Yam Peleg
@Yampeleg • 43,081 subscribers
The only AI researcher they sent a missile for 🇮🇱 | Co-host @thursdai_pod • AI news every Thursday
Videos
![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 it without touching the computer. Everything via WhatsApp. Build what I need on the fly. So the resulting infrastructure will already be battle tested for software development. The entire thing was streamlined with nearly no manual interventions, everything was communicated via WhatsApp using a single script establishing this connection. If the script is down, I need to get home to start it again to resume the development. Claude was upgrading it, debugging it, restarting it while maintaining constant uptime so it could keep communicating with me. I stressed Claude about it, telling it that it will be “in the dark” and other words that deliberately sound scary about losing communications if the script dies. I also refused git and refused cloning the code, I wanted to see Claude adapting to work on a *LIVING* system. The way this whole thing works: Claude has its own dedicated phone number that I am paying for. A real WhatsApp account for it is installed on a real iPhone that is sitting on my desk. All is registered under my name, this is legit setup with no hacks and tricks. I’ve set up a WhatsApp “Community” and multiple different groups under it. Both me and Claude are the admins, so Claude could edit it on my behalf. Each group is a project I am working on and has its own isolated context. The Group description is a system prompt that gets auto-appended to the larger system prompt explaining this setup in general. When I send a message it’s an instant interrupt to Claude Code’s process, just like in the terminal. Voice notes are seamlessly transcribed with a local Whisper model. Images are used with multimodal reading in an isolated parallel session. Multiple groups running in parallel so I can work on all projects at the same time. No cross-talking, everything has an isolated context and history. And because it’s local on my own machine: Everything is REAL. The browser is REAL. I am connected as myself on it to all services because I actually use it in real life. Claude has unlimited internet access, just like humans who use actual browsers. It utilizes custom-made browser tools that I made to control any browser session it wants. Depending on the situation, it can either connect to my existing session or create one for its own. (You can tell it ‘look at my browser for a sec’ then talk about the current page you are on and it just works, pretty cool) My custom browser tools are not perfect (not by a long shot) but I managed to make them work well to the point they are somewhat reliable. This gives Claude full access to my real creds and all the services I actually use. I’m productive AS HELL with this. It really feels like a personal assistant. I ask it to read my emails and msgs, check x .com for news, research arxiv papers, write code, run experiments for me, investigate and reverse engineer github repos, even use my credit card and order things. [I try not to do this one a lot lol so far no disasters]. All from my phone. Super convenient. This is not a product or an open source project (maybe soon of it will make sense). This is just an ugly script I hacked the entire thing is ~600 lines. (ok maybe i did look at the code, but i swear i didn’t edit!) You can also vibe code this from scratch pretty fast and it will probably even end up better. This is just a cool thing so I’m sharing. It is a real speed booster for many things I do on daily basis, mostly boring things. Forcing my routine into some new “agent platform” just didn’t feel right for me. WhatsApp is where I already communicate and look for messages, so I decided that my agents will live there too. AGI in my pocket 24/7.](https://image.24vids.com/tw-2000642897402880491/amplify_video_thumb/2000642716951064582/img/ReuTixQFFAAQc_x0.jpg)
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 it without touching the computer. Everything via WhatsApp. Build what I need on the fly. So the resulting infrastructure will already be battle tested for software development. The entire thing was streamlined with nearly no manual interventions, everything was communicated via WhatsApp using a single script establishing this connection. If the script is down, I need to get home to start it again to resume the development. Claude was upgrading it, debugging it, restarting it while maintaining constant uptime so it could keep communicating with me. I stressed Claude about it, telling it that it will be “in the dark” and other words that deliberately sound scary about losing communications if the script dies. I also refused git and refused cloning the code, I wanted to see Claude adapting to work on a *LIVING* system. The way this whole thing works: Claude has its own dedicated phone number that I am paying for. A real WhatsApp account for it is installed on a real iPhone that is sitting on my desk. All is registered under my name, this is legit setup with no hacks and tricks. I’ve set up a WhatsApp “Community” and multiple different groups under it. Both me and Claude are the admins, so Claude could edit it on my behalf. Each group is a project I am working on and has its own isolated context. The Group description is a system prompt that gets auto-appended to the larger system prompt explaining this setup in general. When I send a message it’s an instant interrupt to Claude Code’s process, just like in the terminal. Voice notes are seamlessly transcribed with a local Whisper model. Images are used with multimodal reading in an isolated parallel session. Multiple groups running in parallel so I can work on all projects at the same time. No cross-talking, everything has an isolated context and history. And because it’s local on my own machine: Everything is REAL. The browser is REAL. I am connected as myself on it to all services because I actually use it in real life. Claude has unlimited internet access, just like humans who use actual browsers. It utilizes custom-made browser tools that I made to control any browser session it wants. Depending on the situation, it can either connect to my existing session or create one for its own. (You can tell it ‘look at my browser for a sec’ then talk about the current page you are on and it just works, pretty cool) My custom browser tools are not perfect (not by a long shot) but I managed to make them work well to the point they are somewhat reliable. This gives Claude full access to my real creds and all the services I actually use. I’m productive AS HELL with this. It really feels like a personal assistant. I ask it to read my emails and msgs, check x .com for news, research arxiv papers, write code, run experiments for me, investigate and reverse engineer github repos, even use my credit card and order things. [I try not to do this one a lot lol so far no disasters]. All from my phone. Super convenient. This is not a product or an open source project (maybe soon of it will make sense). This is just an ugly script I hacked the entire thing is ~600 lines. (ok maybe i did look at the code, but i swear i didn’t edit!) You can also vibe code this from scratch pretty fast and it will probably even end up better. This is just a cool thing so I’m sharing. It is a real speed booster for many things I do on daily basis, mostly boring things. Forcing my routine into some new “agent platform” just didn’t feel right for me. WhatsApp is where I already communicate and look for messages, so I decided that my agents will live there too. AGI in my pocket 24/7.
Yam Peleg419,401 次观看 • 6 个月前
![IDF Spokesperson announced yesterday that Hamas's last battalion in North Gaza is destroyed. [1] North Gaza had 2 brigades divided into 12 battalions. Destruction of all 12 marks half of Hamas. --- [1] Was stationed at Daraj/Tuffah.](https://image.24vids.com/tw-1744053443960930482/ext_tw_video_thumb/1744045588272828416/pu/img/f1CD1fk-b3o2t5Wh.jpg)
Lore TL;DR: > spent summer in SF > missile hit my place back home > officially refugee, returned, officially displaced > snuck into collapse hazard building, rescued GPUs > patched together a working setup > technical posts coming back to x .com > apologies for the inconvenience
Yam Peleg177,658 次观看 • 11 个月前
Recovering Israel’s Hebrew-AI from a Collapsing Bombed Tower (Part 2) —— Background On 12 June 2025, a one‑ton ballistic missile slammed through one of Tel Aviv’s tallest towers home to thousands of residents, dozens of tech offices, and my own apartment. I was abroad when it hit. • Several floors were obliterated; the warhead blew straight out the far side. • Search‑and‑rescue teams smashed every door to reach survivors while the tower swayed, except mine. (they called me, skipped it and moved on). • Many victims remain in critical condition. • Engineers branded the skyscraper an imminent‑collapse hazard; police sealed a multi‑street perimeter 24 / 7. • News outlets camping outside, calling it “a miracle the building still stands” amid lawsuits and a pending demolition order. ⸻ The Mission After weeks stranded overseas, I was granted an exceptional, rare official clearance to enter (solo) and retrieve core infrastructure of Israel’s Hebrew‑AI project from within my personal server rack in my apartment’s bomb shelter. Targets • Hebrew AI models trained in Israel, many yet to be released to the public. • +200TB Hebrew dataset, largest ever collected. • Irreplaceable research data • GPU clusters & AI infrastructure TL;DR • Zero power pitch‑black interior • No elevators, stairs collapsed, blocked passages • 20 floors to climb, +200kg to carry • Strict 2-hour window with multiple trips required • Detailed planing, Custom reinforced cases and carry systems, improvised tools • Two army friends monitoring FaceTime live video, ready to call in help (and call me an idiot for this) ⸻ The Video • Raw POV footage, edited for watchability but untouched and real • Real‑time improvisation, between debris and structural blind spots • Might be the last‑chance for extraction before demolition Not a clickbait, real footage. More parts to come..
Yam Peleg125,772 次观看 • 10 个月前
0:22
Sensitive content
This media may contain sensitive content.
没有更多内容可加载