Full Claude Course
Master Claude to automate repetitive tasks, build apps without coding, create real portfolio projects, and become more valuable at work.
REA + Opus 5.5 is f*cking dangerous…
I'm honestly not sure this should be public.
10 repos that let an AI agent take apart any app like a mechanic takes apart an engine.
send to your Claude:
•REA (171K stars) - one MCP for RE: binaries, Electron, .NET, Android, websites.
https://t.co/78k8zO6CUv
• Chrome DevTools MCP (53K stars) - agent drives a live Chrome: network, console, JS. Maps how any web app works.
https://t.co/UkGUljY31y
• JADX (50K stars) - Android Dex → Java decompiler. GUI + CLI.
https://t.co/E4Yg0NKeQN
• x64dbg (49K stars) - Windows debugger built for RE and malware analysis.
https://t.co/D4fskuXqhJ
• Apktool (26K stars) - unpacks and rebuilds APKs: manifest, resources, smali.
https://t.co/G73AUG7ksa
• radare2 (25K stars) - UNIX-style RE toolkit. Has its own MCP server (r2mcp).
https://t.co/24bk7a5KFH
• Cutter (20K stars) - free GUI RE platform powered by rizin.
https://t.co/hWe7zluGbr
• IDA Pro MCP (12K stars) - connects IDA Pro to your agent over MCP.
https://t.co/iczdt4gexk
• dnSpy (11K stars) - .NET debugger + assembly editor. Patch and rerun.
https://t.co/5VMhkWlxSS
• angr (9K stars) - Python binary analysis. Symbolic execution finds hidden paths.
https://t.co/GNA0rXyuu7
Drop this into your Claude, then watch Opus 5.5 take apart any app you own below.
This is the most DANGEROUS thing on the internet right now
143k stars in 2 days and that says it all
REA (Reverse Engineer Anything) this open-source MCP lets your AI agent deconstruct any app, all the way down to machine code
I unlocked TradingView's full feature set using REA and got FREE access to their premium indicators. The software is ready to go
How it works:
1. Direct REA to TradingView’s public web application to map out all core functionalities, including chart controls, technical indicators, and alert mechanisms
2. Observe and document system behavior when modifying symbols, adjusting timeframes, overlaying indicators, plotting chart levels, or saving custom dashboard layouts
3. Leverage REA’s suite of MCP tools to inspect accessible software artifacts and map underlying application workflows based on concrete evidence
4. Supply these technical insights to Claude Opus 5.5 to produce a comprehensive specification and an actionable implementation roadmap
5. Engineer an independent charting platform complete with live market feeds, candlestick rendering, technical analysis tools, drawing features, and saved watchlists
6. Integrate a quantitative strategy engine capable of backtesting against historical market data while accounting for trading fees, price slippage, and maximum drawdowns
7. Systematically test every subsystem against real-world and benchmarked behaviors, resolving bugs iteratively until the platform operates seamlessly
8. Deliver a fully custom, end-to-end TradingView-inspired quantitative research workstation built on fully owned, extensible source code
This is worth a shot
𝐈𝐍𝐃𝐎𝐍𝐄𝐒𝐈𝐀 𝐀𝐑𝐄 𝐈𝐍𝐓𝐎 𝐓𝐇𝐄 𝐀𝐒𝐄𝐀𝐍 𝐂𝐔𝐏 𝐅𝐈𝐍𝐀𝐋 𝐀𝐅𝐓𝐄𝐑 𝐀 𝐑𝐈𝐃𝐈𝐂𝐔𝐋𝐎𝐔𝐒 𝐄𝐍𝐃 🤯🇮🇩
Indonesia needed two more goals after conceding in the 90+1'... And they scored them in the 90+6' and 90+7'! 🫨🫨🫨
𝗪𝗛𝗔𝗧 𝗔 𝗖𝗥𝗔𝗭𝗬 𝗘𝗡𝗗! 🤯
Mitchell Lee Baker with 𝗙𝗜𝗩𝗘 𝗚𝗢𝗔𝗟𝗦!😳⚽⚽⚽⚽⚽
Indonesia will now play in the final on October 5 against what will most likely be Thailand. 👀🏆
Fuck dropshipping, Fuck claude code, Fuck building AI startups
it's all for poors
The easiest way to print $30k/mo with AI in 2026 is running a fake old lady on tiktok who sells vitamins to women in their 60s....
99% of you won't do it because it's too embarrassing to admit
Total tool stack to operate one of them: $300/mo
ChatGPT $200 (automation using Dots)
Higgsfield $15 (AI avatar)
ManyChat $15 (the DM funnel)
Gumroad FREE
That's the entire infrastructure for a business that does $30-50k/mo
Move 1. Build the character in Higgsfield.
Pick a real older woman archetype. Chinese grandmother for cooking. Asian monk for wellness. Latin abuela for natural remedies.
Move 2. Run the 14-day warming sequence.
Don't post AI videos on day 1. Browse for 3 days. Comment for 4 days. Post 8 normal videos for 7 days. Day 14 start the real content.
Skip this and you get shadow-banned in week 3
Move 3. Pick 5 starter products.
Filter to women 38-65 categories: kitchen, home, beauty, supplements. Skip products with under 50 sales/week. Pick winners with 4+ stars and 3+ creators making sales
Move 4. Write the 18-second BOF script.
Hook line ("if you're over 50 and your knees crack, this is for you"). Demonstration with one specific number. CTA referencing the yellow basket icon. Product visible from second one
Move 5. Automate posting 6 videos a day.
Most will flop. By video 100 you'll have 1-2 winners pulling 200k-500k views. Duplicate the winners 30x. Don't tweak.
Move 6. Set up a manychat trigger before day 1.
Trigger keyword tied to a 4-message DM flow ending in your tiktok shop affiliate link. 31-41% click-through rate vs email at 4%.
Adds $200-800/mo per page on autopilot
Month 2 you'll cross $3-5k. Month 3 you'll cross $10-15k. Month 6 you should be at $30-50k from one page. Month 9 at 2-3 pages
The math nobody talks about
Dropshipping requires inventory, supplier negotiations, ad spend, returns, customer service. Average margin 4-12%. Average operator burnout: 14 months
Coding with claude requires you to learn how software works, get a job at a tech company that may not exist in 4 years, work 50+ hours/week for $120-180k. Average path to $30k/mo: 7-10 years
Building an AI SaaS requires you to compete with VC-funded teams, scale to product-market fit, fundraise, hire engineers. 90% die in 18 months
Running a fake AI grandmother requires $300/mo in tools and the willingness to look stupid. Average path to $30k/mo: 6 months. Average margin: 95%
They don't eat. They don't sleep. They don't quit. They don't get hangovers. They don't go through breakups. They don't ask for raises. They don't ghost me on monday morning
They post 6 times a day for 30 straight days.
I broke down how to build the whole system with OpenAI Dots + GPT-6.1 Sol here:
Após a conferência de imprensa do Selecionador Nacional, e no seguimento de uma conversa com o Presidente da Federação Portuguesa de Futebol, tomei a decisão de deixar o estágio da Seleção Nacional.
A seu tempo, direi a verdade a todos os Portugueses sobre as razões que motivaram a minha saída da equipa nacional, à qual sempre me dediquei.
Agora é tempo de desejar boa sorte a Portugal e a todos os meus companheiros de equipa, sem exceção.
Lo que este tipo subió a GitHub no debería ser gratis.
Una app que convierte tu móvil en un detector de vigilancia.
Escucha las señales Wi-Fi y Bluetooth a tu alrededor y te dice qué hay cerca:
• rastreadores escondidos
• cámaras corporales de policía
• drones, y dónde está el piloto
• gafas inteligentes de Meta grabando
• micrófonos de detección de disparos
Reconoce hasta 242 tipos de dispositivos. Y te avisa si alguno se mueve contigo.
Sin cuenta. Sin servidor. Sin internet. Código abierto.
- PewDiePie trying to distill GPT-Sol
- OpenAI ban his account
- OpenAI trained on the open web.
- PewDiePie tried to trained from the model’s answers.
- Same idea, opposite consequences.
- PewDiePie says OpenAI banned him twice while he was building a local model.
- PewDiePie’s latest project is a reminder of who actually owns the pipeline.
- They spent years absorbing public data.
- He spent weeks trying to improve a small local model.
- If distillation is theft, what do we call the original training run?
- “why do we pay for the model?
Malaysia topped their group in the ASEAN Cup by beating Singapore 6-0. They started celebrating thinking they had qualified for the final. BUT...
In the other match, Indonesia scored another 2 goals in last 3 mins to beat Bangladesh 9-2 and ended up knocking them out on goals scored!
En lugar de ver Netflix este domingo, dedica 1 hora a esto.
Un CURSO COMPLETO de Claude que te enseña a automatizar lo que te roba 3 horas al día.
El lunes lo agradecerás.
this is f**king insane
I cancelled my $200/mo Claude for this
GPT-6 Luna is basically free and someone figured out how to never hit limits on Codex
[it takes 4 mins to set up, here is how]
1. open Codex settings
2. paste the config below
3. never hit a usage limit again
save this and paste it into Codex now.
Teman2 yang lagi cari rumah di Jabodetabek, bisa cek web buatan tim jurnalisme data @hariankompas ini. Di web ini ada data 37 ribu rumah, lengkap dengan lokasi, luas, harga, dan jarak ke pusat kota. Bisa filter berdasar penghasilan juga 😃
Cek di sini: https://t.co/wqQRkKNvKm
@harisfirdaus@hrdbacot@hariankompas Hi, ijin nimbrung, barangkali ada yg mau nitip jual/sewa/KPR propertinya, saya bisa bantu pasarkan melalui platform Next Level Properti kami yang sudah tersebar 17 cabang di seluruh Indonesia & saat ini sdh ada 6000 data listing. Bisa kontak saya melalui https://t.co/7sp8l2qpZE
Valid.
Spill ah biar fokus ngulik beginian drpd ngurusin hal2 g penting kaya kehidupan personal artis wk (JK, bebasin aja guys):
Gue pake ai agent buat scanning lowongan kerja remote yang tidak di posting di linkedin job portal atau job portal umum lainnya. Dipersonalized scanningnya/requirementsnya berdasarkan kekuatan cv gue skrg.
Hasilnya gue dapet full time role as tech sales enterprise, dari company enterprise US yang udah listing di NASDAQ, dan bisa remote atau onsite relocation ke kantor Singapore.
Clerical job atau ngurusin admin mah automate aja guys. Kalo nyari manual, boro2 ada waktu buat nyari lowker yg oke di company website. Kalo muncul di linkedin mah bisa tau, lah ini company's personal web wkwk.
Wait… kalian serius masih cari kerja manual??? 😭
You can literally ask Claude/Cowork to apply for jobs every single day on your behalf. Fully automated.
Pake Computer Use, AI bisa control PC/browser kalian buat:
> cari lowongan yang relevan
> filter job sesuai profile kalian
> customize CV untuk tiap posisi
> bikin cover letter yang spesifik buat tiap company
> isi application form
> bahkan reach out recruiter via LinkedIn buat follow-up
Basically, daripada kalian habisin berjam-jam tiap hari buka LinkedIn, copy-paste data yang sama, edit CV, terus apply satu-satu… suruh AI yang kerjain grunt work-nya.
My brother in Christ, job hunting is already a numbers game. A huge percentage of job postings are either outdated, insanely competitive, or never going to respond to you anyway. Most of your applications will probably get rejected or ghosted.
So why are you still doing the repetitive part manually?
Let AI do the applying. You focus on the part that actually needs you: showing up when the interview invitation hits your inbox.
Asli coba set up ini. Minta dia apply 20 job per day, nanti lo kaget tiba2 dapet undangan interview di email wkwk
Sharing lagi ah mumpung Q3 gue lagi dikasih rejeki overachieve KPI wkwkw.
Guys, buat yang pengen tembus remote full-time jobs dengan gaji double digit gede, atau kerja di company global yang bayarannya lumayan dekat ke real standard USD rate, jangan cuma fokus cari keyword:
“remote jobs Indonesia”
Salah satu cara yang gue pake justru scanning company signal.
Contohnya kayak post Anthropic ini,
Gue gak bahas Anthropic-nya ya wkwkw, itu mah udah top global banget. 🤣
Yang gue maksud adalah pattern-nya.
Kalau ada company US / Europe / Australia yang mulai buka office di Singapore, expand ke APAC, atau mulai hiring orang di SEA, itu biasanya jadi signal menarik buat mulai kita pantengin.
Karena bisa aja beberapa bulan berikutnya mereka mulai hire untuk SG, Indonesia, Malaysia, atau bahkan buka remote role khusus APAC.
Ini bisa remote atau bisa relocate yaa yg mau onsite/hybrid di SG gue pake jalur beginian.
Lanjut 👇