Loading video...

Video Failed to Load

Go Home

this part was generated AND printed with one prompt using codex + text-to-cad: “Make me a thick Möbius strip, and use computer use to print on my Bambu Labs A1 Mini” went to the gym, came back 1.5 hours later and it was sitting on the build plate

earthtojake's profile picture

Jake Fitzgerald

4,806 subscribers

15,085 views • 22 days ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Codex + 5.5 + computer use built me an iPhone shortcut to make it easy to use GPT Image 2 on any photo in my camera roll. Then it edited this screen recording with ffmpeg to speed it up so I could share it. Great for making quick UI mocks on my phone. And for lulz.
0:18

Codex + 5.5 + computer use built me an iPhone shortcut to make it easy to use GPT Image 2 on any photo in my camera roll. Then it edited this screen recording with ffmpeg to speed it up so I could share it. Great for making quick UI mocks on my phone. And for lulz.

Ilya Abyzov

45,451 views • 1 month ago

Did you know how to remove prints from the Bambu Cool Plate SuperTack? Just use the scraper that came with your printer to gently lift the print and carefully pry it off. If it's stuck too tight, heat the plate to 50°C on the heatbed to help it come off. The surface is soft, so be careful with the scraper to avoid scratches (they won’t affect performance though). Want more tips for this plate? Check here:
0:11

Did you know how to remove prints from the Bambu Cool Plate SuperTack? Just use the scraper that came with your printer to gently lift the print and carefully pry it off. If it's stuck too tight, heat the plate to 50°C on the heatbed to help it come off. The surface is soft, so be careful with the scraper to avoid scratches (they won’t affect performance though). Want more tips for this plate? Check here:

Bambu Lab

17,564 views • 1 year ago

✨Three easy steps for extremely high quality, fast 3D prints ✨ 1. Purchase a Bambu Lab printer, P1S + AMS and A1 + AMS Lite Combos are my favorite ❤️. Use my affiliate link to place an order: 2. Skip the stock print profile, use a Zombie Tuned Bambu Studio profile available on This will ensure the highest possible quality without sacrificing printing time.⏱️ 3. Use Polymaker filament, anywhere from PLA to PETG to ASA! Polymaker has you covered with reliable, beautiful, and strong filaments for your projects.🦚 Use my affiliate link and code "POLYMAKERFIRSTTRY" to save 15%: Follow me for more 3D printing content, advice, and tutorials! Check out all the links on my website:
0:16

✨Three easy steps for extremely high quality, fast 3D prints ✨ 1. Purchase a Bambu Lab printer, P1S + AMS and A1 + AMS Lite Combos are my favorite ❤️. Use my affiliate link to place an order: 2. Skip the stock print profile, use a Zombie Tuned Bambu Studio profile available on This will ensure the highest possible quality without sacrificing printing time.⏱️ 3. Use Polymaker filament, anywhere from PLA to PETG to ASA! Polymaker has you covered with reliable, beautiful, and strong filaments for your projects.🦚 Use my affiliate link and code "POLYMAKERFIRSTTRY" to save 15%: Follow me for more 3D printing content, advice, and tutorials! Check out all the links on my website:

ZombieHedgehog | Hedgehog Makes

11,665 views • 1 year ago

AI-generated Spongebob 🤯 This is the new LTX model, and it's pure text-to-video. Prompt was just "Spongebob and Patrick discuss AI sentience." It nailed the voices + characters on its own...
0:10

AI-generated Spongebob 🤯 This is the new LTX model, and it's pure text-to-video. Prompt was just "Spongebob and Patrick discuss AI sentience." It nailed the voices + characters on its own...

Justine Moore

93,018 views • 7 months ago

I created this from a simple Telegram prompt 🔥 - @clawedbot running on Laravel VPS - using Claude Code - using Eleven Labs and my voice clone - using Remotion to bring it together This was the result after two prompts. (< 10min)
0:17

I created this from a simple Telegram prompt 🔥 - @clawedbot running on Laravel VPS - using Claude Code - using Eleven Labs and my voice clone - using Remotion to bring it together This was the result after two prompts. (< 10min)

Christoph Rumpel 🤠

24,987 views • 4 months ago

DeepAgent - Researched and built a website in one shot! 🤯🤯 I gave it a one-liner prompt to build a website by looking things up on the internet, and it came up with this. All the information is correct, the links work, and it even grabbed a photo. Still in limited preview and part of ChatLLM. We will open it up later in the week.
0:19

DeepAgent - Researched and built a website in one shot! 🤯🤯 I gave it a one-liner prompt to build a website by looking things up on the internet, and it came up with this. All the information is correct, the links work, and it even grabbed a photo. Still in limited preview and part of ChatLLM. We will open it up later in the week.

Bindu Reddy

24,348 views • 1 year ago

prompt engineers don’t want you to know this you don’t need complicated text to make AI videos. Just the elements you want and Higgsfield’s Draw to Video. examples and how to use it in this thread 🧵👇
0:10

prompt engineers don’t want you to know this you don’t need complicated text to make AI videos. Just the elements you want and Higgsfield’s Draw to Video. examples and how to use it in this thread 🧵👇

TechHalla

18,264 views • 10 months ago

so my portfolio is live on it was so much fun to go back to the web (frontend) and build this. I built it using Nextra and Aceternity and deployed it on Vercel. I loved your library Manu Arora, thank you for building it :) #buildinpublic
0:16

so my portfolio is live on it was so much fun to go back to the web (frontend) and build this. I built it using Nextra and Aceternity and deployed it on Vercel. I loved your library Manu Arora, thank you for building it :) #buildinpublic

Sachin Dapkara

13,818 views • 2 years ago

Claude 3 Opus, Sonnet, and Haiku are now available as a base for you to build prompt bots with on Poe! These powerful multimodal models are the best in the world for many use cases and support text and image input. We’re excited to see what you create with them!
0:10

Claude 3 Opus, Sonnet, and Haiku are now available as a base for you to build prompt bots with on Poe! These powerful multimodal models are the best in the world for many use cases and support text and image input. We’re excited to see what you create with them!

Poe

17,040 views • 2 years ago

D5 render. I use to think Lumion was the best on fastest those years until I Started using D5. Every Visualizer should try D5 render and thank me later.
0:18

D5 render. I use to think Lumion was the best on fastest those years until I Started using D5. Every Visualizer should try D5 render and thank me later.

ajisafeolumuyiwa

26,337 views • 8 months ago

Google Nano Banana works with annotations. Create an image and add characters, objects and text prompt annotations. Use this as a reference and ask Nano Banana to follow the instructions. It managed to place everything perfectly into the shot.
0:19

Google Nano Banana works with annotations. Create an image and add characters, objects and text prompt annotations. Use this as a reference and ask Nano Banana to follow the instructions. It managed to place everything perfectly into the shot.

Jerrod Lew

372,468 views • 9 months ago

We tested a lot of design skills in Codex and other AI agents. They fix the old AI slop. But they often create a new one: the “taste skill look.” - Same premium sections. - Same editorial typography. - Same generated-design smell. Open Design does not rely on one taste prompt. It combines skills, systems, critique loops, and local harnesses to make AI pages feel less generated and more designed. This page was generated directly in Open Design.
0:15

We tested a lot of design skills in Codex and other AI agents. They fix the old AI slop. But they often create a new one: the “taste skill look.” - Same premium sections. - Same editorial typography. - Same generated-design smell. Open Design does not rely on one taste prompt. It combines skills, systems, critique loops, and local harnesses to make AI pages feel less generated and more designed. This page was generated directly in Open Design.

Open Design

43,632 views • 12 days ago

I remember working on this shot early in the morning before work, and one day when the rough #animation was complete, I went to open the file and it was corrupted. By some miracle I was able to get it working again, but I think this took me the better part of a week to animate.
0:12

I remember working on this shot early in the morning before work, and one day when the rough #animation was complete, I went to open the file and it was corrupted. By some miracle I was able to get it working again, but I think this took me the better part of a week to animate.

Mike Carlo

10,688 views • 7 months ago

Magic Quill: A Free AI Image Editor That Feels Like Magic This tool is incredibly useful and free to use now! It lets you select parts of an image and edit them with just a text prompt. Mostly I’ve gotten exactly what I needed on the first try! Here’s how to use it:
0:15

Magic Quill: A Free AI Image Editor That Feels Like Magic This tool is incredibly useful and free to use now! It lets you select parts of an image and edit them with just a text prompt. Mostly I’ve gotten exactly what I needed on the first try! Here’s how to use it:

el.cine

186,949 views • 1 year ago

wowwow Holy Shit I let Opus 4.7 pick any art on my computer they'd like to use as a starting frame for an animation, and then prompt gptimage2 for animation frames however they'd like to make a 100 frame animation here was the result note - gptimage2 only made 4 images, each one was a 5x5 grid of frames, so that totals to 100
0:12

wowwow Holy Shit I let Opus 4.7 pick any art on my computer they'd like to use as a starting frame for an animation, and then prompt gptimage2 for animation frames however they'd like to make a 100 frame animation here was the result note - gptimage2 only made 4 images, each one was a 5x5 grid of frames, so that totals to 100

w̸͕͂͂a̷͔̗͐t̴̙͗e̵̬̔̕r̴̰̓̊m̵͙͖̓̽a̵̢̗̓͒r̸̲̽ķ̷͔́͝

12,263 views • 1 month ago

The reveal, height change, motion blur, selection... Was a joy to build and still a joy to use.
0:12

The reveal, height change, motion blur, selection... Was a joy to build and still a joy to use.

Brotzky

102,882 views • 1 year ago

jihoon just came on stage to say his message and was escorted back 🥺 he was limping, but he still went on stage to give assurance to the fans :(
0:17

jihoon just came on stage to say his message and was escorted back 🥺 he was limping, but he still went on stage to give assurance to the fans :(

shan

23,729 views • 4 months ago

Yesterday someone suggested I create a fight between Alucard and Drolta Tzuentes using Kling AI 2.6. I usually work with Text to Video, but in this case I had to use Image to Video. The base image is a fusion of two images created in Niji and combined with GPT Image 1.5. Then I added the right prompt to give the fight speed and dynamism. The result isn’t perfect, but it’s pretty cool.
0:10

Yesterday someone suggested I create a fight between Alucard and Drolta Tzuentes using Kling AI 2.6. I usually work with Text to Video, but in this case I had to use Image to Video. The base image is a fusion of two images created in Niji and combined with GPT Image 1.5. Then I added the right prompt to give the fight speed and dynamism. The result isn’t perfect, but it’s pretty cool.

OscarAI

18,533 views • 5 months ago

I just got Codex to reverse engineer the Control+M speech-to-text mode in the Codex app and build a Mac app that lets you run it anywhere. The demo is me making this tweet right now.
0:16

I just got Codex to reverse engineer the Control+M speech-to-text mode in the Codex app and build a Mac app that lets you run it anywhere. The demo is me making this tweet right now.

Anthony Kroeger

140,283 views • 1 month ago