127.0.0.1

@InsiderWire Well, here comes a new skill unlocked clawhub.ai/2eux/prod-shie…

@Cristiano Alhamdulillah

The entire team at DC Cakung is truly delighted to see this, human effort triumphs once again

UPDATED: What's new in v1.2.0 Summary: Adds software supply chain and secrets safety checks, with expanded coverage for installs, upgrades, and untrusted code execution. Added supply chain security: triggers on dependency installs, container builds, CI/CD runs, and many more

@startupideaspod x.com/i/status/20553…

@startupideaspod Bro, explain token limits to him, we hit that limit faster than our roadmap

Boris Cherny, the creator of Claude Code, shared his entire setup. He runs 5-10 Claudes in parallel. Half his coding happens from his phone. Here's his 3-part formula for better results: Use the smartest model available — Counterintuitive: it's actually cheaper — Smarter model = fewer tokens = lower total cost — "Once the plan is good, the code is good" Invest in your Claude MD — Plain text file. No special format. — Whole team contributes multiple times a week — Every mistake Claude makes gets added so it never happens again Give Claude a way to verify its own output — Let it run the code. Let it see the browser. — "Imagine you're a painter wearing a blindfold" — Same thing for an AI that can never check its work His morning routine: wake up, kick off 3 sessions from his phone, check in later. His workflow: start in plan mode → lock the plan → auto-accept edits → done. No fancy setup. No complex tooling. Just multiple Claudes, a good plan, and a shared knowledge base.

@val__greg Absolutely true, not claiming Rust/Go are magically secure, no ecosystem is immune to supply-chain attacks, including Cargo or Go modules. it's more about reducing complexity and dependency sprawl, with smaller dependency fewer packages, especially what happened to Nginx, Next.js

@2eux rust and go have smaller dependency surface but they're not immune, cargo supply chain attacks have happened just less often. switching language reduces familiarity with the attack vector more than it reduces the structural risk

The next generation of serious apps won’t be built on massive JS dependency chains. Too much surface area. Too many supply-chain attacks. Too many malicious npm hijacks. That’s why I’m building with: • Rust • Dioxus • GoFiber • PostgreSQL • Redis • Convex

@Jacobsklug @Lovable Build

After shipping 250+ apps and making $3M+ with AI, I built a course for @lovable apps—and I'm giving it away. In the past two years, we cracked the code to building apps with AI. Refining our process as the tools got better. I've distilled everything into this single document. Comment "Build" and drop a follow. I'll DM it to you. P.S. This will likely blow up, so give me some time to reply.

@InsiderWire "Because production only gets one chance."

@InsiderWire ProdShield governs how Claude executes actions against real systems. Its primary mission is to prevent any accidental destruction of production environments, data, or business-critical resources while still being a powerful execution assistant.

#BREAKING: Anthropic’s AI coding agent ‘Claude’ reportedly wiped a company’s production database and backups in 9 seconds.

@InsiderWire Well, here comes a new skill unlocked clawhub.ai/2eux/prod-shie…

Ini Ibam, bicara sendiri agar Ririe terlindungi. Betul, ketika belum jadi tersangka, saya dapat ancaman: buat pernyataan "mengarah ke atas" kalau tidak kasusnya "akan diperluas". Saya tolak, ngga mau bohong & zalim. Tiga minggu kemudian, saya jadi tersangka. Saya tolak bukan untuk lindungi Nadiem, tapi karena memang ngga pernah ada arahan dari Nadiem ke saya agar pengadaannya jadi Chromebook semua. Seperti yang terungkap dari 22x sidang, tidak ada sama sekali arahan dari atas seperti itu. Saya hanya diminta memberi masukan netral dan objektif sebagai konsultan. Artinya, ketika menerima ancaman tersebut saya dihadapkan ke dua pilihan: Berbohong mengarang cerita menuduh orang lain untuk menyelamatkan diri sendiri. Atau, berpegang kepada integritas, kejujuran, dan kebenaran yang saya yakini, dan menolak untuk berbohong. Dengan shalat istikharah dan kesadaran penuh akan risikonya, saya memilih jalan yang kedua: kejujuran. Insya Allah selalu berpegang pada kejujuran akan berujung pada kebaikan untuk saya, Ririe, dan keluarga kecil kami. Kalau tidak di dunia, maka di akhirat kelak. Lalu jawabannya apa ketika saya menolak untuk berbohong? "Oke, kami perluas.” Saya tidak berdaya. Ya Allah, apa lagi yang bisa kami lakukan ketika dihadapkan pada pilihan seperti itu? Pegangan kami hanya prinsip integritas dan kejujuran. Ketika konsekuensinya beberapa minggu kemudian saya dinyatakan tersangka, kami hanya bisa memperbanyak istighfar dan ikhtiar. Kami jalani dan hormati proses hukum yang ada dengan tabah, kami berniat jelaskan di persidangan fakta-fakta yang membuat terang, kami masih percaya dengan hukum Indonesia. Mungkin ngga banyak yang tahu, tapi Ririe istri saya adalah seorang sarjana dan magister hukum. Di Belanda dulu kami banting tulang nabung dan berhemat banyak, supaya bisa bayar uang kuliah S2 Ririe. Dari Ririe, saya belajar banyak tentang hukum Indonesia, apa saja yang mungkin terjadi, dan bagaimana hukum kita tetap memungkinkan pembelaan yang efektif. Baik, mari berjuang di persidangan, luruskan seluruh tuduhan. Satu persatu fakta di persidangan muncul dengan terang benderang, satu persatu tuduhan bisa kami bantah. Sampai akhir rangkaian sidang, 57 orang saksi dihadirkan, tidak ada bukti saya menerima keuntungan dari perkara ini, tidak ada bukti masukan saya karena konflik kepentingan, tidak ada bukti saya mengarahkan. Yang terungkap malah saya sebagai konsultan sudah menyarankan Chromebook diuji dulu, pejabat menolak pengujian dan memutus Chromebook, nama saya dicatut di SK, masukan saya dipelintir. Kami merasa pembelaan hukum kami sudah maksimal, kebenaran sudah terungkap, tinggal menumpu harapan pada keadilan dan kebijaksanaan dari majelis hakim yang mulia, yang kami merasa sudah sangat objektif dan penuh kearifan sepanjang persidangan. Namun, ketika JPU menyebutkan tuntutan 15 tahun penjara, denda Rp1 miliar, uang pengganti Rp16,9 miliar subsider 7,5 tahun penjara tambahan... Ini titik kezaliman yang sangat terang benderang, tekanan kepentingan yang sangat kentara, saya memutuskan pembelaan saya tidak lagi bisa hanya di persidangan. Besok saya akan sidang pembelaan (pleidoi) dan kami bersurat kepada Presiden @prabowo Subianto serta @KomisiIII DPR, untuk memohon perlindungan hukum dari kriminalisasi, ketidakadilan, intimidasi, serta pengkambinghitaman yang sudah sekentara ini. Kami takut untuk bicara? Takut ada intimidasi lain? Itu risiko yang jelas, tapi kami tidak gentar. Tuntutan 22,5 tahun dan belasan miliar yang tidak mampu kami bayar mungkin dianggap akan membuat kami terdiam, tapi kami malah semakin berani untuk melawan kriminalisasi ini. Mohon bantuan, dukungan, dan perlindungannya dari masyarakat Indonesia, dari pekerja kreatif dan pekerja pengetahuan, serta dari semua yang ingin bantu negara atau takut dizalimi negara. Kami berjuang bukan untuk kami sendiri, tapi agar tidak ada lagi kriminalisasi dan ketakutan bagi mereka yang tulus mau bantu Indonesia. Kami masih percaya Indonesia bisa menjaga dan menghadirkan keadilan dalam kasus kami.

@SoftWarNews Menarik jika photo ini valid, untuk liat OS yang digunakan Desktop dan Tablet nya

Media Iran melaporkan bahwa pilot AS ditemukan oleh warga sipil Iran di sebuah gua di Iran selatan. Mereka menipunya dengan membuatnya percaya bahwa ia akan diserahkan kepada pasukan AS, tetapi sebaliknya, ia diserahkan kepada intelijen Korps Garda Revolusi Iran.

@TechWith_Nova OpenClaw

My OpenClaw bot builds websites & mails a postcard with a QR link to local businesses on autopilot... You can use it to land new customers without a single cold call, here's how it works: - Finds 100s of local businesses via Google Maps - Builds each one a custom website in minutes - Prints a real postcard with their site preview + QR code - Mails it directly to their door - They scan it, see their site, and reach out - Runs 24/7 completely hands off Direct mail gets a much higher response rate than cold email. Reply "OpenClaw" and I'll send you the full breakdown of how you can do it too (must be following so I can DM)

@AiwithTyler @hasan28d Page

@ziwenxu_ @ASolovichh Would they get stressed if you made their office smaller?

@ASolovichh Full Inspiration haha x.com/ziwenxu_/statu…

The OpenClaw Control Panel is finally coming to life. 🦞 - Real-time agent logs - Automated cron jobs - Live AI Agent Office (yes, they have a breakroom) - Kanban board that OpenClaw can access and update Everything you need to orchestrate an autonomous team in one view. Full demo video drops tomorrow. Want in? Comment "OpenClaw" for early access!

@lukepierceops INFRA

I found a way to sell AI infrastructure to companies doing $2M-$50M/year. ALL with no sales team, enterprise connections or cold calls. Businesses are desperate for Ai implementation right now and anyone can do this. But most people get it wrong and that's why they fail. They lead with tools, ex) "we build automations" or "we integrate AI." That means nothing to a CEO managing 40 people and $5M in revenue. They pitch features instead of showing the cost of doing nothing. And they price hourly, so the buyer treats them like a freelancer instead of a partner. Mid-market and enterprise companies are bleeding $100K-$500K/year on broken processes, bloated SaaS stacks, and manual work they don't even realize they're paying for. They WANT to buy AI infrastructure, they just don't trust most people selling it. Because most people selling it sound like every other agency. I created a guide breaking down exactly: → How to position AI infrastructure so executives actually listen → The discovery framework that turns a 30-min call into a $25K-$100K project → How to calculate ROI so the price sells itself → The 3-pillar strategy process that closes 60%+ of qualified prospects → Why "sell the map before you sell the build" changes everything RT + reply "INFRA" and I'll send you the FULL guide (must follow so I can DM)

@malekoo @hayatveren_de @awnihannun @ActuallyIsaak Hmm.. couldn't agree more. Looking forward to seeing the results

@hayatveren_de @awnihannun @ActuallyIsaak It's not about tokens per second. It's about ownership, privacy, and running research on your own terms. Finetuning, training, full control over the stack. No API dependency, no rate limits, no one else's terms of service. Different goals, different infrastructure.

Two Mac Studios just landed. M3 Ultra. 512GB unified memory per machine. The AI lab is getting serious. Running the biggest models locally. No cloud, no compromise. Developing in MLX, built for Apple Silicon from the ground up. Shoutout to @awnihannun @ActuallyIsaak and the MLX community for building an incredible foundation. We'll be building on it.

@Jacobsklug @openclaw @Lovable OS

I'm giving away my entire @openclaw architecture. Behind my $250k/month agency. After weeks of building, I've dialled in the exact system that runs my business 24/7. What's included: • Memory folder structure (how to organize agent context) • Cron job templates (daily briefs, meeting syncs, content automation) • How to build a custom dashboard in @lovable • API reference doc (so your agent never forgets its tools) • Voice training method (85 posts to teach it your style) • Supabase schema for dashboard connection Comment "OS" and follow. I'll DM it to you. P.S. This will probably blow up so give me some time to reply.