAI to mean open to everyone instead of open source, even though it always meant open source.” “ I came up with the name. That’s how I know.” “ I mean, essentially, since I came up with the idea for the company, named it, provided the A, B, and C rounds of funding, recruited the critical personnel, and told them everything I know, if that had been a commercial corporation, I'd probably own half the company.” “It was totally at my discretion. I could have done that.” “But I created it as an open source nonprofit for the world.” Chamath: “ Do you think the right thing to do is to take those models and just open source them today?” Elon: “ Yeah, I think that is what it was created to do, so it should.” “Try using any of the recent so-called OpenAI open source models, they don't work.” “They open sourced a broken, non-working version of their models as a fig leaf.” “I mean, do you know anyone who's running OpenAI's open source models? Jason: “No.” Elon: “Exactly.”

Elon exposes OpenAI -- OpenAI execs betrayed the founding mission as soon as there was revenue and profits to be had -- If it started as a for-profit, Elon would own 50% Elon Musk: “There's a mountain of evidence that shows that OpenAI was created as an open source nonprofit.” “That's the exact description in the incorporation documents. They have completely violated that.” “And they tried to change the definition of OpenAI to mean open to everyone instead of open source, even though it always meant open source.” “ I came up with the name. That’s how I know.” “ I mean, essentially, since I came up with the idea for the company, named it, provided the A, B, and C rounds of funding, recruited the critical personnel, and told them everything I know, if that had been a commercial corporation, I'd probably own half the company.” “It was totally at my discretion. I could have done that.” “But I created it as an open source nonprofit for the world.” Chamath: “ Do you think the right thing to do is to take those models and just open source them today?” Elon: “ Yeah, I think that is what it was created to do, so it should.” “Try using any of the recent so-called OpenAI open source models, they don't work.” “They open sourced a broken, non-working version of their models as a fig leaf.” “I mean, do you know anyone who's running OpenAI's open source models? Jason: “No.” Elon: “Exactly.”

The All-In Podcast

387,223 görüntüleme • 10 ay önce

Can't believe in less than 24 hours I created my own game with Claude and Three.js. Running in a browser at 120 FPS. All I had to do was give Claude the repo for Threejs and describe an MMO-like game for it to build from scratch. All the assets and mechanics you see are all from a prompt. As you can see, it is far from done but the progress is insane. Everyone should be using Three.js now without a doubt!

Can't believe in less than 24 hours I created my own game with Claude and Three.js. Running in a browser at 120 FPS. All I had to do was give Claude the repo for Threejs and describe an MMO-like game for it to build from scratch. All the assets and mechanics you see are all from a prompt. As you can see, it is far from done but the progress is insane. Everyone should be using Three.js now without a doubt!

NeilXbt

23,504 görüntüleme • 1 ay önce

So here's my attempt at a one shot in Opus 5 after skepticism. I asked it to make me a game inspired by Elder Scrolls Daggerfall and to create all the assets. This is what it created in Cowork which took roughly 8 hours as it was making sure every single pixel was perfect. There's some hitching but on the whole I'm surprised that this is just from one paragraph of prompting engineered to produce the best results it could. It even built the indoor church lighting and water reflections.

So here's my attempt at a one shot in Opus 5 after skepticism. I asked it to make me a game inspired by Elder Scrolls Daggerfall and to create all the assets. This is what it created in Cowork which took roughly 8 hours as it was making sure every single pixel was perfect. There's some hitching but on the whole I'm surprised that this is just from one paragraph of prompting engineered to produce the best results it could. It even built the indoor church lighting and water reflections.

𝔊𝔯𝔦𝔪𝔣𝔢𝔩

33,655 görüntüleme • 1 ay önce