the model isn't the problem. your setup is | ai skills, agents, prompts
Washington
Joined September 2026
- Tweets919
- Following44
- Followers106
- Likes1.2K
Vector retweeted
Mia Khalifa was one of the most searched names on the biggest adult site on earth.
Over a billion views on her videos.
Her cut: $12,000.
She was 21. Three months. About 12 scenes at roughly $1,000 each. She quit in early 2015.
The videos never stopped. Millions in revenue for the companies. Her share of ongoing profits: zero.
She doesn’t own the videos, the photos, or even the domain with her own name on it. Her team tried to buy the rights back. No deal.
The studio later said she was paid $178,000 and filmed more scenes. She says most of that was for a separate social-media job.
Two versions. They can’t both be true. Either way, the clips are still running.
In her words: “It makes me feel like I lost all right to my privacy.”
She signed the contract.
Does the internet own her face forever - or should anyone be able to take it back?
Sophie Rain has shown ~$100M+ in OnlyFans gross. High-profile people with real money online are constant targets.
A recent case shows how little it takes: a user lost thousands after three days on open hotel Wi-Fi. No phishing link. No leaked seed phrase. Just a fake approval prompt that looked normal while he was on a legitimate site.
Here’s the usual play:
→ Attacker joins the same local network (hotel, Airbnb, café, or a compromised router).
→ Injects or sits in the middle of traffic.
→ You open your wallet or exchange as usual.
→ A “reconnect,” “verify,” or approval request appears.
→ You sign once. Funds move later (or immediately).
On-chain there is no undo.
How to stay uncooked:
→ Never touch a wallet or exchange on public/shared Wi-Fi. Use a hotspot or VPN.
→ Keep serious size on a hardware wallet.
→ Read every signature on the device before confirming—especially permissions and unlimited approvals.
→ Lock down your own router (change defaults, disable remote access).
Your bag is only as safe as the network you open it on.
Save this before the next trip.
Vector retweeted
this is f*cking insane
the most underrated way to give Claude Code a memory: a globe of plain text files around one map, and every answer comes back with the file it came from
zero apps, and Claude says not found instead of inventing a password
how it works:
→ one map file in the center, loaded before you type anything
→ three folders around it: notes, people, projects
→ every dot is one topic in one file, named after what's inside
→ memory and decisions stay pinned next to the map
paste this into Claude Code in an empty folder ↓
"Build a second brain here:
1. Folders: notes, people, projects.
2. Root files for memory, lessons and decisions.
3. One map file that says where each kind of info lives.
4. One topic per file, lowercase with hyphens.
5. Answer from the file the map points to and cite it. Not there? Say so.
Show me the plan first."
save this now, your globe grows with every file you add
Vector retweeted
Sophie Rain has shown ~$100M+ in OnlyFans gross. High-profile people with real money online are constant targets.
A recent case shows how little it takes: a user lost thousands after three days on open hotel Wi-Fi. No phishing link. No leaked seed phrase. Just a fake approval prompt that looked normal while he was on a legitimate site.
Here’s the usual play:
→ Attacker joins the same local network (hotel, Airbnb, café, or a compromised router).
→ Injects or sits in the middle of traffic.
→ You open your wallet or exchange as usual.
→ A “reconnect,” “verify,” or approval request appears.
→ You sign once. Funds move later (or immediately).
On-chain there is no undo.
How to stay uncooked:
→ Never touch a wallet or exchange on public/shared Wi-Fi. Use a hotspot or VPN.
→ Keep serious size on a hardware wallet.
→ Read every signature on the device before confirming—especially permissions and unlimited approvals.
→ Lock down your own router (change defaults, disable remote access).
Your bag is only as safe as the network you open it on.
Save this before the next trip.
Vector retweeted
THIS CABLE CHARGES YOUR PHONE. BUT PLUG IT INTO YOUR LAPTOP AND IT COULD START TYPING COMMANDS WITHOUT YOU.
same plastic. same logo. charges like any other cable. you’d never look at it twice.
inside there’s a chip smaller than a fingernail. plug it in and your laptop thinks a keyboard just connected. then it types on its own. opens a terminal, runs commands, closes it before you look up.
some versions go further and log your keystrokes. passwords included.
this isn’t sci-fi. it’s called the O.МG cable, and it’s sold to security testers right now.
will someone target you with one? honestly, probably not.
but the trick behind it is everywhere:
→ your laptop trusts anything that says “i’m a keyboard”
→ public chargers and “free” cables are a blind spot
→ nobody checks what a cable actually is
simple habits:
→ use your own cable. always
→ “trust this computer?” at a public charger = tap no
→ a cheap usb data blocker for public ports
borrowed a cable or found one in the office? i made a prompt that has claude code check it in 2 minutes.
it’s in the first reply.
Vector retweeted
HOLY SH*T people are still manually wiring Claude into Obsidian as a second brain while the Obsidian CEO already open-sourced the entire setup plan
Here are 4 GitHub repos that do the heavy lifting for you:
→ obsidian skills (by kepano) github.com/kepano/obsidia… Teaches Claude the exact internal mechanics of your vault
→ claude obsidian (by AgriciDaniel) github.com/AgriciDaniel/c… Ready-to-use commands for wiki-links, ingestion, queries and linting
→ obsidian second brain (by eugeniughelbur) github.com/eugeniughelbur… 48 ready-to-run commands for Claude Code, Codex and Gemini
→ second brain starter (by coleam00) github.com/coleam00/secon… Interactive onboarding that builds a personalized 9-step setup plan
Most tutorials floating around still point to dead scripts and broken workflows.
Bookmark this before it disappears.
Vector retweeted
🚨I asked Claude Code to turn his WiFi router into a radar
In 40 minutes he wrote the code that reads how the WiFi signal bends around bodies and draws them as moving shapes on the map of his floor
He tested it at night and lives alone thought it was a bug so he went to the bedroom and the shape didn't move
The map showed it standing next to the bed looking at the door so he turned it off and still doesn't know what it was he was reading the code
Save it
Vector retweeted
YOUR WIFI CAN DETECT MOVEMENT WITHOUT A CAMERA. I ASKED CLAUDE CODE TO TURN THAT IDEA INTO A 3D RADAR.
And the result is pretty damn wild.
A week ago, I turned my Wi-Fi router into a radar using Claude Code. No camera needed.
Claude rewrote the router’s firmware in just 10 minutes, then built code that analyzes how Wi-Fi signals bend around human bodies, turning them into moving silhouettes on a 3D map of my apartment.
I’d been running it every night, just to see what it could detect. But last night, I couldn’t sleep. So I opened the radar map, and something caught my attention.
Three human silhouettes. Tracking people as they move through rooms. And even the ability to monitor a person's heart rate
I was scared by that third silhouette because I've been living with my girlfriend for a year now. I asked Claude about it, but he didn't say anything.
This technology has both helped and frightened people at the same time:
WiFi CSI measures how wireless signals change as people move through a space.
The basic motion detection logic:
csi = np.abs(wifi.get_csi())
motion = np.mean(np.abs(csi - baseline))
if motion > threshold:
radar.flag_activity()
Claude Code helped me build a 3D visualization around that concept.
→ CSI: 64 real-time motion signals.
→ Three.js: lifelike human figures and a 3D apartment.
→ Tracking: real steps, movement between rooms, and persistent identifiers.
→ Vital signs: breathing and heart rate readings.
And here's what's actually insane.
Researchers are already using real WiFi CSI to detect movement, estimate breathing, and explore contactless heart-rate monitoring.
My video shows just how insanely fast this tech is evolving. We're talking days, not months.
Today Claude Code builds a WiFi radar. Tomorrow it'll probably make my damn toaster cook breakfast at 9 AM lol.
Soon, your WiFi won't just connect your devices. It could actually sense what's happening inside your home.
And that third figure on my radar? Still have no clue who it was supposed to be...
So what do you think? Pretty sick innovation or a straight-up privacy nightmare?
Vector retweeted
Quantum Space 🚨 WiFi Yönlendiriciniz Sizi Görebilir mi? Claude Code ile Gerçek Zamanlı Radar Deneyi!
Bir geliştiricinin Claude Code kullanarak WiFi yönlendiricisini bir radara dönüştürmesi, kablosuz sinyallerin ev içindeki hareketleri nasıl takip edebileceğini gözler önüne serdi.
• **Sinyal Analizi:** Yalnızca 40 dakika içinde yazılan özel kod, WiFi sinyallerinin cisimler etrafındaki bükülmelerini okuyarak dairenin haritası üzerinde hareket eden figürlere dönüştürdü.
• **Şoke Eden Sonuç:** Gece saatlerinde test edilen sistemin haritada yatak odasında ayakta duran ve kapıya bakan bir insan figürü algılaması, teknolojinin sınırlarını ve potansiyel gizlilik risklerini bir kez daha tartışmaya açtı.
• **Dijital Mahremiyet:** Evimizdeki kablosuz ağ cihazlarının veri toplama ve çevreyi izleme kapasitesi dijital güvenlik açısından yeni soru işaretleri doğuruyor.
Vector retweeted
🚨Le pidio a Claude Code que convirtiera su router de WiFi en un radar
En 40 minutos escribió el código que lee como la señal de WiFi se dobla alrededor de los cuerpos y los dibuja como formas en movimiento sobre el mapa de su piso
Lo probo de noche y vive solo penso que era un bug entonces fue al dormitorio y la forma no se movio
El mapa la mostraba de pie junto a la cama mirando a la puerta entonces lo apago y aun no sabe que estaba leyendo el codigo
Guardalo
Readers added context they thought people might want to know
La detección de personas con señales WiFi es real como en el proyecto RuView. Requiere dispositivos adicionales como ESP32 para capturar los cambios en las ondas no solo código de Claude para un router común.
ru-view.com
ruview.pro/how-it-works
Vector retweeted
11 PEDESTRIANS. 6 VEHICLES. 1 TAXI. ONE CAMERA TRACKING EVERYTHING.
No one watching the monitor. No security team manually tracking every movement.
Just Claude Code turning ordinary street footage into a damn impressive AI traffic monitoring system.
And honestly, it handled the job better than I expected.
Watch the screen.
A pedestrian enters the crosswalk. Detected, assigned an ID, tracked.
A truck moves through the intersection. Classified.
A taxi appears among regular cars. Identified separately.
Every object gets tracked. Every movement generates data. And the dashboard updates as the scene changes.
33 objects tracked. 0 alerts. All from one camera.
Here's where Claude Code really impressed me.
Instead of spending days manually connecting detection models, tracking algorithms, and event logging, I used Claude Code to help bring the entire pipeline together.
The detection stage uses the same basic idea as this simplified YOLOX snippet:
frame = letterbox(frame, 640)
out = yoloх.run(None, {"images": frame})[0]
people = out[out[:, 4] * out[:, 5] > 0.12]
tracks = tracker.update(people)
Then the system connects several technologies:
→ OpenCV processes the video frames.
→ YOLO / YOLOX detects pedestrians and vehicles.
→ ByteTrack maintains tracking IDs across frames.
→ Python handles crosswalk zones, event logs, and alerts.
And that's the real achievement.
Claude Code didn't invent computer vision. It helped turn several complex technologies into one working system.
A regular CCTV camera records traffic.
This system converts that footage into structured data you can actually use.
And this is only one of my experiments.
I tested 7 ways Claude Code can interact with the real world, from CCTV monitoring to device diagnostics and security automation.
The complete breakdown, code examples, and experiments are in my article below.
AI coding agents aren't just writing code anymore. They're helping us build tools that interact with the world around us.
If you liked this, read my article. Lots more info like this there ↓
Vector retweeted
CLAUDE CODE BUILT A FAKE AIRPORT WIFI AND IT TOOK A PASSWORD IN 30 SECONDS
i wanted to see how easy it actually is. everyone connects to free wifi at airports, cafes and hotels without thinking. i do it too
i asked claude code to build a fake wifi login page. the kind you see everywhere. it wrote the whole thing in 3 minutes
then i put up a hotspot called "Guest_Network". same name as half the networks you've ever joined
here's what happened the second someone connected:
- a normal looking "Welcome to Our Wi-Fi" page popped up
- it asked for email and password to connect
- looked exactly like a real captive portal
- nothing on the phone looked off
i typed a test email and password. walked over to the laptop. claude code opened the admin panel
both were sitting right there in plain text:
- the email
- the password
- the exact timestamp
two people connected in under a minute. both entered real looking logins without a second thought
the scariest part is there's no warning. no popup, no lock icon telling you something is wrong. the page looks identical to the real one
this cost $0. a laptop and a few lines of code claude code wrote. no special hardware, no pineapple, no flipper. just a hotspot and a fake page
this is a demo i ran on my own devices, for educational purposes only
the point is simple. if i can do this in 3 minutes, so can the person sitting next to you at the gate
how to protect yourself is in the first reply. go through it tonight, takes 2 minutes
bookmark this and send it to anyone who connects to free wifi
Vector retweeted
i still don't get why people build a second brain for Claude Code from scratch
7 repos already did it. 75,000+ stars combined
1. obsidian-skills: 6 skills from the CEO of Obsidian. teaches Claude its formats and tools
github.com/kepano/obsidian-s…
2. claude-obsidian: drop text in inbox/, check the plan, get linked notes
github.com/AgriciDaniel/clau…
3. obsidian-second-brain: saves decisions and tasks, loads them back next session
github.com/eugeniughelbur/ob…
4. karpathy-llm-wiki: unofficial Karpathy-style wiki. ingest, query, lint
github.com/Astro-Han/karpath…
5. second-brain-os: starter vault with 18 skills and 72 commands
github.com/undefined-ui/seco…
6. ai-second-brain: turns your ChatGPT and Claude exports into linked notes. run only step 1 of the README
github.com/charlie947/ai-sec…
7. llm-wiki: rules load every session, wiki pages only when needed. skip its tip to keep secrets in memory
github.com/MehmetGoekce/llm-…
start with #1. it takes 2 commands:
/plugin marketplace add kepano/obsidian-skills
/plugin install obsidian@obsidian-skills
all 7 run on plain markdown. you can open every file in any editor
full guide in the article below
Vector retweeted
🚨Attention. Two phone stories hit your feed this month. One changed its numbers three times. The other has Apple’s own patch notes behind it.
The photo story: versions of it claim 145,763 files, then 147,863, then 152,417. Apps with access went from 23 to 19. The video shows a terminal listing and a blurred grid.
The jailbreak story: Calif, a small firm, rebooted an iPhone 18 Pro on a stage in Paris and opened a root shell. No computer attached. Calif has published no tool and no technical details. Apple’s iOS 27.2 then patched 163 flaws. Six credit Calif. Anthropic Research is credited on three, OpenAI on four.
The AI timeline is in my article. April 25: the first kernel bug. May 1: a working chain past Apple’s Memory Integrity Enforcement, a shield Apple spent about 5 years building. Under a week. Humans still had to beat it. Nobody has confirmed AI built the October chain.
Apple pays up to $2,000,000 for a zero-click chain. Over $5,000,000 with bonuses. It has paid $35,000,000 to 800+ researchers. Faster bug finding means more patches, and more money at stake.
Inside: confirmed vs noise, a correction on my own photo post, a 10 minute check and four prompts that never open your photos.
The full article is below. Almost nobody reads past the headline.
Vector retweeted
A $5 CABLE + CLAUDE CODE ( FREE VERSION ). YOUR CAR JUST GOT HACKED. NO CAP.
This guy plugged a cheap OBD2 adapter into his dad's car and gave Claude Code one job:
"Figure out how to talk to this car and build me a live dashboard."
5 minutes later, things got pretty damn interesting.
Real engine data. Live temperatures. Diagnostic readings. All flowing into an app Claude helped build from scratch.
Here's what was actually happening under the hood.
Claude wasn't just drawing some fancy dashboard. It had to figure out how to communicate with a real car.
And the tech behind it is surprisingly simple:
→ ELM327 + OBD-II: A cheap adapter connects the laptop to the car's diagnostic interface, giving access to supported ECU data.
→ SAE J1979: Commands like 010C request engine RPM, 0105 reads coolant temperature, and 010D checks vehicle speed.
→ Python + python-OBD: Sends diagnostic queries, reads sensor values and converts raw responses into actual measurements.
→ pySerial: Handles communication with compatible adapters, including connection errors and timeouts.
→ Claude Code: Helps write the connection logic, fix broken scripts and turn incoming vehicle data into a working application.
→ HTML + CSS + JavaScript: Can transform those numbers into live gauges, temperature indicators and a custom dashboard.
→ DTC diagnostics: Reads supported fault codes so you can understand what that annoying check-engine light is complaining about.
And here's the funny part.
You don't need 500 lines of code just to ask your engine what it's doing.
A basic read-only query looks like this:
```python
import obd
car = obd.OBD()
rpm = car.query(obd.commands.RPM)
temp = car.query(obd.commands.COOLANT_TEMP)
print(rpm.value, temp.value)
```
A few lines of Python. Real engine data.
The dashboard shows 69°C coolant temperature, battery voltage and diagnostic status.
And the cool part? Claude can customize everything.
Racing-style RPM gauges? Done.
Engine fault explanations? Easy.
A full Knight Rider-style dashboard? Hell yeah, lol.
But here's the twist.
He didn't bypass the car's security. He made it communicate with custom AI-built software.
5 minutes. One prompt. A $5 cable.
Next time your check-engine light comes on, imagine opening your own diagnostic app instead of guessing what's wrong.
Authored by @Vectorxeth
Vector retweeted
Claude Code found spyware on my wife's phone. It had tracked her for 14 weeks and logged 9,408 places she had been…
She thought she was just being paranoid, but someone really did know where she went every single day, down to the minute.
Every 90 seconds, even with the screen off, her location went out to a single number.
I plugged her iPhone into my MacBook and asked Claude Code what was running that she never installed. It flagged an app called "Device Sync" with no icon, which had come in with a free "Wi-Fi Booster" she installed in August and forgot about.
Then it traced where all of this was going. The phone on the other end had been 2 miles from our house the whole time:
reports to → +1 (312) *** **19
carrier → Verizon
device id → IMEI 35 ********** 82
receiver last seen → 2.1 mi from our home
last ping it sent → 41.8**, -87.6** · 1 min ago
When she started feeling watched 2 weeks ago, she turned off location for every app, but this one kept sending it anyway. My guess is it found her through the Wi-Fi networks around her.
Claude wiped the app on its own, and we passed everything it had recorded to the people who handle this. Who was on the other end, I don't know yet.
I had no idea an app could follow someone like this without ever asking permission. If you want to check yours, plug your iPhone into a Mac, tap "Trust" and ask Claude Code which apps send data in the background and to whom.
The 5 steps and the exact prompt I used are in the comments. Save this and check the phones in your family tonight.
Vector retweeted
Your TV is watching what you watch.
Then it sells the list.
Someone got sick of it and handed their TV to Claude Opus 5.5.
Not to delete a few apps.
To reverse-engineer it.
Claude connected over adb and pulled the stock launcher apart.
Decompiled the APK.
Read through the code nobody was supposed to read.
It found where the ads come from.
The services that phone home.
The "recommended" rows, wired straight to an ad server.
Then it shut them down, one by one.
And when the old home screen was gone, it wrote a new one from scratch.
A Mac-style dock. Netflix, YouTube, Spotify, PlayStation.
Weather. Calendar. Music on the wall.
No ads. No tracking. Nothing it didn't ask for.
The TV manufacturer spent years building that system.
Claude took it apart in an afternoon.
Watch ↓
Vector retweeted
Claude Code just caught a scammer trying to take my account before I opened the link
The message said my account would be suspended tonight unless I verified it immediately. One sentence, one link, and a deadline designed to make me stop thinking.
I wanted to find out what was behind it. More than that, I wanted to know whether Claude Code could tell me who sent it.
So I saved the message and the available evidence, opened Claude Code, and gave it one rule: investigate the link without entering credentials or submitting anything to the page.
The first thing it did was pull the address apart. Then it checked the saved DNS and certificate records, traced the redirects and read the final page’s HTML.
The code kept moving. The evidence started lining up.
→ The message threatened to suspend my account
→ “Verify now” pushed me to act before checking
→ The link passed through two redirects
→ The final page asked for my password
→ Then it asked for a one-time code
That last part changed how I looked at the message. It wasn’t just trying to learn my password. The form wanted the second piece of information I’d need to approve a login.
Claude Code also checked whether the domain, DNS record and certificate referred to the same host. They did. That sounds reassuring until you realize a scam page can have a working certificate too. A secure connection tells you how your browser talks to a site. It doesn’t tell you whether you should trust the person running it.
Then Claude Code indexed the five evidence files and recorded their hashes. The message, the redirect record, the page source and the other saved records were tied together in one report. If I reported the link, I could show what led to the conclusion instead of sending a screenshot and saying, “This looks fake.”
I was waiting for the dramatic part: a name, an address, the person behind the page.
That wasn’t what the report said.
It showed a hosting address and registration details, but it could not verify the operator’s identity. The server location wasn’t the sender’s location. The registration record wasn’t proof of who built the page.
Claude Code had caught the attempted credential grab. It hadn’t magically unmasked a stranger.
Honestly, that made the report more useful. It separated the things the evidence showed from the answer I wanted it to give me.
The scam didn’t depend on being technically complicated. It depended on me believing the deadline, following the redirects and typing both my password and one-time code into a page I reached through a message.
If you get an account warning like this, don’t use its link to check. Open the real app yourself. Keep the message, and if you investigate it with Claude Code, ask it to show its evidence and say clearly what it cannot establish.
I’ll put the prompt in the first reply.
Vector retweeted
Claude Code found my mom's Gmail still open on a print shop computer for 8 months. With all 63 of her saved passwords synced to it.
She printed one plane ticket there in March. She didn't just log in. She logged into Chrome.
I sat down with her phone, took screenshots of her Google device list and our router's connected devices page, and had Claude Code go through them. Read-only.
What it pulled:
device → Windows, Chrome
place → the print shop by the train station
signed in → since March
last active → 3 days ago
chrome sync → ON
saved passwords → 63, bank included
drive → a scan of her passport from 2021
When you sign into Chrome on someone else's computer, it asks to turn on sync. She tapped yes, because it always asks and you always tap yes. That copied every password she ever saved onto a computer anyone in that shop can sit at. Nobody hacked anything. They just had to open Settings.
The second one was worse:
router → the one the provider installed in 2019
wi-fi password → still the one on the sticker
connected → 19 devices
recognized → 15
the other 4 → no names, online every night
top one last month → 41 GB through our internet
The sticker is on the back of the router. The router sits in our hallway. Every guest, every repairman, every friend who ever asked "what's the Wi-Fi?" has seen it.
What we did that night:
→ signed out the print shop computer (Google app → her profile picture → Manage your Google Account → Security → Your devices)
→ changed her Google password, then every password that was in that Chrome
→ turned on 2-step verification and checked Recent security activity for anything she didn't do
→ changed the Wi-Fi password and the router admin password, which was also still default
→ made a separate guest network for visitors
My mom said next time she'll print at home. We don't have a printer.
The prompt I used, paste it into Claude Code with the screenshots in the folder:
"I'm checking my own family's accounts. Read-only. From these screenshots of the Google device list, recent security activity and our router's connected devices page, list every device signed into her account with its last-active date and place, whether Chrome sync is on for any device that isn't hers, every device on our Wi-Fi we can't match to someone in the family, and whether the Wi-Fi and router passwords look like factory defaults. Then give me the fixes in order."
Run it on every account in your house. Bookmark this before you forget which print shop still has your passwords.
Vector retweeted
I just canceled my $199 / year WHOOP subscription, and…
reverse-engineered their entire app for my Apple Watch with Opus 5.5 in 2 hours, then i made it open-source:
→ github.com/0xCodez/pulsr
recovery. strain. sleep. one beating orb. free and open-source.
what it does:
→ Recovery 0–100% from your overnight HRV, resting heart rate and sleep
→ Strain 0-21 with a daily target based on your recovery
→ how much sleep you need tonight + a recommended bedtime
→ stress monitor, health monitor and a “body age” estimate
→ a journal that shows which habits help or hurt your recovery
→ an AI coach that runs on-device. no API key
→ an Apple Watch app, light and dark mode
→ no subscription, no account. your data never leaves your iPhone
Find full prompt below ↓
Then, read how to rebuild any app from scratch with Opus 5.5 in the article below.