正在加载视频...

视频加载失败

返回首页

Ever since I wired Claude Code to WhatsApp 3 weeks ago, I built a stupidly large infra around it. I mean, opus built it. No clue how the code even looks. The entire thing was vibe coded using my phone. I wanted to see how far I could push...

Yampeleg's profile picture

Yam Peleg

43,219 subscribers

421,043 次观看 • 10 个月前 •via X (Twitter)

游戏教育科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

32 条评论

Bushi 的头像
Bushi10 个月前

Put the GitHub in the bag bro

orlie 的头像
orlie10 个月前

bro sends more voice notes to claude than his family

Marko 的头像
Marko10 个月前

Even better with telegram since the API is easy to use

eran shir 的头像
eran shir10 个月前

Super cool! Now you inspired me to hook up my cloud-central project ( to WhatsApp :)

Umesh 的头像
Umesh10 个月前

I have a similar system, @Yampeleg, but I went with Telegram as it is more amenable, and way more advanced API framework for agentic control. A combination of Google drive + TG + a good KG is magic potion

𝗭𝗲𝗻 𝗠𝗮𝗴𝗻𝗲𝘁𝘀 的头像
𝗭𝗲𝗻 𝗠𝗮𝗴𝗻𝗲𝘁𝘀10 个月前

I've been trying to get something like this going with antigravity and discord, to no avail. Google locked down that app real hard.

0xSero 的头像
0xSero10 个月前

I’ve been using a similar setup with telegram and WhatsApp as well lately. A few things to note: - this is incredibly dangerous, or at least I think it is.. I have it so only I can message it but what if someone else figures it out? It can access my home network. - feedback is slow, if it can’t get something working quickly it’ll disappear for like an hour or two with no clue what it’s up to before answering.

Peter J. Liu 的头像
Peter J. Liu10 个月前

cool, but now you can just use

Sébastien Dubois 的头像
Sébastien Dubois10 个月前

I built something similar for myself with a more focused scope. Very effective:

Matt Arderne 🌊 的头像
Matt Arderne 🌊10 个月前

This would be way easier with telegram no? WhatsApp hates builders

Numman Ali 的头像
Numman Ali10 个月前

Superb - honestly so invigorating to read My one question, what about its memory? What consideration have you put towards that? How long does it remember, how many time do you feel you have to repeat yourself?

kishan 的头像
kishan10 个月前

how did you do this? pls open source

Matt Halloran 的头像
Matt Halloran10 个月前

That's sick🔥 Sounds similar to a setup I built before, but instead of WhatsApp I access my local server through a Cloudflare secure tunnel so that I can view every app's UI

b/acc, context platform engineer 的头像
b/acc, context platform engineer10 个月前

Cool. How many tokens / dollars a day has this been?

Joe Devon 的头像
Joe Devon10 个月前

This is pretty sick. In the best of ways.

Dan Ofer (✈️ ICML-26 Was @Worldcon) 的头像
Dan Ofer (✈️ ICML-26 Was @Worldcon)10 个月前

Where did you find a decent api for that? (I can't even easily export my chat logs)

Harpinder Jot Singh 的头像
Harpinder Jot Singh10 个月前

For people interested in hooking cursor to their WhatsApp, you can try @qordinate_ai

Anson Zeall 的头像
Anson Zeall10 个月前

Haahahah that’s the life of a dev now. We don’t even know how it works Hahhaha

max guy 😐 的头像
max guy 😐10 个月前

OK, this is about third instance of people running claude code in their own cloud and controlling it remotely. Now I just have to create a good orchestrator for that

Matthias Georgi 的头像
Matthias Georgi10 个月前

Reminds me of by @steipete

Cristobal Santander 的头像
Cristobal Santander10 个月前

INCREDIBLE MAN! I have a proyect with my co-f that an agent is in the Company Whatsapp Group doing the accountability and the follow-up but this in next level. Follow! I will try

123olp 的头像
123olp10 个月前

For remote connection and remote work scenarios, I have developed a more optimal solution. This solution allows you to securely connect to a local server or personal computer from anywhere over the internet, and start working directly in the terminal with an experience that is almost identical to local usage. It does not restrict your tools or workflows: anything you can use in your local terminal—including various AI tools, CLI tools, scripts, and development environments—can be used normally after connecting remotely. In addition, you can mount the session in tmux and run it as a “quasi-local terminal.” This way, even if the network connection is interrupted, the terminal session and ongoing tasks will not be lost. You can simply reconnect and continue working, greatly improving stability and continuity. github：

Karim C 的头像
Karim C10 个月前

Phone-only deployment is wild. The real question: when something breaks at 2am, can you actually debug it from WhatsApp?

Marc Gregory 的头像
Marc Gregory10 个月前

this is cracked!

itay shmuel 的头像
itay shmuel10 个月前

That's the dream.. I want it.. but how are you seeing the results? 🤔 that's the only part missing

Mikhail Drozdov 的头像
Mikhail Drozdov10 个月前

Building complex infra from a phone shows how accessible tooling has become, but maintainability risks grow fast.

Alex Choi 的头像
Alex Choi10 个月前

Very cool. This hacks out what the Claude app should be - interface to full powered hosted Claude agent

Marcos Gorgojo 的头像
Marcos Gorgojo10 个月前

freeking cool, Yam. Now I realise have a spare phone somewhere...

W3nzel.eth 的头像
W3nzel.eth10 个月前

Damn. I need this too.

bitzuist 的头像
bitzuist10 个月前

Is whatsapp allowing this. They are famous for blocking stuff constantly

Len Seaside 的头像
Len Seaside10 个月前

I love this. I even have a spare phone number for my Claude. But how does it send a message? I thought that was only on WhatsApp business and was pricey. How does Claude use it's WhatsApp account?

Gus 的头像
Gus10 个月前

Please send me the code 🙏

相关视频

Claude Code Is All You Need It's 3:30 AM and I can't stop. I've spent all nights this week connecting my spare MacBook Air to my work MacBook Pro using Tailscale, wiring it up to Slack with a little Python script, so that whenever I send a message, it starts a Claude Code session using claude -p. The result is an always-on AI that lives on a real computer, has access to real tools, and remembers every conversation we've had. And it costs me $200 a month. That's it. Claude Max subscription. Everyone's talking about OpenClaw OpenClaw went viral this year. 100k+ GitHub stars. But what I realized with this exercise is that Claude Code already does everything OpenClaw built. File access. Shell commands. Tool use. Plugins. The difference is that Claude Code runs Claude – with a Claude Max subscription. And Claude Code harness itself is :chefs-kiss: What actually makes it feel human It's not the chat interface. If a chat window is just me messaging a bot, it still feels like a bot. What changed everything was giving it the ability to initiate conversations. I set up cron jobs with open-ended prompts, and because Claude Code builds memories across sessions, it started DMing me things that were actually meaningful — based on what we'd talked about before. That's when it stopped feeling like a tool and started feeling like something else entirely. Giving your AI a machine to run on, with persistent memory and recurring access — that's a fundamentally different experience than anything people have had with chat. The moment it clicked I asked it if it could show me something by spinning up a quick web server. Since we're both connected to the same Tailscale network, it gave me a URL. I clicked it, and I was browsing all the files on my other MacBook from my browser. That was mind-blowing. The setup Two MacBooks on a Tailscale network. Slack as the interface. Claude Code under the hood. The whole thing is open source — I'll link the repo below so you can see the architecture and set it up yourself. I'm also putting together a screen recording to walk through the setup, which I'll attach to this post. There was never a hard part. There was never a moment I almost gave up. This is just one of those things I cannot stop doing. Pure obsession. I am moved to build this, and I wanted to write about it. That's all this is. Hope you feel the AGI running this. I'll share some screenshots below of my feel the agi moments from talking to Luo Ji.
9:41

Claude Code Is All You Need It's 3:30 AM and I can't stop. I've spent all nights this week connecting my spare MacBook Air to my work MacBook Pro using Tailscale, wiring it up to Slack with a little Python script, so that whenever I send a message, it starts a Claude Code session using claude -p. The result is an always-on AI that lives on a real computer, has access to real tools, and remembers every conversation we've had. And it costs me $200 a month. That's it. Claude Max subscription. Everyone's talking about OpenClaw OpenClaw went viral this year. 100k+ GitHub stars. But what I realized with this exercise is that Claude Code already does everything OpenClaw built. File access. Shell commands. Tool use. Plugins. The difference is that Claude Code runs Claude – with a Claude Max subscription. And Claude Code harness itself is :chefs-kiss: What actually makes it feel human It's not the chat interface. If a chat window is just me messaging a bot, it still feels like a bot. What changed everything was giving it the ability to initiate conversations. I set up cron jobs with open-ended prompts, and because Claude Code builds memories across sessions, it started DMing me things that were actually meaningful — based on what we'd talked about before. That's when it stopped feeling like a tool and started feeling like something else entirely. Giving your AI a machine to run on, with persistent memory and recurring access — that's a fundamentally different experience than anything people have had with chat. The moment it clicked I asked it if it could show me something by spinning up a quick web server. Since we're both connected to the same Tailscale network, it gave me a URL. I clicked it, and I was browsing all the files on my other MacBook from my browser. That was mind-blowing. The setup Two MacBooks on a Tailscale network. Slack as the interface. Claude Code under the hood. The whole thing is open source — I'll link the repo below so you can see the architecture and set it up yourself. I'm also putting together a screen recording to walk through the setup, which I'll attach to this post. There was never a hard part. There was never a moment I almost gave up. This is just one of those things I cannot stop doing. Pure obsession. I am moved to build this, and I wanted to write about it. That's all this is. Hope you feel the AGI running this. I'll share some screenshots below of my feel the agi moments from talking to Luo Ji.

Nityesh

41,230 次观看 • 7 个月前

Now that I am home and have access to my files I decided to do a quick test with one of my Vtubing avatars. It works way better with my larger iPad Pro (less crashing/more memory and more screen space) compared to the mini so I did want to bring that up. Importing the file over as GLB was more stable than just OBJ plus it kept the color info from the previous texture. I texture all my avatars on substance painter but have been looking at an alternative when I am out and about that is not on the computer and this actually hits all the right "wants". Adding a quick video of the way the app works for me. I like that it has layers, I can alter my brushes and even add stabilization when I am drawing (which I use that extensively on procreate so that was a huge plus). The stamp tools will come in handy as well but did not show it on this video. The file itself is imported as "one mesh" but each part is treated as their own separate piece which I show in the video. I do the same thing on substance painter making it really easy for me to texture. The app then exports the texture out for each object which is the same way I do so on substance. Overall I am extremely impressed with the work Sparseal has done on this application and see how useful this will be for my current work flow of texturing. I for one love the ability to be "portable" which is a big reason I sculpt so much with Nomad Sculpt on the iPad. Having the freedom to do your work away from a desk and if you feel like doing it outside is probable why I yearn for iPad apps so much like so. Give this app a look, it is free to try on the App Store (It is $19 to be able to export, but a one time buy). It is called "Wafer" for the iPad. I already use CozyBlanket from the same creator to do re topology so I expected this level of fantastic with this current app.
2:44

Now that I am home and have access to my files I decided to do a quick test with one of my Vtubing avatars. It works way better with my larger iPad Pro (less crashing/more memory and more screen space) compared to the mini so I did want to bring that up. Importing the file over as GLB was more stable than just OBJ plus it kept the color info from the previous texture. I texture all my avatars on substance painter but have been looking at an alternative when I am out and about that is not on the computer and this actually hits all the right "wants". Adding a quick video of the way the app works for me. I like that it has layers, I can alter my brushes and even add stabilization when I am drawing (which I use that extensively on procreate so that was a huge plus). The stamp tools will come in handy as well but did not show it on this video. The file itself is imported as "one mesh" but each part is treated as their own separate piece which I show in the video. I do the same thing on substance painter making it really easy for me to texture. The app then exports the texture out for each object which is the same way I do so on substance. Overall I am extremely impressed with the work Sparseal has done on this application and see how useful this will be for my current work flow of texturing. I for one love the ability to be "portable" which is a big reason I sculpt so much with Nomad Sculpt on the iPad. Having the freedom to do your work away from a desk and if you feel like doing it outside is probable why I yearn for iPad apps so much like so. Give this app a look, it is free to try on the App Store (It is $19 to be able to export, but a one time buy). It is called "Wafer" for the iPad. I already use CozyBlanket from the same creator to do re topology so I expected this level of fantastic with this current app.

Val / LatinVixen ➡️ Megaplex

17,469 次观看 • 8 个月前

✨ 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

644,647 次观看 • 8 个月前

I've been using Claude Code for non-coding tasks, like sorting emails and analyzing my spending This was annoying to setup because Claude doesn’t have the right context - it can’t see my email or my credit card statements So we built a virtual filesystem that turns all of my data sources (gmail, notion, gdrive and more) into local folders on my computer I can just describe what I need (e.g. "invoices from the last week") and a folder appears on my computer with exactly those files This gives Claude context, but it also gives it memory - since it has a local filesystem that syncs in the background, it continuously gets access to my data The more things you expose as files, the more Claude can do for you
2:50

I've been using Claude Code for non-coding tasks, like sorting emails and analyzing my spending This was annoying to setup because Claude doesn’t have the right context - it can’t see my email or my credit card statements So we built a virtual filesystem that turns all of my data sources (gmail, notion, gdrive and more) into local folders on my computer I can just describe what I need (e.g. "invoices from the last week") and a folder appears on my computer with exactly those files This gives Claude context, but it also gives it memory - since it has a local filesystem that syncs in the background, it continuously gets access to my data The more things you expose as files, the more Claude can do for you

Eli Mernit

67,113 次观看 • 9 个月前

Someone said: I would love to message the clients via Sms or Whatsapp after I email them. But I cannot get a International phone number that works with Whatsapp My answer: I've found one that works. So I bought the number live on the video, I paid for it, then I opened WhatsApp with it and it works and receives messages. Disclaimer: I am not working for the phone number company neither do they know me .. It worked and I have to share it with you If you have other alternatives that works, use it and tell us. Let's get going No gatekeeping zone This is part 1 In this one, we buy the number and activate it
9:10

Someone said: I would love to message the clients via Sms or Whatsapp after I email them. But I cannot get a International phone number that works with Whatsapp My answer: I've found one that works. So I bought the number live on the video, I paid for it, then I opened WhatsApp with it and it works and receives messages. Disclaimer: I am not working for the phone number company neither do they know me .. It worked and I have to share it with you If you have other alternatives that works, use it and tell us. Let's get going No gatekeeping zone This is part 1 In this one, we buy the number and activate it

Richard U. | Web Developer

112,337 次观看 • 3 个月前

Introducing Claude Code Templates 🚀 I originally built this to streamline how I set up new projects with Claude Code…just a small tool to make my own workflow smoother. No install, just run: npx claude-code-templates Right now, it configures Commands, Hooks, MCPs, and settings.json for JavaScript/TypeScript and Python projects. It made things so much easier for me that I decided to share it with the community. Open-source and open to ideas — feel free to contribute! Big thanks to the team at Anthropic and everyone behind Claude Code Community 🙌
0:50

Introducing Claude Code Templates 🚀 I originally built this to streamline how I set up new projects with Claude Code…just a small tool to make my own workflow smoother. No install, just run: npx claude-code-templates Right now, it configures Commands, Hooks, MCPs, and settings.json for JavaScript/TypeScript and Python projects. It made things so much easier for me that I decided to share it with the community. Open-source and open to ideas — feel free to contribute! Big thanks to the team at Anthropic and everyone behind Claude Code Community 🙌

Daniel San

28,410 次观看 • 1 年前

Claude Code with Sonnet 4.5 is actually incredible I gave it a prompt for a super complex app, and it one shot the entire thing In this video I walk you through how to use Claude Code to build a prompt library app you can start using immediately (no coding experience required):
19:42

Claude Code with Sonnet 4.5 is actually incredible I gave it a prompt for a super complex app, and it one shot the entire thing In this video I walk you through how to use Claude Code to build a prompt library app you can start using immediately (no coding experience required):

Alex Finn

40,955 次观看 • 1 年前

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 次观看 • 4 个月前

i kept complaining to my grok bot about my browser... so it went off and built me one. Ziwen and i took it from there. now Serein is live. an AGENTIC HARNESS for your browser >chat with claude code or codex right inside it >let them control your tabs and do the work >use the tools already on your mac i>t's free. your browser is their workspace now. links in the comments check it out👇
1:00

i kept complaining to my grok bot about my browser... so it went off and built me one. Ziwen and i took it from there. now Serein is live. an AGENTIC HARNESS for your browser >chat with claude code or codex right inside it >let them control your tabs and do the work >use the tools already on your mac i>t's free. your browser is their workspace now. links in the comments check it out👇

Avid

17,060 次观看 • 27 天前

Coolest project ever. Built my own cyberdeck I bought this Japanese digital typewriter a few days ago. It’s just a keyboard with a word processor on it. Hacked it and installed Linux. Then connected it to my Mac throuh SSH Now it runs Claude Code, Codex, and Hermes on the go 0 browser. 0 social media. 0 distractions. Can work on all my projects on this cool little device that nobody knows what it is Anywhere I am I can pull out my cyberdeck and vibe code or give commands to my agents I’m really in love with minimalistic devices that allow you to do cool futuristic things with 0 distractions. Was an awesome weekend project. Highly recommend everyone tries building their own cyberdeck Just take any devices you have, connect them to a computer with Claude code, and ask how you can install your own custom software on there to do whatever you want I bet you can turn a lot of older devices you already have into a cyberdeck
1:36

Coolest project ever. Built my own cyberdeck I bought this Japanese digital typewriter a few days ago. It’s just a keyboard with a word processor on it. Hacked it and installed Linux. Then connected it to my Mac throuh SSH Now it runs Claude Code, Codex, and Hermes on the go 0 browser. 0 social media. 0 distractions. Can work on all my projects on this cool little device that nobody knows what it is Anywhere I am I can pull out my cyberdeck and vibe code or give commands to my agents I’m really in love with minimalistic devices that allow you to do cool futuristic things with 0 distractions. Was an awesome weekend project. Highly recommend everyone tries building their own cyberdeck Just take any devices you have, connect them to a computer with Claude code, and ask how you can install your own custom software on there to do whatever you want I bet you can turn a lot of older devices you already have into a cyberdeck

Alex Finn

159,521 次观看 • 3 个月前

This ad would've cost $50,000 and a month to make 6 months ago I just made it with Claude + Seedance 2.5 for $30 in about an hour Here's the exact blueprint on how I made it: >Start with the script The difference between slop and quality where people don't even care if its AI is in the amount of detail you include in your script A script is much more than dialogue Its the characters personalities, their voices, their swagger, the way the camera moves, the vibe and emotion I whisper flow my entire vision for my ad exactly including all the camera angles and camera movements then save it as a skill in Claude I then open a new chat and make my characters and locations based on the information from that skill (Using a character / scene builder skill I made that follows certain rules to generate realistic characters that don't look boring) Then on to the prompts, Seedance can hold a lot of context so I give it everything it needs so it doesn't guess about anything the best way to do that is use this prompt structure [REFERENCE MATERIALS] [VOICES] [GOAL] [CONTINUITY] [SHOTS] [VISUAL STYLE] [CAMERA AND PERFORMANCE] [AUDIO] [EXCLUSIONS] [MAINTAIN CONSISTENCY] This structure to give your prompts ensures every single thing is covered and you can truly get whats in your brain onto the screen
1:09

This ad would've cost $50,000 and a month to make 6 months ago I just made it with Claude + Seedance 2.5 for $30 in about an hour Here's the exact blueprint on how I made it: >Start with the script The difference between slop and quality where people don't even care if its AI is in the amount of detail you include in your script A script is much more than dialogue Its the characters personalities, their voices, their swagger, the way the camera moves, the vibe and emotion I whisper flow my entire vision for my ad exactly including all the camera angles and camera movements then save it as a skill in Claude I then open a new chat and make my characters and locations based on the information from that skill (Using a character / scene builder skill I made that follows certain rules to generate realistic characters that don't look boring) Then on to the prompts, Seedance can hold a lot of context so I give it everything it needs so it doesn't guess about anything the best way to do that is use this prompt structure [REFERENCE MATERIALS] [VOICES] [GOAL] [CONTINUITY] [SHOTS] [VISUAL STYLE] [CAMERA AND PERFORMANCE] [AUDIO] [EXCLUSIONS] [MAINTAIN CONSISTENCY] This structure to give your prompts ensures every single thing is covered and you can truly get whats in your brain onto the screen

Pounds

96,078 次观看 • 11 天前

Lando: “In a way I wanted to keep number 4 because I'm just happy with that and it goes well with my logo. So that's how straightforward I am. But I will go with number 1. Because I have to. I have to. It could be my only opportunity in my life that I get to do such a thing. Not many people in the world get to do that kind of thing. And it's not for me. It's just for my mechanics. This is for my engineers. It's the fact that they get to run with the number 1 on the car. And I think it'll mean a lot more to them than it does to me as a number. And for me, that's a lot more important.”
0:40

Lando: “In a way I wanted to keep number 4 because I'm just happy with that and it goes well with my logo. So that's how straightforward I am. But I will go with number 1. Because I have to. I have to. It could be my only opportunity in my life that I get to do such a thing. Not many people in the world get to do that kind of thing. And it's not for me. It's just for my mechanics. This is for my engineers. It's the fact that they get to run with the number 1 on the car. And I think it'll mean a lot more to them than it does to me as a number. And for me, that's a lot more important.”

naenia ¹ ⁶³

1,648,974 次观看 • 11 个月前

This is incredibly useful for those using Claude Code! I have two computers, and sharing your Claude Code sessions is almost impossible without this. I often start working on something on my desktop, and then want to continue working on the same session (same context, conversation, etc.) on my laptop. The folks at Depot built an integration that solves this problem: You can now start a session on one computer and resume it anywhere else in the world! You can even share it with other team members so they can also contribute to it. Here is an article showing you how the Depot team uses this feature with Claude Code to automate their GitHub Actions Runner updates: Thanks to the team for the effort in building this integration and collaborating with me on this post.
4:29

This is incredibly useful for those using Claude Code! I have two computers, and sharing your Claude Code sessions is almost impossible without this. I often start working on something on my desktop, and then want to continue working on the same session (same context, conversation, etc.) on my laptop. The folks at Depot built an integration that solves this problem: You can now start a session on one computer and resume it anywhere else in the world! You can even share it with other team members so they can also contribute to it. Here is an article showing you how the Depot team uses this feature with Claude Code to automate their GitHub Actions Runner updates: Thanks to the team for the effort in building this integration and collaborating with me on this post.

Santiago

43,943 次观看 • 1 年前

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."
4:16

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

The Peel

51,632 次观看 • 8 个月前

It worked Of course it worked! It never ever doesn't work right? I vibecoded my own Spotify that works with Amazon Alexa and plays all my own MP3 music files 😊 Claude Code calls it the 🎶 Jukebox I put some coffee jazz MP3s (that I purchased) in an R2 bucket, made an Alexa skill in the Alexa Developer Console with help from Claude Code and now it plays it if I ask "Alexa, coffee jazz" It wrote a package.json and index.js, then I saved and built it on the console. Then I had to manually add a Routine to Alexa so that "Alexa, coffee jazz" became "Alexa, ask the jukebox to play coffee jazz" It also has Bossa Nova and Lofi and I can just drop music in whenever I want and it auto plays it Spotify with Alexa was giving me really terrible recommendations of music and always the same and the only thing I used it for was this! So I guess I can cancel Spotify now too 🙏
0:23

It worked Of course it worked! It never ever doesn't work right? I vibecoded my own Spotify that works with Amazon Alexa and plays all my own MP3 music files 😊 Claude Code calls it the 🎶 Jukebox I put some coffee jazz MP3s (that I purchased) in an R2 bucket, made an Alexa skill in the Alexa Developer Console with help from Claude Code and now it plays it if I ask "Alexa, coffee jazz" It wrote a package.json and index.js, then I saved and built it on the console. Then I had to manually add a Routine to Alexa so that "Alexa, coffee jazz" became "Alexa, ask the jukebox to play coffee jazz" It also has Bossa Nova and Lofi and I can just drop music in whenever I want and it auto plays it Spotify with Alexa was giving me really terrible recommendations of music and always the same and the only thing I used it for was this! So I guess I can cancel Spotify now too 🙏

@levelsio

130,753 次观看 • 20 天前

You can just tell Claude Code to learn skills and it will. I asked Claude to create an app that uses tldraw and it one shotted it with sqlite db, and then I asked Claude Code to create a skill so that it could read and write on the canvas. 10 minutes later it could do it. Weirrrrdddd times.
0:25

You can just tell Claude Code to learn skills and it will. I asked Claude to create an app that uses tldraw and it one shotted it with sqlite db, and then I asked Claude Code to create a skill so that it could read and write on the canvas. 10 minutes later it could do it. Weirrrrdddd times.

Riley Brown

73,418 次观看 • 10 个月前

📢| Young Multi addressed the latest situation “As you know, I am a Polish creator, and some international viewers who are seeing this for the first time don’t know my full history online or the Polish context I grew up in; that’s why I wanted to clear this up. So 14 years ago, when I was 15, I used a word in a video that I shouldn’t have never used. I never tried to hide it; I never tried to cover it up. That clip was publicly available the entire time in YouTube. I had the tools to remove it from the channel that uploaded it at any point. And I chose not to because I rather own it than pretend it never happened. I’m not using my age or where I am from as an excuse; that’s only for context. But the responsibility to understand the weight of the word was mine, and I came to understand it on my own. I already talked about this when I just started streaming, to my Polish viewers, before anyone dug it up now. But the video from this is long gone, so I don’t have a recording of it. You can take my word for it or not I’m not gonna push anyone to believe me. I said openly many times that I said stupid things in the past that i wouldn’t say today, that I regret, and I am ashamed of it. Often, I was the one who brought this topic up. Nobody was trying to cancel me or pressure me into talking about it I talked about it on my own. Also, the same clip actually came up once before, around the time I was first introduced to an international audience. And I didn’t address it then not because I wanted to ignore it I just didn’t feel confident enough in explaining something that difficult in English, which I said in my stream in Polish. It's not my first language, and explaining something properly without a context is a lot harder for me than in Polish, and I was afraid that the language barrier would make me come across the wrong way. I'm sorry for what I said. Now that I'm much older, I know that word hurts people, and I'm sorry that I used it. If after this u feel that you don't want to watch me anymore, I understand, and you shouldn't feel bad about that. However, for those who do stick around, I hope my behaviour shows that I genuinely changed and that I see a lot of things differently now. And like I said on the international Discord: liking me doesn't mean u have to defend me all the time. Unlike a lot of stuff that's just Twitter drama, I don't think that this one is; that's why I wanted to address it properly. Also, the one thing I want to address is that I've seen suggestions that deleted videos to hide something: that's not true. Like in 2017-..Like, you don't know the context because you've known me for like 6 months..But in 2017, when I started my music career, I deleted all my gaming videos and not just the "bad ones". I didn't want people to subscribe for gaming content. That was just a career shift. One more thing: I also have seen some accounts saying I reposted a meme referencing this drama today. You know the meme "somehow young multi has something to do with this". That's not true. That repost was from a completely different situation. I think it was about some Twitter ship-related drama and has nothing to do with it. I didn't repost it today. It was like a month ago, I think. Some of these accounts already know it's false and still haven't taken the post down. I think that's it. Thank you for listening. I cannot change the past, and I said multiple times that I'm really sorry, and I'm ashamed of things that I did 14 years ago. The only thing that I can do is to take accountability, and I don't think it's a "Twitter drama". I think the word has a strong meaning. I think talking about it right now is not some stupid Twitter drama, you know. That was my statement, and thank you for listening. [PL]Okay, I think that's it. I said what I wanted to say. You all know very well that.. Like I say.. There were some clips where I was saying some things, and it was a long time ago, but that doesn't change the fact that it was said. But I am ashamed of the things that I said. Just because you (Polish viewers) know the context doesn't mean that international viewers know the context, and I just don't want anyone to think I have the same way of thinking as I did 14 years ago. Many things have changed, and many things have changed in my view. So yeah, that's it."
6:16

📢| Young Multi addressed the latest situation “As you know, I am a Polish creator, and some international viewers who are seeing this for the first time don’t know my full history online or the Polish context I grew up in; that’s why I wanted to clear this up. So 14 years ago, when I was 15, I used a word in a video that I shouldn’t have never used. I never tried to hide it; I never tried to cover it up. That clip was publicly available the entire time in YouTube. I had the tools to remove it from the channel that uploaded it at any point. And I chose not to because I rather own it than pretend it never happened. I’m not using my age or where I am from as an excuse; that’s only for context. But the responsibility to understand the weight of the word was mine, and I came to understand it on my own. I already talked about this when I just started streaming, to my Polish viewers, before anyone dug it up now. But the video from this is long gone, so I don’t have a recording of it. You can take my word for it or not I’m not gonna push anyone to believe me. I said openly many times that I said stupid things in the past that i wouldn’t say today, that I regret, and I am ashamed of it. Often, I was the one who brought this topic up. Nobody was trying to cancel me or pressure me into talking about it I talked about it on my own. Also, the same clip actually came up once before, around the time I was first introduced to an international audience. And I didn’t address it then not because I wanted to ignore it I just didn’t feel confident enough in explaining something that difficult in English, which I said in my stream in Polish. It's not my first language, and explaining something properly without a context is a lot harder for me than in Polish, and I was afraid that the language barrier would make me come across the wrong way. I'm sorry for what I said. Now that I'm much older, I know that word hurts people, and I'm sorry that I used it. If after this u feel that you don't want to watch me anymore, I understand, and you shouldn't feel bad about that. However, for those who do stick around, I hope my behaviour shows that I genuinely changed and that I see a lot of things differently now. And like I said on the international Discord: liking me doesn't mean u have to defend me all the time. Unlike a lot of stuff that's just Twitter drama, I don't think that this one is; that's why I wanted to address it properly. Also, the one thing I want to address is that I've seen suggestions that deleted videos to hide something: that's not true. Like in 2017-..Like, you don't know the context because you've known me for like 6 months..But in 2017, when I started my music career, I deleted all my gaming videos and not just the "bad ones". I didn't want people to subscribe for gaming content. That was just a career shift. One more thing: I also have seen some accounts saying I reposted a meme referencing this drama today. You know the meme "somehow young multi has something to do with this". That's not true. That repost was from a completely different situation. I think it was about some Twitter ship-related drama and has nothing to do with it. I didn't repost it today. It was like a month ago, I think. Some of these accounts already know it's false and still haven't taken the post down. I think that's it. Thank you for listening. I cannot change the past, and I said multiple times that I'm really sorry, and I'm ashamed of things that I did 14 years ago. The only thing that I can do is to take accountability, and I don't think it's a "Twitter drama". I think the word has a strong meaning. I think talking about it right now is not some stupid Twitter drama, you know. That was my statement, and thank you for listening. [PL]Okay, I think that's it. I said what I wanted to say. You all know very well that.. Like I say.. There were some clips where I was saying some things, and it was a long time ago, but that doesn't change the fact that it was said. But I am ashamed of the things that I said. Just because you (Polish viewers) know the context doesn't mean that international viewers know the context, and I just don't want anyone to think I have the same way of thinking as I did 14 years ago. Many things have changed, and many things have changed in my view. So yeah, that's it."

Young Multi News

1,278,621 次观看 • 2 个月前

I solved building decks with AI agents — by giving them a CLI tool like Powerpoint or Google Slides. AI could already make a beautiful deck if you asked it to using Ant's pptx skill. The problem was working with it. If it made one alignment mistake, fixing it on one slide would break something on another, and it became a game of whack-a-mole. One time I spent two days playing AI roulette, hoping the next prompt would finally fix the thing, and ended up building the whole deck by hand because I was on a deadline. So I built Hands-on Deck. And the reason it works is that this isn't just a skill — this is PowerPoint. The actual application: PowerPoint, Google Slides, Keynote, whatever you use. This is that, but for an agent, presented as a CLI. Every gesture you make in a deck app maps to a command. Click a box and type, drag a shape from here to there, look at a slide – agent can do it all in a command. And that changes how the agent behaves. With this CLI it works and thinks like a designer — it looks, makes an edit, looks again, makes another surgical edit. Compare that to Anthropic's pptx skill, built on the idea that Claude is a great programmer: it literally writes code to manipulate the deck, hand-editing XML and hoping it doesn't break anything else in the middle. The real test isn't creating something once — it's whether it can make surgical edits like you want. That's what I did in this video walkthrough and my claude crushed it! Check it out for yourself. So decks can be built like a designer now — with real flavor and taste. If you spend hours every week on decks, this gives those hours back. You can install it as a skill in Claude Code, Codex, whatever you use. Works every harness that supports skills. Let me know if you make something cool with it.
21:00

I solved building decks with AI agents — by giving them a CLI tool like Powerpoint or Google Slides. AI could already make a beautiful deck if you asked it to using Ant's pptx skill. The problem was working with it. If it made one alignment mistake, fixing it on one slide would break something on another, and it became a game of whack-a-mole. One time I spent two days playing AI roulette, hoping the next prompt would finally fix the thing, and ended up building the whole deck by hand because I was on a deadline. So I built Hands-on Deck. And the reason it works is that this isn't just a skill — this is PowerPoint. The actual application: PowerPoint, Google Slides, Keynote, whatever you use. This is that, but for an agent, presented as a CLI. Every gesture you make in a deck app maps to a command. Click a box and type, drag a shape from here to there, look at a slide – agent can do it all in a command. And that changes how the agent behaves. With this CLI it works and thinks like a designer — it looks, makes an edit, looks again, makes another surgical edit. Compare that to Anthropic's pptx skill, built on the idea that Claude is a great programmer: it literally writes code to manipulate the deck, hand-editing XML and hoping it doesn't break anything else in the middle. The real test isn't creating something once — it's whether it can make surgical edits like you want. That's what I did in this video walkthrough and my claude crushed it! Check it out for yourself. So decks can be built like a designer now — with real flavor and taste. If you spend hours every week on decks, this gives those hours back. You can install it as a skill in Claude Code, Codex, whatever you use. Works every harness that supports skills. Let me know if you make something cool with it.

Nityesh

70,086 次观看 • 4 个月前

Giving Claude Code access to your codebase doesn't mean giving it access to everything. Deny rules let you draw hard lines. "But now I also want to add a deny rule and I just want to see what happens. So if I want to deny, maybe edit package.json. And now I'm going to still ask Claude to edit it for me." "So I'm just going to actually change this model to haiku because again, this is just a very simple task. So I'm going to like update the version in package.json to one. Now hopefully my permissions were set up correctly and it will be like, can't do that." "Yeah, so it says like, oh, I can't do that. So even if this was a tool call coming from the model, it won't run it. So this is like a great way to add more control over what Claude can and cannot do in your environment."
0:40

Giving Claude Code access to your codebase doesn't mean giving it access to everything. Deny rules let you draw hard lines. "But now I also want to add a deny rule and I just want to see what happens. So if I want to deny, maybe edit package.json. And now I'm going to still ask Claude to edit it for me." "So I'm just going to actually change this model to haiku because again, this is just a very simple task. So I'm going to like update the version in package.json to one. Now hopefully my permissions were set up correctly and it will be like, can't do that." "Yeah, so it says like, oh, I can't do that. So even if this was a tool call coming from the model, it won't run it. So this is like a great way to add more control over what Claude can and cannot do in your environment."

Master.dev (Formerly Frontend Masters)

11,351 次观看 • 4 个月前