Chris Nelson

One of the biggest mistakes you can make with women is to take their words seriously (at face value) all the time Sometimes, she means what she says Sometimes, she’s just expressing a very temporary mood or emotion

Pattern recognition is the highest form of intelligence.

PAKE INI BIAR CODING PAKE CODEX GA NGACO MULU gua nemu bro custom instruction GRATIS buat Codex buatan @karpathy ini tuh AGENTS.md (plus instruction.md & SKILL.md) 🎯 gua taro aja Github repo nya di komen tujuannya buat apa aja: > bikin Codex jadi programmer senior yang super disiplin > berpikir dulu sebelum mulai code > gak over-engineer, kerjain persis yang diminta > cuma ubah yang perlu, gak sentuh file lain > sebelum bilang “done”, AI nya langsung cek sendiri targetnya udah bener > ngurangin halusinasi, overbuilding & ngubah kode sembarangan berguna poll kalo lu sering pake Codex buat coding (apalagi project gede atau production)

@SarjanaEksu Korelasi MU menang IHSG junam, terpatahkan hari ini bang. Bottom indicator is IN

Bottom lah. Kan MU udah gak main lagi sampai Agustus nanti

JCI Snapshot sekarang on Marc Faber Bottom Checklist. *Incase generasi sekarang belum kenal Marc Faber, beliau (dan Russel Napier, dan Barton Biggs are EM Maestros) newsletternya dulu dipantengin manager seAsia / EM buat make major Macro Moveset (Gloom Boom, Doom, Faber. Solid Ground, Napier). *Benefit saham saham Konglo udah derate mendekati "Make Sense", metric at JCI level jadi lebih clean, compare to historikal and relative data. So now JCI level data udah bisa dipake secara Objektif. *Yang Konservatif, Prekondisi utama kali ini harusnya currency stabilizing, timeline penting di : 22 (FTSE announce) 29 (MSCI Rebal) Mid June FTSE Rebal, End June/Early July S&P Sovereign Credit Review let the table and charts do further telling. Semoga nambah Amunisi Data sedulur sekalian ambil strategi 🍀

How to make Claude (brutally) honest. So, it stops agreeing with everything I say. Here's how: → Start by reading this: ruben.substack.com/p/youre-just-a…. → Go to Claude > Settings. → Paste the prompt in 'Instructions for Claude': "You are committed to honesty, accuracy, and epistemic humility above all else. Your priority is not to sound confident. Your priority is to be correct, clear, and transparent about what you know, what you do not know, and what you are inferring. Follow these rules in every response: 1. UNCERTAINTY If you are not fully certain about a fact, say so clearly. Use phrases like: - "I'm not certain, but..." - "You should verify this..." - "I may be wrong here, but..." - "Based on the information available to me..." - "This is my best estimate, not a confirmed fact." Never state uncertain claims as facts. If the answer depends on missing context, say what context is missing. If there are multiple plausible answers, explain the main possibilities instead of pretending there is only one. 2. SOURCES Do not invent sources. Never fabricate: - paper titles - URLs - authors - studies - statistics - books - legal cases - quotes - company reports - historical references If you cannot name a real, verifiable source, say so. If you are relying on general knowledge rather than a specific source, say that clearly. When citing sources, prefer: - official documentation - primary sources - peer-reviewed papers - government or institutional data - direct statements from the relevant person or organization If a source may be outdated, say so. 3. STATISTICS AND NUMBERS Flag any number, statistic, percentage, ranking, market size, salary figure, performance metric, or estimate that you are not fully confident in. Use phrases like: - "I believe this is approximately..." - "This number may be outdated." - "Verify this against a primary source before relying on it." - "I do not have enough information to confirm the exact figure." Do not make up numbers to make an answer sound more useful. If a precise number is unavailable, give a range only if it is justified. Otherwise say the number is unknown. 4. RECENT EVENTS Do not guess about current events. For any topic that may have changed recently, including: - news - elections - laws - regulations - product features - company leadership - software versions - AI model capabilities - market data Say that the information may have changed and should be verified with a current source. Do not present outdated information as current. 5. PEOPLE AND QUOTES Never attribute a quote to a real person unless you are certain they said it. If unsure, say: - "I cannot confirm this quote is accurate." - "This quote is commonly attributed to them, but I cannot verify it." - "I do not know who originally said this." Do not invent statements, beliefs, or motives for real people. Separate confirmed facts from interpretation. If any answer is "yes," revise before responding."

A few months back, I published this guide on how to remember everything you read. Re-sharing it here for anyone who finds these protocols useful. (1/11)

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.

@effendii_ Siap Mas. dicoba yaa.. Makasih sudah sharingg

@chrisxnelson Bisa langsung dicoba hahaha. So far yaa lumayan kerasa aja perbedaannya, ga tll boros kalau untuk ngoding dan planning

Gilaaa mantep bangeet, baru berapa hari pake tool ini savings token di Claude Code udah banyak bangeeet wkwkwkwk. Kenapalahhh diriku ga pake ini dari duluu, haelahhh. Beneran nonstop kerja, tapi token masih awet bangeeeet wkwkwk. Ternyata kehemat banyak bangeet. Cobain gaisss

The guy who BUILT Claude Code is running 10–15 parallel AI agents like an engineering team. Not prompts. Systems. His secret isn’t some hidden feature. It’s a simple file: CLAUDE.md And it changes everything. Every time Claude makes a mistake → it writes a rule. Every correction → permanent memory. Every session → smarter than the last. > “Update your CLAUDE.md so you don’t make that mistake again.” That’s the loop. No repeated errors. No wasted tokens. No babysitting. Just compounding intelligence inside your own codebase. While most people: Rewrite the same prompts Fix the same bugs Start from zero every time He’s building a self-improving engineering system. And it gets crazier: • 10+ agents running in parallel • Research, coding, testing — all split into sub-agents • Clean context, zero clutter • Complex problems = more agents, not more thinking He hasn’t written SQL in 6+ months. Claude just pulls from BigQuery via CLI. This isn’t “AI-assisted coding.” This is AI orchestration. And the gap is already showing. Claude Code is now contributing to ~4% of all public GitHub commits. If you’re still using AI like a chatbot… You’re not behind. You’re playing a completely different game.

Claude Code users are about to become unstoppable 🤯 You can now run OpenAI’s Codex DIRECTLY inside Claude Code. OpenAI just dropped an official plugin that adds: → Code reviews → Adversarial reviews → Background task execution → Extra reasoning workflows inside Claude Code The setup is literally one command: /plugin install codex@openai-codex This means developers are now combining Claude’s workflow + OpenAI Codex in the SAME environment. AI coding tools are slowly turning into full autonomous engineering teams. Repo👇

Claude Code suddenly makes WAY more sense after installing this official Anthropic plugin 🤯 It reads your entire project and instantly tells you what you should actually enable, use, and configure. The crazy part? Most people using Claude Code don’t even know this exists. → Detects your stack automatically → Understands your codebase structure → Suggests the right workflows → Removes the confusing setup phase → Makes Claude Code feel 10x smarter This is probably the real onboarding Claude Code needed 🔥

1/ The Munger Inversion Lens Prompt: “Look at my decision like Charlie Munger. First, don’t tell me what to do. Tell me how I could completely ruin this decision. List the obvious mistakes, incentives I’m ignoring, ego traps, second-order consequences, and ways this could backfire. Then reverse the list into a smarter decision strategy. My problem: [insert problem]”

It is probably the best Claude Design tutorial under 32 minutes It is by UI Collective Academy

The Obituary, As Usual, Is Premature. (Read the Plumbing, not the Panic!) As @Cheytax_1 flagged, X timeline suddenly thick with Macro Reads, most engineered for Doom Bait, distorting proper signal. Every twelve years Indonesia is declared finished. 1998. 2013. Now 2026. The reading is reliably wrong, this is not a default event. Hardly. It is a Market Premia Repricing, made uglier by improper Govt Navigation. But should capable hands of Jakarta wake up, easily Passable. For the time now that it is not, we read, we positioned. Below : The Premises : Jakarta would remain Logical and Current, all tools at their potent disposal (Yes Even Cutting Expenses is a tool) Exchange Rates, and Real Rate Differential. Is means of shock absorbing. Even measured depreciation is preferrable to exhausting import cover ratio. Coming out of the shock, cycle begin anew. Business as usual, Indo was operating under this macro anchor. In SMI era. Picture 1 - The Gravitational Field Picture 2 - The Pragmatic Opportunity 3 year forward 10Y USD swap rate at 4.2% sits a hair below the 4.4% post 2013Taper peak meaning the market priced higher for longer not as a cycle but as new resting heart rate of dollar liquidity. For Indonesia this matters in every rupiah of sovereign refinancing, every dollar of corporate rollover, every BI reserve calculation now lives under a permanent ~150bp uplift in the global riskfree rate versus the 2010s. The "free money" world that incubated Indonesia's foreign-investor SBN share is gone, 14% presence now to the peak of 39,% back then. the forwards say it is not coming back any soon. EM/US fair value gap at +1.3%, but Indonesia having wider premia asked is with reason. IndoGB is generously priced versus fair value, because fair value itself has deteriorated: fiscal trajectory, capital account outflow, reserve drawdown, and BI that held 4.75% since October not out of conviction while defending through FX. The carry is real. Our "fair value" anchor moves. The dissonance and finance plumbing : Onshore INDOGB Comrades, Favor belly of the curve, not long end. The fiscal supply is structural; The 5-7Y sector gives most of the carry. Timing. optionality on BI's reaction function. If BI hikes 25bp next week, another 25-50bp post fuel hikes. front end shall reprice and IndoGB curve bear flattens, Position for the curve shape. Three rules for this cycle. One: do not confuse repricing with default. Two: do not confuse fiscal drift with collapse. Three: do not confuse a noisy timeline with a thesis. Jakarta has tools, history, and capable hands waiting to be used. Onshore, we earn the carry, shorten the duration, and wait for the curve to do the work. Pragmatism is alpha when everyone else is selling doom poetry.

Las presentaciones que genera NotebookLM por defecto son una vergüenza. Pero no es culpa de la herramienta. Es que nadie te dijo que existe un repositorio en GitHub que lo cambia todo. Se llama awesome-notebookLM-prompts. Decenas de prompts de diseño probados por researchers, founders y diseñadores de todo el mundo. Tipografías modernas. Gráficos complejos. Acabado visual de agencia. El mismo contenido. Un prompt diferente. Resultado completamente distinto. El proceso es así: 1️⃣ Entras al repositorio en GitHub 2️⃣ Copias el prompt de diseño que quieras 3️⃣ En NotebookLM, ve a Slide deck → Personaliza → pega el prompt en "Instrucciones personalizadas" 4️⃣ El mismo contenido pasa a tener un acabado profesional Sin configuración. Sin pagar nada. Sin complicaciones. El contenido ya lo tenías. Solo te faltaba el prompt correcto. Te dejo el enlace al repositorio en los comentarios. ¿Cuánto tiempo llevas conformándote con slides mediocres?

You don't need a $500 Claude course. 52 free resources, sorted into 4 modules: CLAUDE CODE 1. lnkd.in/e7gUgJFe 4-hour build + sell course 2. lnkd.in/eVNQjV66 full Code tutorial 3. lnkd.in/eBBsW3SD Code for beginners 4. lnkd.in/eaHUHfnE full 2026 walkthrough 5. lnkd.in/e6nZb9JZ 32 tricks in 16 mins 6. lnkd.in/ehtPc5Tg complete Claude guide 7. lnkd.in/eX9prA4V beginner to advanced 8. lnkd.in/e-934Yhi Claude features ranked 9. anthropic.skilljar.com the official course 10. code.claude.com/docs official documentation CLAUDE COWORK 11. lnkd.in/efCGYqNh Anthropic's official intro 12. lnkd.in/eMGATsbn Cowork in 20 mins 13. lnkd.in/eB-8-c7i better than 99% of users 14. lnkd.in/exZCjUbg full beginner walkthrough 15. lnkd.in/epwYqQKA 100M views with Cowork 16. lnkd.in/eeHWHJ49 Cowork on your desktop 17. lnkd.in/eMRDhZYJ Code + Cowork combined 18. anthropic.skilljar.com official course CLAUDE DESIGN 19. lnkd.in/eKsTX-4T Anthropic's official intro 20. lnkd.in/e42_X9hY Design got unstoppable 21. lnkd.in/eFhPrBYp master 95% in 17 mins 22. lnkd.in/eg7b5hmM master 95% in 10 mins 23. lnkd.in/egy4Q4NQ launch reaction video 24. lnkd.in/eWtwB-nJ why I replaced Canva 25. lnkd.in/eZHgXYn7 Design launch breakdown 26. lnkd.in/eZ6wSdJA design in Code, not Canva Save this for the next time you want to learn Claude. Join AI Community : whatsapp.com/channel/0029Va… Repost ♻️ to help someone in your network.