Glootie App Developer

This is why cybersecurity is the best startup category to build in right now Every major platform is getting breached in 2026. vercel, snowflake, the list keeps growing. AI made it 100x easier to build. it also made it 100x easier to attack. If you're building a cybersecurity startup right now, your timing is perfect The attack surface is expanding every single day and the buyers have never been more plentiful Be safe out there

OBSIDIAN + CLAUDE CODE. A PERSONAL OPERATING SYSTEM. BUILT ON MARKDOWN, BACKLINKS, AND A COMMAND-LINE AGENT. You write notes like always. No new app to learn, no proprietary format, just a folder of .md files on your machine. Claude Code reads the entire vault on its own. Every file, every backlink, every connection. In one session. Obsidian CLI breaks down the graph node by node. The agent sees not just the files, but the relationships between them. Without a single manual hint. Custom slash commands turn the agent into a thinking partner. /trace follows how an idea evolved over months. /connect bridges two domains through the link graph. /ghost answers the way you would answer. /challenge pressure-tests your current beliefs. /ideas generates actionable concepts from what you already wrote. All grounded in your own words. One hour of walkthrough from empty vault to a working second brain. The system runs on real notes from a real life. Works on any machine. Markdown files - take them and run. Personal knowledge is no longer locked inside your head. AI turned reflection into leverage.

Stop thinking of Claude as something you talk to. A student spent $4 on a transmitter $350 on an iPad, one afternoon wiring it together. Now Claude physically taps through apps while he does absolutely nothing. No laptop open. No prompts. No supervision. No salary. It opens books, clicks menus, reads the screen, decides what to do next. Acts. This is not a chatbot, this is not a copilot, this is a deployed worker that costs less than your grocery run. Silicon Valley is burning $100m+ trying to build autonomous agents, A broke student did it on a Saturday for $354. The future isn't coming, some kid already built it on his desk and went back to sleep.

Claude can now meal prep your entire week and hit your exact nutrition goals like a $200/hour registered dietitian from the Mayo Clinic. For free. Here are 12 prompts that plan meals, calculate macros, and save you $500/month on groceries: (Save this before it disappears)

what the fuck

Save this Claude tree before your next prompt. Step 1: is it more than a quick answer? ☑️ No: use Sonnet 4.6. ☑️ Yes: move to Step 2. Step 2: If you pick Sonnet 4.6: → Simple task? Prompt example: "You are a [role]. [Task] this [input]. Keep it under [length]. Tone: [casual/formal]. No preamble. Just the output." → Create files (Excel, docs, slides)? Prompt example: "Create a professional Excel spreadsheet (.xlsx) for: [PURPOSE]. Context: [WHO / HOW USED]. It should cover: [LIST]. Rules: Use Excel formulas - never hardcoded calculations. Put editable assumptions in their own labeled cells." → Connect with more connectors. Slack, Google Drive, Notion, Figma and 50+ more. Step 3: If yes, does it require working with files? ☑️ No: use Haiku 4.5 (lightweight, token-saver). ☑️ Yes: use Opus 4.7 (reasoning model). Step 4: If you pick Haiku 4.5: → Chat. No files needed. → Turn on web search. → Plan in Chat, build in Cowork. Prompt example: "I want to [desired results] with [constraints]. Ask me questions using AskUserQuestion before you start." ☑️ Use token-saving habits: - Edit your message, don't send a follow-up - Batch tasks into one message - Say "No commentary. Just the output." - Convert PDFs to .md before uploading - Turn off Search & Extended Thinking - New topic = new chat. Always. - Keep files under 2,000 words Step 5: If you pick Opus 4.7: → Turn on Extended Thinking. Always. → Upload .md files (not PDFs!). → Open Cowork. Select your folder. Prompt example: "I want to [task] so that [success looks like]. Read the uploaded files completely. DO NOT start yet. Ask me clarifying questions (use AskUserQuestion) so we can refine the approach step by step." After Cowork: → Download your file. → Save session-notes .md. → Start a fresh session to save tokens. Claude is not one tool. It's three models. Most people use the wrong one for every task. --- To download all of my other Claude infographics: Step 1. Go to how-to-ai.guide. Step 2. Subscribe for free. Don't pay anything. Step 3. Open my welcome email (most skip this). Step 4. Hit the automatic reply button inside. Step 5. Download my infographics from my Notion. Bonus. Enjoy my best copy-paste prompts, too.

- you work 60 hours a week - half of it is the same tasks on repeat - reports - research - emails - content - you know AI exists - you’ve even used it - but you do anyway - because setup feels like effort - every year you hand 1,000 hours - to tasks that take a machine 3 mins - you’re unautomated - slowly trading your life - for work a computer would do

Claude Code x TradingView is one of the most powerful AI trading setups I've ever used. You can literally turn Claude into your personal trading assistant in minutes. Vibe-code custom indicators, conduct deep technical analysis, and more. This cheatsheet teaches you how:

Excellent analogy: Post-Mythos, LLMs have fully surpassed human hackers. Proving something is safe means spending more tokens than attackers will. That's the PoW security model to a tee. Cryptoeconomics now applies to all software. Recommended reading👇 dbreunig.com/2026/04/14/cyb…

You're using Claude like it's 2024. Here's the full 2026 setup (one cheatsheet to save): 1. Get the Claude app (claude .com/download). 2. You need a Pro plan ($20/mo). Worth every cent. 3. You'll see 4 tabs: Chat, Cowork, Code & Projects. ----- ✦ Cowork = Claude works inside your computer. Pick a folder. Add 3 files: about-me .md, anti-ai-style .md, my-company .md. Go to how-to-ai.guide to my .md files. Don't pay anything, get it in the welcome email. Set Global Instructions so it reads before tasks. Claude generates clickable forms. Click & answer. ✦ Projects = persistent context for your team. Go to claude .ai → Click "Projects" in the sidebar. Upload your brand docs, writing samples & data. Set custom instructions. Chat inside the Project. Every conversation remembers everything. ✦ Skills = slash commands that fire automatically. Open Cowork → prompt: "Use the skill-creator to build a skill for [your task]." Claude interviews you. Builds the Skill. You upload it once. Now type /brief anywhere. It just works. Browse plugins: Customize → Personal plugins → +. ✦ Code = a junior developer for $0.66/day. Go to the Code. Connect your free GitHub account. Type what you want in English. Attach a screenshot. Claude builds it. Pushes it live. You edit with words. Install VS Code + bypass permissions to go 10x fast. ----- Pro tip: Select Opus 4.6 + Extended thinking for complex tasks. Use Sonnet for quick ones. Help others be better at Claude ♻️ repost this. PS: I write a newsletter to 484,000+ readers. ↳ Join us for free at how-to-ai.guide. ↳ Open the welcome email after subscring. ↳ Download all of my infographics, also for free.

If Metcalfe’s Law is the best way to value blockchains, which I believe it is, then the two variables that matter are value transacted per user and total users. They compound. The key future drivers: Value transacted per user will come from the financial system moving to blockchain rails, led by stablecoins and then the tokenization of everything else. TradFi value dwarfs everything else. User growth will come from agents. Smaller transactions, but orders of magnitude more users than humans will ever produce. Everything else will be a rounding error in 10 years.

Stop being cynical. Go out and make something.

As discussed on @theallinpod a few weeks ago…this risk is real and, imo, q-day gets pulled in closer in time with every major model breakthrough.

I have been asked by several people what I meant when I said “we are in a world war” in my most recent note. To be clear, I didn’t mean to convey that I expect a shooting war between the U.S. and China (or any of the great powers) anytime soon. What I meant is that we are in the phase of the Big Cycle when major powers are in military wars and that the various wars happening now are interrelated, hence we are in a “world war," with the sides lined up as I described and with the implications for each of the main players and the whole unfolding in relatively classic interrelated ways that I describe as a progression of the Big Cycle. For example, it is now widely believed that if the U.S. fails to open the Strait of Hormuz to have free shipping and to protect its Gulf Allies from attacks, countries all around the world (most importantly in Asia) will conclude that the U.S. might not be the strong ally and countervailing force to China that they thought it would be. which will lead some to tilt economically and geopolitically more toward China in a number of ways - e.g. to buy less U.S. debt (which is what happened to the British in the Suez Crisis, bringing about the ultimate end of their Empire) - and it could lead others to build up their military capabilities.  As I complete my nearly three-week trip in Asia, I can convey that what I am saying is based on a lot more than conjecture. The reason I do not expect a U.S.-China military war soon, but I do expect a lot of brinksmanship, is because both nations realize that such a war would be devastating and that it would be impossible to fully win over the other, at the same time as they won’t want to give much.  Also, each country believes in its own economic and political systems and that the outcomes of those systems will determine their relative powers. And both nations have critically important domestic issues to deal with.  Some people in leadership positions, especially in China, believe that the relative health, wealth, and power levels between countries is not as important as their own absolute health, wealth, and power levels, and that helping each other build these rather than tear them down is most important. For example, they believe that the world will be a dangerous place if the U.S. and China don't have AI cooperations and controls, and they are concerned that AI can be weaponized. Most countries know that most wars in history were won by one of the sides secretly developing new technologically advanced weapons and showing them to their opponents. So, I believe that both sides think that their wars will be non-military wars that will yield evolutionary changes in relative powers.  As for how the Chinese will fight, and how the world order related to it will evolve, it will probably look more like the type of war described in the “Art of War” (which I suggest you read if you haven't), and for how the new international world order will evolve, to the extent that it is influenced by the Chinese, it will evolve to be more like the tribute system (which I suggest you understand if you don’t) than the existing world order. At the same time, I expect that there will continue to be trade, capital, technology, cyber, and geopolitical influence wars between these great powers and that both will continue to have justifiable fears of being cut off from essential goods, services, and capital that will necessarily will greatly reduce imbalances and interdependencies as well as efficiencies in production and trade of goods, services, and capital. I also believe we will increasingly see these two powerful nations pressure each other because there is no other way to resolve disputes now that the rules-based multilateral world order has been replaced by a power-based, self-serving world order. Said differently, I expect that China will be very strong in its defense without being very aggressive in its offense.  That is not just for tactical reasons; it is also because China has strong cultural inclinations to be that way. I hope this is helpful in clarifying my thinking and as always I'd be happy to answer any other questions or hear your thoughts. Ray

15 AI related accounts you should follow on Twitter: 1. @karpathy His tweets already create LLMs narratives that you later see on linkedin in 2 months. 2. @fchollet posts thoughtful research on intelligence, benchmarks, and AI limitations. Keras creator + ARC-AGI 3. @ylecun Yann LeCun is Deep learning pioneer & Meta Chief AI Scientist; big-picture research takes and critiques (and drama). 4. @AndrewYNg Andrew Ng is AI education legend; practical ML advice, courses, and real-world implementation. creator of deeplearning ai 5 @rasbt Sebastian Raschka posts on Practical ML/LLM implementations, "build from scratch" tutorials, and books. 6. @dair_ai Weekly ML/AI paper threads and accessible research explainers (high-signal for staying current). 7. @lilianweng Lilian Weng is ex-OpenAI and her Lil'Log-style threads are good. has In-depth LLM research breakdowns 8. @jeremyphoward posts interesting takes on AI/crypto news, and works on democratizing practical deep learning and accessible education. 9. @simonw Simon post Practical LLM tools, takes, experiments, prompting, and engineering breakdowns. django co-founder 10. @_akhaliq Curates the latest arXiv papers, model releases, and open-source AI drops. 11. @ID_AA_Carmack AGI/low-level optimization takes that makes you think about the problem. 12. @gwern Really high-quality long-form AI research notes and essays. 13. @goodside LLM evaluation, prompting research, and real capabilities testing 14 @drfeifei Computer vision pioneer; human-centered AI and spatial intelligence research 15 @demishassabis Been following his work for 9 years. Demmis is my hope against google usurpating their power with AI. Demmis is google DeepMind's CEO Let me know who I missed guys

i watched this Taiki Maeda's latest video on why BTC has bottomed and it connected a lot of dots i've been thinking about. the main thesis is simple.. rn crypto feels completely dead.. fear and greed sitting at extreme fear for weeks. people are positioned for a crash that already happened. and BTC is just.. climbing. quietly. $75K + today.. this is what they call a wall of worry. price goes up while everyone explains why it shouldn't. nobody believes it. nobody is positioned for it. and that's exactly why it works… but the part that really got me thinking is the STRC angle. saylor's STRC pays 11.5% yield right now. institutions are buying it. BlackRock, Fidelity, VanEck. and every dollar that flows into STRC goes directly into buying BTC. it's a machine.. now think about this for a second. if the market genuinely thought BTC was going lower, why would institutions be lining up to buy a Bitcoin backed yield product at these levels? they wouldn't. the demand for STRC is the market quietly saying that BTC at $65-70K is fair value or below.. and this is also why the 4 year cycle might be dead. previous cycles didn't have a whale buying billions in BTC every single month like clockwork. that changes the floor dynamics completely. Saylor bought $1B last week alone. and he's not stopping. the bear case is that saylor eventually blows up. fine. but even taiki makes a good point here. even if it ends badly in 2-3 years, it has to pump BTC massively before that happens. so why would you be short during the run up? the other thing that hit home for me. he said whenever he looks for Bitcoin beta through altcoins, he finds out that he's the beta. holding ETH, holding random DeFi coins, watching them bleed while BTC rips. last cycle solana didn't start moving until BTC 2x'd off the bottom. so the play is simple. own BTC. don't try to be clever. the wall of worry is being climbed and most people are sitting in cash waiting for a crash that's not coming…

Si estás empezando con Claude, hay 12 conceptos que tenés que entender: 1) CLAUDE.md 2) Permissions 3) Plan Mode 4) Checkpoints 5) Skills 6) Hooks 7) MCP 8) Plugins 9) Context 10) Slash Commands 11) Compaction 12) Subagents En el video lo explican muy bien 👇

Stop writing 500-word prompts that don't work. Here's the exact 3-part structure that works better: Part 1: Context (.md) files. Part 2: Clear instructions. Part 3: "Don't start yet - ask me questions first." That's it. But most people skip all three. Here's what each one fixes: Part 1 - Context files. Step 1. Create a file called "ABOUT ME." Step 2. Put in your role, audience, goals, and tone. Step 3. Create a second file: "WRITING STYLE." Step 4. Add 3–5 examples of your best past writing. Step 5. Save both as .md files. Step 6. Upload them before you type a prompt. Step 7. It knows who you are before it writes a word. Part 2 - Clear instruction. Step 1. State the task in one sentence. Step 2. Name the format. (Post, email, thread, ad.) Step 3. Name the audience. (Founders, marketers.) Step 4. That's your prompt. Not 500 words. 3 lines. Part 3 - "Ask me questions first." Step 1. Add this line at the end of every prompt: "DO NOT start writing yet. Ask me clarifying questions first." Step 2. Claude will ask 3–6 questions. Step 3. Answer them by clicking buttons. Step 4. Now Claude writes something that actually sounds like you said it. Or skip all of that. To download my exact files: Step 1. Go to how-to-ai.guide. Step 2. Subscribe for free. Don't pay anything. Step 3. Open my welcome email. Step 4. Hit the automatic reply button inside. Step 5. Download my .md files. Upload to Claude. ✦ Here's why your current prompts fail (red flags): "Write me a LinkedIn post about AI tools." "Make it engaging and professional." "Keep it under 200 words." One sentence. No context. No style. No voice. You gave Claude nothing to work with. That's like handing someone a blank page & saying, "write something amazing." No reference, examples & direction. The fix isn't a longer prompt. It's a smarter setup. Bad prompt: one vague sentence → generic AI slop. Better prompt: clear task + "ask me questions first" Best prompt: .md files + clear task + "ask me questions first" → sounds like you wrote it. To get my exact files, subscribe to how-to-ai.guide. ♻️ Repost to help one person, prompt better.

> "i'm good at Claude" > use 5% of it > everyone uses 5% of it > spend 30 days learning the other 95% > companies start paying you > to teach their employees > what you learned in 30 days > they pay thousands > the knowledge was free > the 30 days was the only cost