Loading video...

Video Failed to Load

Go Home

And it works!!!!!!! 😍👌 Made a whole computer room from 1995 with Three.js on the web using Claude Code (on the server) in just a few hours I can connect to the internet and surf the web, play DOOM and mIRC and read the news, all in 3d now...

levelsio's profile picture

@levelsio

886,045 subscribers

458,589 views • 1 year ago •via X (Twitter)

Science & TechnologyGaming
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

✨ Added a CRT curvature distortion to pieter™ now It takes the Em-DOSBox and processes it in WebGL and builds a new with the distortion of a classic CRT screen which had this convex curvature (like an old TV) even though the screen itself was square I had this working on DOSBox on MacOS and on Linux with CRT-Pi shader, but on web it doesn't support shaders so I had to build my own with Claude Code in JS, very easy I remember trying this a year ago and Claude Code fucked it up so bad that I gave up, so I think the models have improved a lot Tomorrow I'll try add some scanlines, it really helps make the simulation more passable (and nostalgic!) 😊👌
2:20

✨ Added a CRT curvature distortion to pieter™ now It takes the Em-DOSBox and processes it in WebGL and builds a new with the distortion of a classic CRT screen which had this convex curvature (like an old TV) even though the screen itself was square I had this working on DOSBox on MacOS and on Linux with CRT-Pi shader, but on web it doesn't support shaders so I had to build my own with Claude Code in JS, very easy I remember trying this a year ago and Claude Code fucked it up so bad that I gave up, so I think the models have improved a lot Tomorrow I'll try add some scanlines, it really helps make the simulation more passable (and nostalgic!) 😊👌

@levelsio

88,256 views • 6 months ago

How I have Claude automate anything I do on my computer just by showing it: I use the free Clips app and hit record to start recording. Then I just do the action - like navigating to Rippling and approving any unapproved time off - and I’ll often just talk out loud as I do it explaining any add’l details like I would when showing a human. The Clips app captures everything on your screen and everything you say, and transforms it into a format Claude can “see and hear”. You'll then get a link that you can easily share with Claude (or humans too). I’ll paste it to Claude and say something like, "automate this for me every day at 8:00 AM." The link has special metadata that agents like Claude can discover. It exposes APIs to see the full transcript with timestamps and grab screenshots of what was on your screen at any of those timestamps. Once it's created the routine, you can go to the Routines tab in Claude Code desktop app. This also works with the CLI, Claude Cowork, Codex etc. You’ll see your new routine there, and you can just hit Run Now to have it start running it. Video attached shows this step by step. The Clips apps is free and open source - I’ll link to it and the source code in the thread.
1:54

How I have Claude automate anything I do on my computer just by showing it: I use the free Clips app and hit record to start recording. Then I just do the action - like navigating to Rippling and approving any unapproved time off - and I’ll often just talk out loud as I do it explaining any add’l details like I would when showing a human. The Clips app captures everything on your screen and everything you say, and transforms it into a format Claude can “see and hear”. You'll then get a link that you can easily share with Claude (or humans too). I’ll paste it to Claude and say something like, "automate this for me every day at 8:00 AM." The link has special metadata that agents like Claude can discover. It exposes APIs to see the full transcript with timestamps and grab screenshots of what was on your screen at any of those timestamps. Once it's created the routine, you can go to the Routines tab in Claude Code desktop app. This also works with the CLI, Claude Cowork, Codex etc. You’ll see your new routine there, and you can just hit Run Now to have it start running it. Video attached shows this step by step. The Clips apps is free and open source - I’ll link to it and the source code in the thread.

Steve (Builder.io)

25,473 views • 1 month ago

🖨️ It took over a year and lots of help from Claude Code but I have now been able to create a real dot matrix printer on the web that prints from Windows 3.11 in your browser: Here's the test page: I couldn't get the LPT1 port to work but COM2 did work (the dial up model already uses COM1), the JS receives the COM2 serial data (just raw print data) and then prints it Next is to make the dot matrix printer better looking (kinda 3d like on pieter dot com) and have the paper also flowing in 3d out of the printer and integrate it on the page My idea was that it might work because we also capture the COM1 data (from the dial up modem) and send it to a Websocket as a dial up connection, so we should be able to capture the COM2 traffic too but I didn't know how, but now I do IT WORKS!! 😊
0:51

🖨️ It took over a year and lots of help from Claude Code but I have now been able to create a real dot matrix printer on the web that prints from Windows 3.11 in your browser: Here's the test page: I couldn't get the LPT1 port to work but COM2 did work (the dial up model already uses COM1), the JS receives the COM2 serial data (just raw print data) and then prints it Next is to make the dot matrix printer better looking (kinda 3d like on pieter dot com) and have the paper also flowing in 3d out of the printer and integrate it on the page My idea was that it might work because we also capture the COM1 data (from the dial up modem) and send it to a Websocket as a dial up connection, so we should be able to capture the COM2 traffic too but I didn't know how, but now I do IT WORKS!! 😊

@levelsio

85,969 views • 2 months ago

From time to time, people ask me how I make models so close to the reference, so here it goes: I work in orthographic view on one screen for modeling, and on the other, I keep a viewport with the camera aligned and the reference in front at low opacity using PureRef or Kuadro
0:56

From time to time, people ask me how I make models so close to the reference, so here it goes: I work in orthographic view on one screen for modeling, and on the other, I keep a viewport with the camera aligned and the reference in front at low opacity using PureRef or Kuadro

Vicente Moscardó Ribes

52,304 views • 1 year ago

Below is a screen recording from March 6, 2024. It is a screen recording of a group text between myself, Jen McCabe, Julie Criselo, and Lisa Criselo. I'm going to post the screen recording for now. I have children to attend to, and a life. But when I have time (possibly this evening) I will return to explain away Kate's lies and the details. For now.. everyone has eyeballs and, as far as I'm aware, knows how to read.
0:33

Below is a screen recording from March 6, 2024. It is a screen recording of a group text between myself, Jen McCabe, Julie Criselo, and Lisa Criselo. I'm going to post the screen recording for now. I have children to attend to, and a life. But when I have time (possibly this evening) I will return to explain away Kate's lies and the details. For now.. everyone has eyeballs and, as far as I'm aware, knows how to read.

Lindsey Gaetani

155,443 views • 6 months ago

Now that i have a full green screen room i thought it was a cool idea to align myself with my avatar in #VRChat and yeah, every move i made in game was shown to players too. (i use the Orion Trackers from SomaticVR) So they see the avatar i use, and the camera see me IRL
0:45

Now that i have a full green screen room i thought it was a cool idea to align myself with my avatar in #VRChat and yeah, every move i made in game was shown to players too. (i use the Orion Trackers from SomaticVR) So they see the avatar i use, and the camera see me IRL

SoundsLikeRonen

45,145 views • 3 months ago

I learned how to use the GPU Profiler, and I was able to optimize the game enough that even I can play it at 100% resolution and around 60fps now! And that's with the screen recorder going too. Turns out there was a render target eating up about 20fps this whole time!
1:18

I learned how to use the GPU Profiler, and I was able to optimize the game enough that even I can play it at 100% resolution and around 60fps now! And that's with the screen recorder going too. Turns out there was a render target eating up about 20fps this whole time!

DRIG

15,283 views • 10 months ago

Casually vibe coded Trevor Noah's latest website "Books" page using Fable 5 😍 I really loved the effects and animations on the website and immediately wanted to see if I could recreate them with AI. Pretty close in just a couple of prompts, isn't it? Everything is built in Three.js with no 3D assets for the books. Claude built the whole thing using pure math and animated it nicely with GSAP. Feels so realistic and close to real book. Pretty fun to see how close you can get to the kind of work agencies charge thousands of dollars for, just by describing what you want :D Live: Code:
0:23

Casually vibe coded Trevor Noah's latest website "Books" page using Fable 5 😍 I really loved the effects and animations on the website and immediately wanted to see if I could recreate them with AI. Pretty close in just a couple of prompts, isn't it? Everything is built in Three.js with no 3D assets for the books. Claude built the whole thing using pure math and animated it nicely with GSAP. Feels so realistic and close to real book. Pretty fun to see how close you can get to the kind of work agencies charge thousands of dollars for, just by describing what you want :D Live: Code:

The Bugged Dev

218,330 views • 14 days ago

lando on how special it is to drive car number one: “i saw it actually earlier on the timing screen and i still find it just unbelievable. it's still a crazy thing to see. now it's really the first time i get to see it on my suit, on the car, on the timing screens and it looks good. so still a surreal feeling, the whole situation of being champion.” ❤️❤️
1:01

lando on how special it is to drive car number one: “i saw it actually earlier on the timing screen and i still find it just unbelievable. it's still a crazy thing to see. now it's really the first time i get to see it on my suit, on the car, on the timing screens and it looks good. so still a surreal feeling, the whole situation of being champion.” ❤️❤️

ray

15,968 views • 6 months ago

Throwback to when i first tried to these animations and I made the whole showroom screen. Animation still wasn't as smooth as now and also I didn't center car properly but when I first made it, I was very proud of my self for getting the look close
0:26

Throwback to when i first tried to these animations and I made the whole showroom screen. Animation still wasn't as smooth as now and also I didn't center car properly but when I first made it, I was very proud of my self for getting the look close

Hacao

19,012 views • 3 months ago

Ever seen a fresh (20x) Claude Max account's 5-hour usage allowance get drained in ~14 minutes? Feast your eyes on my bizarre life now with this screen recording of a recent live work session, something I've gotten at least 100 requests for over the past month. Maybe you can understand now why I need so many accounts and how I can work on so many different projects. You can also see the truth of what I was saying recently about how, once your plan is done and the beads made and polished, it's mostly just machine-tending the swarm that doesn't require much thought. Lots of just telling it to get the next bead and work on it, to review code, to re-read AGENTS dot md after a compaction, etc. And you can see how I use gemini-cli for code review. I give Google a lot of crap for the harness being broken and the capacity overloads, but when it works, it's actually really good for this code review use case. I don't usually let it write new code, though, because I think Opus and 5.2 do a better job. Also, sorry the recording is a bit blurry; I have a 5K resolution monitor and screen recordings usually are hard to watch from it. And btw, this really wasn't that normal of a session for me, it was more frenetic than usual, because I don't want to dox myself or my clients by accident. Hence all the ceaseless terminal tab swirling. I usually do more planning work while this stuff is going on, but I wanted to minimize the chances of leaking important information. That's also why I didn't refresh the Gemini login in the WezTerm window, which killed me, trust me. It's the reason I hate doing these screen recordings in the first place; it kills my productivity. Anyway, hope you liked it. I will also post to YouTube, see reply for link. Thanks for watching.
14:24

Ever seen a fresh (20x) Claude Max account's 5-hour usage allowance get drained in ~14 minutes? Feast your eyes on my bizarre life now with this screen recording of a recent live work session, something I've gotten at least 100 requests for over the past month. Maybe you can understand now why I need so many accounts and how I can work on so many different projects. You can also see the truth of what I was saying recently about how, once your plan is done and the beads made and polished, it's mostly just machine-tending the swarm that doesn't require much thought. Lots of just telling it to get the next bead and work on it, to review code, to re-read AGENTS dot md after a compaction, etc. And you can see how I use gemini-cli for code review. I give Google a lot of crap for the harness being broken and the capacity overloads, but when it works, it's actually really good for this code review use case. I don't usually let it write new code, though, because I think Opus and 5.2 do a better job. Also, sorry the recording is a bit blurry; I have a 5K resolution monitor and screen recordings usually are hard to watch from it. And btw, this really wasn't that normal of a session for me, it was more frenetic than usual, because I don't want to dox myself or my clients by accident. Hence all the ceaseless terminal tab swirling. I usually do more planning work while this stuff is going on, but I wanted to minimize the chances of leaking important information. That's also why I didn't refresh the Gemini login in the WezTerm window, which killed me, trust me. It's the reason I hate doing these screen recordings in the first place; it kills my productivity. Anyway, hope you liked it. I will also post to YouTube, see reply for link. Thanks for watching.

Jeffrey Emanuel

86,071 views • 6 months ago

To achieve it, I used a single Niagara actor to read the screen-space velocity directly from the GBuffer and apply that to a render target by using a Grid2D interface to loop through each screen pixel. The rest is mapping, manipulating and masking that in the material :) #Shaders
0:32

To achieve it, I used a single Niagara actor to read the screen-space velocity directly from the GBuffer and apply that to a render target by using a Grid2D interface to loop through each screen pixel. The rest is mapping, manipulating and masking that in the material :) #Shaders

Pedro Borges

15,227 views • 1 year ago

shoutout to all of the parents in the world that know how to read words on a screen and recognize their children’s faces and voices
0:37

shoutout to all of the parents in the world that know how to read words on a screen and recognize their children’s faces and voices

ꨄ︎ ✧･ﾟ* ★

131,864 views • 8 months ago

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as Marc Köhlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to Peter Steinberger 🦞 who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by Richard Atkinson on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next
1:30

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as Marc Köhlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to Peter Steinberger 🦞 who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by Richard Atkinson on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next

@levelsio

642,483 views • 5 months ago

[Day 21] My vibe coding journey: Initial prompt: "Create a 3D website where, as the user scrolls, an astronaut flies through space, passes through a 4D tunnel to another universe, breaks through a monitor screen, and then returns to a normal web experience." I can't believe it works! I am hooked! Planning and Code: Grok 3. Of course Three.js. Hater is going to hate. Live link in the comment!!
0:22

[Day 21] My vibe coding journey: Initial prompt: "Create a 3D website where, as the user scrolls, an astronaut flies through space, passes through a 4D tunnel to another universe, breaks through a monitor screen, and then returns to a normal web experience." I can't believe it works! I am hooked! Planning and Code: Grok 3. Of course Three.js. Hater is going to hate. Live link in the comment!!

ᴇᴅᴀɴ ᴋᴡᴀɴ

128,079 views • 1 year ago

Okay someone I can't find in the replies anymore suggested nippleJS for the mobile joypads, so I asked Cursor to add that and now it works on mobile :D Shooting I think press center of screen
0:29

Okay someone I can't find in the replies anymore suggested nippleJS for the mobile joypads, so I asked Cursor to add that and now it works on mobile :D Shooting I think press center of screen

@levelsio

602,776 views • 1 year ago

I hope Apple will invent a way to not touch the screen with a keyboard. Maybe they expect us to keep using that packaging paper in between the keyboard and screen? ¯\_(ツ)_/¯
0:36

I hope Apple will invent a way to not touch the screen with a keyboard. Maybe they expect us to keep using that packaging paper in between the keyboard and screen? ¯\_(ツ)_/¯

Aivars Meijers

129,052 views • 2 years ago

We have now fully commissioned the machine after a few hiccups related to an old dying hard drive in the machine PC (it had a 1 gb hard drive!!) could save the machine in the nick of time with the help of a fellow machining junkie who knew how to do it! But the real reason i am writing is that we successfully ran our first 3D program on it and that the program was written entirely using Claude !! I did it myself and it took me a few hours to get it going. The best part of using Claude was that I could ask it to use macros to write the program which meant i could control *all* variables in the program. And it ran like a charm! Rendered on the part a fine finish and a brilliant high to see the part come out better than expected! I set the job myself because I wanted to get a feel for the machine, its ways and how to work with it. It had been nearly 15 years since I had set a job on the machine for a VMC, and it felt good to know the craft has not left my hands and getting them dirty while making parts still makes me happy! Samaachar samaapth :)
0:28

We have now fully commissioned the machine after a few hiccups related to an old dying hard drive in the machine PC (it had a 1 gb hard drive!!) could save the machine in the nick of time with the help of a fellow machining junkie who knew how to do it! But the real reason i am writing is that we successfully ran our first 3D program on it and that the program was written entirely using Claude !! I did it myself and it took me a few hours to get it going. The best part of using Claude was that I could ask it to use macros to write the program which meant i could control *all* variables in the program. And it ran like a charm! Rendered on the part a fine finish and a brilliant high to see the part come out better than expected! I set the job myself because I wanted to get a feel for the machine, its ways and how to work with it. It had been nearly 15 years since I had set a job on the machine for a VMC, and it felt good to know the craft has not left my hands and getting them dirty while making parts still makes me happy! Samaachar samaapth :)

Sanjeev

11,761 views • 5 months ago

I've been building a music player with Next.js for fun. Here's a quick demo of how it works (it's open source!) • Demo: • Code: If you want to learn more about how it's built, here's more details ↓ I'm using Postgres (with Drizzle) to store information about the songs and playlists. Audio and image files are stored in Vercel Blob (object storage), and the URLs are then referenced in the database. For the UI, I'm using shadcn/ui (so Tailwind CSS and Radix). This made it easy to copy/paste in some nice components, like the dropdown menus. I built the entire first version of the UI in v0 and then iterated from there, feeding it my Drizzle schema as a source in the project and having it scaffold some of the boilerplate for me: I added support for keyboard navigation (using arrow keys) or vim motions (j/k to go up/down, and h/l to go between playlists and tracks). Also, space to toggle the now playing song, and / to focus the search input. The search function has a nice utility to highlight the currently searched text on the page in yellow. Then, I was exploring how to pass metadata from my application to macOS or iOS. Turns out there's an API for that – MediaSession. Web apps can share metadata about what media is playing (title, artist, album artwork) and sync play/pause/seek with system media controls. Works across modern browsers — even integrates with iOS dynamic island and shows up on lock screens: I set up my app like a PWA – it has a manifest.json file, so it can be installed to my iOS home screen or added to my dock on macOS. On iOS, it then uses the full screen height `100dvh` (dynamic viewport) and has padding on the bottom for the safe area with the `env()` CSS function. Finally, I was able to use the Vercel AI SDK in a script to clean up the metadata on audio files I downloaded from YouTube. Bonus: I even was able to dogfood the React Compiler, which helped me fix a performance bug! That's all! It's fun to make personal software:
2:03

I've been building a music player with Next.js for fun. Here's a quick demo of how it works (it's open source!) • Demo: • Code: If you want to learn more about how it's built, here's more details ↓ I'm using Postgres (with Drizzle) to store information about the songs and playlists. Audio and image files are stored in Vercel Blob (object storage), and the URLs are then referenced in the database. For the UI, I'm using shadcn/ui (so Tailwind CSS and Radix). This made it easy to copy/paste in some nice components, like the dropdown menus. I built the entire first version of the UI in v0 and then iterated from there, feeding it my Drizzle schema as a source in the project and having it scaffold some of the boilerplate for me: I added support for keyboard navigation (using arrow keys) or vim motions (j/k to go up/down, and h/l to go between playlists and tracks). Also, space to toggle the now playing song, and / to focus the search input. The search function has a nice utility to highlight the currently searched text on the page in yellow. Then, I was exploring how to pass metadata from my application to macOS or iOS. Turns out there's an API for that – MediaSession. Web apps can share metadata about what media is playing (title, artist, album artwork) and sync play/pause/seek with system media controls. Works across modern browsers — even integrates with iOS dynamic island and shows up on lock screens: I set up my app like a PWA – it has a manifest.json file, so it can be installed to my iOS home screen or added to my dock on macOS. On iOS, it then uses the full screen height `100dvh` (dynamic viewport) and has padding on the bottom for the safe area with the `env()` CSS function. Finally, I was able to use the Vercel AI SDK in a script to clean up the metadata on audio files I downloaded from YouTube. Bonus: I even was able to dogfood the React Compiler, which helped me fix a performance bug! That's all! It's fun to make personal software:

Lee Robinson

118,242 views • 1 year ago