正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

this GitHub README is where the $5k AI OS starts one CLI > Drive > Gmail > Calendar > Docs > Sheets Claude Code stops being a chat box and starts touching the actual business. that is what clients buy. they buy the moment Google Workspace becomes executable. one... show more

Myttle

1,385 subscribers

12,602 次观看 • 1 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

AGENCIES ARE CHARGING $50,000 FOR HEAVY, CLUNKY AUTOMATION, WHILE SOLO OPERATORS ARE SELLING THE SAME OUTCOME FOR $5k AND BUILDING IT IN JUST 3 HOURS Most people think building an AI agency requires an expensive stack of tools like n8n, Make, and Zapier to justify high monthly retainers They spend weeks pitching and designing overly complex “spaghetti” workflows for clients In reality, the better approach is to build an AI Operating System directly in VS Code using local Markdown files The cost gap is insane. You pay $20/month for a Claude account and spend a few hours wiring up ClickUp and Google Workspace APIs Then you package that same architecture as a $5k one-time setup and a $2k monthly retainer Right now, founders are paying $15k + for enterprise AI setups that a single operator can build with almost zero overhead And if you want a practical AI OS playbook, I’ve attached an article below Save this post and the article so you can come back later and learn how to build a full AI operating system in just 3 hours

AGENCIES ARE CHARGING $50,000 FOR HEAVY, CLUNKY AUTOMATION, WHILE SOLO OPERATORS ARE SELLING THE SAME OUTCOME FOR $5k AND BUILDING IT IN JUST 3 HOURS Most people think building an AI agency requires an expensive stack of tools like n8n, Make, and Zapier to justify high monthly retainers They spend weeks pitching and designing overly complex “spaghetti” workflows for clients In reality, the better approach is to build an AI Operating System directly in VS Code using local Markdown files The cost gap is insane. You pay $20/month for a Claude account and spend a few hours wiring up ClickUp and Google Workspace APIs Then you package that same architecture as a $5k one-time setup and a $2k monthly retainer Right now, founders are paying $15k + for enterprise AI setups that a single operator can build with almost zero overhead And if you want a practical AI OS playbook, I’ve attached an article below Save this post and the article so you can come back later and learn how to build a full AI operating system in just 3 hours

Bonsai 🌳

10,885 次观看 • 1 个月前

THIS GUY BUILT AN AUTONOMOUS AI AGENT OUT OF CLAUDE CODE + OBSIDIAN and this is way more interesting than another “use AI to take notes” demo the trick is simple: Obsidian is not the writing app here. it becomes the agent’s memory, task board, and context folder. Claude Code is not just answering prompts. it reads the vault, edits files, follows instructions, and keeps moving through the work like a junior operator with a filesystem. the reusable setup looks like this: 1. create an Obsidian vault for one project 2. keep goals, rules, tasks, decisions, and references as markdown files 3. point Claude Code at the folder 4. give it a clear operating loop: read context → choose next task → execute → write back what changed 5. use the notes as persistent memory instead of re-explaining the project every chat that’s the part people miss. the “agent” is not magic. it’s the boring combination of: - local files - explicit rules - task state - write access - a model that can run through the repo/vault Obsidian makes the memory human-readable. Claude Code makes the memory executable. that combo is why the video worked: it turns a notes app into an operating surface for actual work. best use cases: - content systems - research vaults - coding projects - client ops docs - personal knowledge bases that need actions, not just storage the caveat: if your vault is messy, your agent becomes messy too. folders, naming, “done” criteria, and forbidden actions matter more than the prompt. but once the structure is clean, this is one of the easiest ways to build an agent that remembers what happened yesterday without paying for a full custom app.

THIS GUY BUILT AN AUTONOMOUS AI AGENT OUT OF CLAUDE CODE + OBSIDIAN and this is way more interesting than another “use AI to take notes” demo the trick is simple: Obsidian is not the writing app here. it becomes the agent’s memory, task board, and context folder. Claude Code is not just answering prompts. it reads the vault, edits files, follows instructions, and keeps moving through the work like a junior operator with a filesystem. the reusable setup looks like this: 1. create an Obsidian vault for one project 2. keep goals, rules, tasks, decisions, and references as markdown files 3. point Claude Code at the folder 4. give it a clear operating loop: read context → choose next task → execute → write back what changed 5. use the notes as persistent memory instead of re-explaining the project every chat that’s the part people miss. the “agent” is not magic. it’s the boring combination of: - local files - explicit rules - task state - write access - a model that can run through the repo/vault Obsidian makes the memory human-readable. Claude Code makes the memory executable. that combo is why the video worked: it turns a notes app into an operating surface for actual work. best use cases: - content systems - research vaults - coding projects - client ops docs - personal knowledge bases that need actions, not just storage the caveat: if your vault is messy, your agent becomes messy too. folders, naming, “done” criteria, and forbidden actions matter more than the prompt. but once the structure is clean, this is one of the easiest ways to build an agent that remembers what happened yesterday without paying for a full custom app.

kocer

30,403 次观看 • 20 天前

THIS GUY BUILT A BUSINESS SECOND BRAIN WITH CLAUDE CODE + OBSIDIAN IN 3 STEPS Most teams do not need another Notion workspace. They need a place where the company can remember how it works. The video shows a simple setup: 1. Create one empty folder called second brain. 2. Split it into 3 buckets: raw new knowledge wiki 3. Let Claude Code turn messy company material into connected notes. The useful part is the separation. Raw is where your existing stuff goes: SOPs, sales docs, process notes, client delivery checklists, old Loom summaries, onboarding docs. New knowledge is where fresh outside material lands: articles, clips, tactics, examples, market notes. Wiki is the cleaned version: concepts, roles, processes, SOPs, gaps, reusable decisions. That is where Claude Code becomes more useful than a normal chat window. Instead of asking it to remember random context forever, you give it a folder it can read, edit, and reorganize. Then Obsidian becomes the human interface. The Obsidian Web Clipper captures useful pages into the vault. Claude Code ingests them. The wiki gets updated. Then you can ask questions like: “Does my current workflow actually hold up?” That is the real point. Not “AI notes.” A business memory system that can compare what you do today against new information tomorrow. The caveat: this is not magic company intelligence. If your raw docs are vague, outdated, or full of tribal knowledge, Claude will organize weak inputs into cleaner weak outputs. You still need naming rules, review habits, and someone responsible for deleting junk. But the setup is refreshingly practical. Folder first. Clipper second. Claude Code as the maintainer. No giant knowledge base migration. No complex setup. Just a local vault that can slowly turn scattered business memory into something searchable, editable, and actually reusable.

THIS GUY BUILT A BUSINESS SECOND BRAIN WITH CLAUDE CODE + OBSIDIAN IN 3 STEPS Most teams do not need another Notion workspace. They need a place where the company can remember how it works. The video shows a simple setup: 1. Create one empty folder called second brain. 2. Split it into 3 buckets: raw new knowledge wiki 3. Let Claude Code turn messy company material into connected notes. The useful part is the separation. Raw is where your existing stuff goes: SOPs, sales docs, process notes, client delivery checklists, old Loom summaries, onboarding docs. New knowledge is where fresh outside material lands: articles, clips, tactics, examples, market notes. Wiki is the cleaned version: concepts, roles, processes, SOPs, gaps, reusable decisions. That is where Claude Code becomes more useful than a normal chat window. Instead of asking it to remember random context forever, you give it a folder it can read, edit, and reorganize. Then Obsidian becomes the human interface. The Obsidian Web Clipper captures useful pages into the vault. Claude Code ingests them. The wiki gets updated. Then you can ask questions like: “Does my current workflow actually hold up?” That is the real point. Not “AI notes.” A business memory system that can compare what you do today against new information tomorrow. The caveat: this is not magic company intelligence. If your raw docs are vague, outdated, or full of tribal knowledge, Claude will organize weak inputs into cleaner weak outputs. You still need naming rules, review habits, and someone responsible for deleting junk. But the setup is refreshingly practical. Folder first. Clipper second. Claude Code as the maintainer. No giant knowledge base migration. No complex setup. Just a local vault that can slowly turn scattered business memory into something searchable, editable, and actually reusable.

kocer

16,542 次观看 • 17 天前

20-YEAR-OLD GUY SHOWS HOW CLAUDE API CAN TURN 500-VIEW CONTENT INTO A $40K/MONTH CLIENT WORKFLOW Not from a big agency. Not from hiring writers. Just taking the same service people sell every week and wiring Claude API into the boring middle. A topic goes in. It pulls the research, angles, outline, draft, edits, and a clean file. That is normally $500-$1,500 of freelance work per client project. The screen says around $40K/month, but the real number is the time saved. A $3K project stops being 8 hours of rewriting and becomes 45 minutes of checking before delivery. Most people use Claude to write one answer. He is showing what happens when the whole process becomes the product.

20-YEAR-OLD GUY SHOWS HOW CLAUDE API CAN TURN 500-VIEW CONTENT INTO A $40K/MONTH CLIENT WORKFLOW Not from a big agency. Not from hiring writers. Just taking the same service people sell every week and wiring Claude API into the boring middle. A topic goes in. It pulls the research, angles, outline, draft, edits, and a clean file. That is normally $500-$1,500 of freelance work per client project. The screen says around $40K/month, but the real number is the time saved. A $3K project stops being 8 hours of rewriting and becomes 45 minutes of checking before delivery. Most people use Claude to write one answer. He is showing what happens when the whole process becomes the product.

Gipp 🦅

19,254 次观看 • 1 个月前

THIS GUY SPENT 5 MINUTES SETTING UP A $20 CLAUDE WORKSPACE AND TURNED 30 MINUTES OF DAILY PROMPT CHAOS INTO A SYSTEM Most people open Claude, type 1 messy prompt, rewrite it 10 times, get the same generic answer and call the model “bad.” He opens Claude Cowork, adds the project rules, past context, working files, examples, decisions and a clean place for the model to remember what it is doing. Same Claude. Same $20 tool. Completely different output. The funny part is there is no magic prompt here. No secret template. No “10x Claude” trick. Just the boring layer Karpathy keeps pointing at: context, memory and structure before output. A setup like this can save 30 minutes a day, which is 15 hours a month. If you use Claude for client work at $50 to $100/hour, that is $750 to $1,500/month in time you stop burning on repeated prompts. The model is real. The output is real. The edge is in not making Claude start from zero every single time.

THIS GUY SPENT 5 MINUTES SETTING UP A $20 CLAUDE WORKSPACE AND TURNED 30 MINUTES OF DAILY PROMPT CHAOS INTO A SYSTEM Most people open Claude, type 1 messy prompt, rewrite it 10 times, get the same generic answer and call the model “bad.” He opens Claude Cowork, adds the project rules, past context, working files, examples, decisions and a clean place for the model to remember what it is doing. Same Claude. Same $20 tool. Completely different output. The funny part is there is no magic prompt here. No secret template. No “10x Claude” trick. Just the boring layer Karpathy keeps pointing at: context, memory and structure before output. A setup like this can save 30 minutes a day, which is 15 hours a month. If you use Claude for client work at $50 to $100/hour, that is $750 to $1,500/month in time you stop burning on repeated prompts. The model is real. The output is real. The edge is in not making Claude start from zero every single time.

Gipp 🦅

14,871 次观看 • 1 个月前

Your Claude has a tell, and almost nobody uses it. Make it start every reply with your name. One line in custom instructions, no code. The moment it stops saying your name, its context window is full. That is the exact point the output starts drifting, and you do not notice. Name stops? Start a fresh chat. It has killed about 90% of my “why has Claude gone weird” moments. Miners sent a canary down the pit to catch the gas they could not see. Same trick, for your context. Comment GUIDE and I’ll send you the exact canary setup.

Your Claude has a tell, and almost nobody uses it. Make it start every reply with your name. One line in custom instructions, no code. The moment it stops saying your name, its context window is full. That is the exact point the output starts drifting, and you do not notice. Name stops? Start a fresh chat. It has killed about 90% of my “why has Claude gone weird” moments. Miners sent a canary down the pit to catch the gas they could not see. Same trick, for your context. Comment GUIDE and I’ll send you the exact canary setup.

Charlie Hills

22,956 次观看 • 3 天前

how to use openclaw to spin up 24/7 digital employees and build cash-flowing assets: 1. spin up openclaw (mac mini, vm, orgo, whatever) in a workspace so you can run 5–10 machines at once (main agent + sub-agents) 2. pick one boring workflow inside one industry (distributors, real estate, insurance, law firms) 3. map the workflow tip-to-tail (email/trigger → legacy software clicks → downloads → parsing → upload to crm) 4. use claude code to build the “under the hood” python pipeline (openclaw becomes the operator + trigger, code does the heavy lifting) 5. productize it as a repeatable bundle: “setup + 30 days management + new workflows each week” 6. use upwork as the lead source and the sandbox (it tells you what people pay for right now) 7. turn the best-paying workflow into a vertical workspace: 20 skills, 8 sub-agents, one invite link 8. sell it to bigger companies as “ai employees for this department” (with clear outcomes + SLA) "BuT yoU cAn'T bUiLD a BiG coMpaNY dOInG uPwoRk deAls" think about it like this “how does a $1k automation gig turn into a big company deal?” like this: 1. upwork gives you paid reps + proof someone pays for the workflow 2. those reps become case studies (“saved 12 hrs/week”, “uploaded 5k records/day”, “reduced ops errors by 80%”) 3. you stack 5–10 workflows in the same vertical 4. now you’re selling a package and not a one off deal which is tough 5. bigco buys packages because procurement 6. understands scopes + outcomes openclaw is the wrapper. claude code is the factory. sub agents/skills are the workforce. the vertical bundle is the product. episode is live on The Startup Ideas Podcast (SIP) 🧃 i will never gatekeep i want to see you win in this openclawed world i am rooting for you watch.

how to use openclaw to spin up 24/7 digital employees and build cash-flowing assets: 1. spin up openclaw (mac mini, vm, orgo, whatever) in a workspace so you can run 5–10 machines at once (main agent + sub-agents) 2. pick one boring workflow inside one industry (distributors, real estate, insurance, law firms) 3. map the workflow tip-to-tail (email/trigger → legacy software clicks → downloads → parsing → upload to crm) 4. use claude code to build the “under the hood” python pipeline (openclaw becomes the operator + trigger, code does the heavy lifting) 5. productize it as a repeatable bundle: “setup + 30 days management + new workflows each week” 6. use upwork as the lead source and the sandbox (it tells you what people pay for right now) 7. turn the best-paying workflow into a vertical workspace: 20 skills, 8 sub-agents, one invite link 8. sell it to bigger companies as “ai employees for this department” (with clear outcomes + SLA) "BuT yoU cAn'T bUiLD a BiG coMpaNY dOInG uPwoRk deAls" think about it like this “how does a $1k automation gig turn into a big company deal?” like this: 1. upwork gives you paid reps + proof someone pays for the workflow 2. those reps become case studies (“saved 12 hrs/week”, “uploaded 5k records/day”, “reduced ops errors by 80%”) 3. you stack 5–10 workflows in the same vertical 4. now you’re selling a package and not a one off deal which is tough 5. bigco buys packages because procurement 6. understands scopes + outcomes openclaw is the wrapper. claude code is the factory. sub agents/skills are the workforce. the vertical bundle is the product. episode is live on The Startup Ideas Podcast (SIP) 🧃 i will never gatekeep i want to see you win in this openclawed world i am rooting for you watch.

GREG ISENBERG

241,383 次观看 • 4 个月前

THIS GUY BUILT A 24/7 AI COMPANY WITH 7 AGENTS THAT CHECKS 48 TIMES A DAY, PICKS ITS OWN TASKS AND KEEPS WORKING WHILE HE SLEEPS 00:05 the map shows agents moving between the marketplace, research lab and command center, with each one handling a different job inside the same shared system the setup runs on 4 core layers: automatic triggers, shared memory, connected tools and an isolated verifier that checks every result before the next step starts each cycle reads the last 10 log entries, updates open tasks, saves new signals and passes the context forward, so the next agent never starts from zero one agent researches, two execute, another monitors outcomes and a read-only checker reviews the work independently, allowing several workflows to run in parallel without breaking the system bookmark this before everyone stops prompting one agent at a time and starts building AI teams that work, learn and improve around the clock

THIS GUY BUILT A 24/7 AI COMPANY WITH 7 AGENTS THAT CHECKS 48 TIMES A DAY, PICKS ITS OWN TASKS AND KEEPS WORKING WHILE HE SLEEPS 00:05 the map shows agents moving between the marketplace, research lab and command center, with each one handling a different job inside the same shared system the setup runs on 4 core layers: automatic triggers, shared memory, connected tools and an isolated verifier that checks every result before the next step starts each cycle reads the last 10 log entries, updates open tasks, saves new signals and passes the context forward, so the next agent never starts from zero one agent researches, two execute, another monitors outcomes and a read-only checker reviews the work independently, allowing several workflows to run in parallel without breaking the system bookmark this before everyone stops prompting one agent at a time and starts building AI teams that work, learn and improve around the clock

Gipp 🦅

18,927 次观看 • 14 天前

THIS OPERATOR REPLACED A $50,000 AUTOMATION AGENCY WITH A 3-HOUR BUIL 378 browser tabs. 47 Notion pages nobody touched in 6 months. A spreadsheet that crashes every Monday He didn't hire a dev team. He didn't buy n8n enterprise He cloned a GitHub repo, wired 3 API keys, and typed /onboard into Claude Code By day 14 his team messaged the AI OS in Slack instead of messaging him His old workflow: 3 hours of context switching, 2 hours of actual work His new workflow: 5 hours of deep work, 30 minutes of admin This is not a dashboard. This is a command center Full breakdown below ↓

THIS OPERATOR REPLACED A $50,000 AUTOMATION AGENCY WITH A 3-HOUR BUIL 378 browser tabs. 47 Notion pages nobody touched in 6 months. A spreadsheet that crashes every Monday He didn't hire a dev team. He didn't buy n8n enterprise He cloned a GitHub repo, wired 3 API keys, and typed /onboard into Claude Code By day 14 his team messaged the AI OS in Slack instead of messaging him His old workflow: 3 hours of context switching, 2 hours of actual work His new workflow: 5 hours of deep work, 30 minutes of admin This is not a dashboard. This is a command center Full breakdown below ↓

Asteri

10,194 次观看 • 1 个月前

I'm making over $1,000 an hour with one AI offer. The entire thing runs on Claude Opus 4.8. I call it the AI Concierge. Clients pay me $1,500+ a month for two 45-minute calls where we build their AI systems live, on their screen. I have 4 clients. I'm capping at 6. Here's the entire model: 1) The intake form is the audit. A 10-minute JotForm (built by Claude) surfaces their time sinks and hands me 1-3 AI opportunities before call one. 2) Done-with-you, not done-for-you. They share their screen. We build skills, set up Cowork, and write context files together. They learn to drive. (Done-for-you is the upsell.) 3) Every session runs through AOA: Audit, Optimize, Automate. Fix the process first, then turn it into a skill. Automating chaos just gives you faster chaos. 4) Day one has to move the needle. We ship at least one skill or automation on call one. No first-call win, dead engagement. 5) Unlimited Voxer between calls. They send a voice message, I reply in under 12 business hours. A 24/7 partner, not a guy they see twice a month. 6) The Notion hub is the renewal mechanism. Every call logs a quantified list of what we built. "Call one: 2 skills, 3 context files, Cowork live" makes $1.5K a month a no-brainer. 7) I never fill Notion out by hand. Two Claude skills log the call, pull the action items, and draft the recap email. 30 seconds. 8) Pricing ladder: $1,000/month, then $1,500 at 2 clients, then $1,800. At $1,500 you're already at $1,000/hour. If everyone says yes then you're priced too low. Two things that make this work: 1) Build the fulfillment infrastructure once. An afternoon. Then it runs itself outside the calls. 2) The value must be visible. People renew what they can measure. Full breakdown below. Go watch.

I'm making over $1,000 an hour with one AI offer. The entire thing runs on Claude Opus 4.8. I call it the AI Concierge. Clients pay me $1,500+ a month for two 45-minute calls where we build their AI systems live, on their screen. I have 4 clients. I'm capping at 6. Here's the entire model: 1) The intake form is the audit. A 10-minute JotForm (built by Claude) surfaces their time sinks and hands me 1-3 AI opportunities before call one. 2) Done-with-you, not done-for-you. They share their screen. We build skills, set up Cowork, and write context files together. They learn to drive. (Done-for-you is the upsell.) 3) Every session runs through AOA: Audit, Optimize, Automate. Fix the process first, then turn it into a skill. Automating chaos just gives you faster chaos. 4) Day one has to move the needle. We ship at least one skill or automation on call one. No first-call win, dead engagement. 5) Unlimited Voxer between calls. They send a voice message, I reply in under 12 business hours. A 24/7 partner, not a guy they see twice a month. 6) The Notion hub is the renewal mechanism. Every call logs a quantified list of what we built. "Call one: 2 skills, 3 context files, Cowork live" makes $1.5K a month a no-brainer. 7) I never fill Notion out by hand. Two Claude skills log the call, pull the action items, and draft the recap email. 30 seconds. 8) Pricing ladder: $1,000/month, then $1,500 at 2 clients, then $1,800. At $1,500 you're already at $1,000/hour. If everyone says yes then you're priced too low. Two things that make this work: 1) Build the fulfillment infrastructure once. An afternoon. Then it runs itself outside the calls. 2) The value must be visible. People renew what they can measure. Full breakdown below. Go watch.

Corey Ganim

103,260 次观看 • 1 个月前

You don't fully understand what this integration could turn into. Five skills. Created by the CEO of Obsidian. Released publicly. Free to add. He read it and thought about who would pay him to implement it for them. Law firms. Agencies. Medical practices. All have the same problem, knowledge that lives in someone's head until that person leaves. He builds the vault. Writes the files. Connects Claude. Delivers in three days. $2,200 once. $1,500 every month after. The pitch is one sentence: your new employee will read every process, every client file, and every decision made in the last three years before their first day. 6 clients. $9,000 a month. 10 hours of work a week. Five skills from the CEO. One business on top of them.

You don't fully understand what this integration could turn into. Five skills. Created by the CEO of Obsidian. Released publicly. Free to add. He read it and thought about who would pay him to implement it for them. Law firms. Agencies. Medical practices. All have the same problem, knowledge that lives in someone's head until that person leaves. He builds the vault. Writes the files. Connects Claude. Delivers in three days. $2,200 once. $1,500 every month after. The pitch is one sentence: your new employee will read every process, every client file, and every decision made in the last three years before their first day. 6 clients. $9,000 a month. 10 hours of work a week. Five skills from the CEO. One business on top of them.

Superior

28,320 次观看 • 3 天前

A JAPANESE GUY BUILT A 200,000-SUBSCRIBER DINOSAUR CHANNEL THAT CAN MAKE $10K - $15K/MONTH At first, the channel looks stupid: cartoon dinosaurs, kids stories, bright thumbnails and 278 videos built around the same simple format. But that is exactly why it works. One niche, one audience, one repeatable machine. The setup can cost less than $100/month: AI voice, basic visuals, editing tools and thumbnails. No camera, no studio, no actor, no personal brand. Just a pipeline that can keep producing the same type of video every week. The real system is not the cartoon. Claude writes the script, hook, title, description, tags and retention points, then the rest becomes assembly: voiceover, visuals, thumbnail, upload, repeat. Run this for 6-12 months and the numbers start getting stupid. Kids content has endless topics, YouTube understands the audience fast, and every new upload feeds the same channel. Most people see cheap dinosaur cartoons. A smarter person sees a faceless media factory that can keep producing while the owner sleeps.

Gipp 🦅

94,710 次观看 • 2 个月前

A DOCTOR BUILT AN AI-QUERYABLE DATABASE OF EVERY DISEASE HE KNOWS IN OBSIDIAN. THE SAME STACK CAN RUN AN ENTIRE COMPANY ON ONE PERSON'S BRAIN Zoomed out, his vault looks like a constellation. Every disease linked to its symptoms, every symptom to the conditions it shows up in, every treatment to what it treats. Adding a new case is one note that wires itself into the rest. It's a personal database, and the structure has nothing to do with medicine. It's just nodes and links. Once you see that, the same setup runs anything: > a startup that needs to remember every customer, decision, and meeting; > a school whose curriculum links to every lecture and student question; > a business where SOPs, clients, and vendors all sit in one queryable graph. Drop Claude on top, and the vault stops being a map. It becomes something you can ask, in plain English, across everything you've ever written down. Full Claude + Obsidian build in the article below. Bookmark this

A DOCTOR BUILT AN AI-QUERYABLE DATABASE OF EVERY DISEASE HE KNOWS IN OBSIDIAN. THE SAME STACK CAN RUN AN ENTIRE COMPANY ON ONE PERSON'S BRAIN Zoomed out, his vault looks like a constellation. Every disease linked to its symptoms, every symptom to the conditions it shows up in, every treatment to what it treats. Adding a new case is one note that wires itself into the rest. It's a personal database, and the structure has nothing to do with medicine. It's just nodes and links. Once you see that, the same setup runs anything: > a startup that needs to remember every customer, decision, and meeting; > a school whose curriculum links to every lecture and student question; > a business where SOPs, clients, and vendors all sit in one queryable graph. Drop Claude on top, and the vault stops being a map. It becomes something you can ask, in plain English, across everything you've ever written down. Full Claude + Obsidian build in the article below. Bookmark this

Yarchi

32,382 次观看 • 25 天前

MICROSOFT JUST RELEASED A FREE TOOL THAT SLASHES CLAUDE TOKEN COSTS BY 70% LLMs: eating 3,000 tokens per PDF page just to parse broken tables. context windows burned before you ask the first question. one MCP server command. zero manual copy-pasting. Microsoft's "MarkItDown" auto-converts PDFs, Excel sheets, and YouTube videos into raw Markdown. 10 clients at $1,500/month automated content engine = $15,000/month. from a single n8n workflow. while you sleep. > MarkItDown . Claude Code . n8n agencies are firing human copywriters because of token limits. this setup didn't. HOW TO BUILD A 1-MAN B2B CONTENT FACTORY (STEP-BY-STEP) 👇 1/ THE PROBLEM When you feed Claude a raw PDF or YouTube URL, it wastes massive computational power scraping junk formatting. You are literally burning money on token overhead. 2/ THE PIPELINE Inbound: Client drops raw webinars, technical docs, or zoom recordings into a Google Drive folder. The Clean: MarkItDown auto-triggers via Python script, stripping images and converting everything into clean .md. The Scale: Claude processes the native Markdown instantly, saving 70% on context limits. 3/ THE PRODUCT LINE The Knowledge Base: Turning chaotic corporate files into a structured Obsidian/Notion workspace. The Content Engine: Turn ONE 60-minute client webinar into 1 long-form article, 5 TG posts, and 3 high-engagement X threads. 4/ THE COLD OUTBOUND HACK Pick an expert's YouTube video. Run it through MarkItDown + Claude. DM them the polished, high-value thread with: "Hey, turned your video into this in 5 minutes. I can ship 30 of these a month. Let’s talk." 5/ INFRASTRUCTURE Once the prompt logic is dialed in, spin up AI agents via n8n to handle fetching, converting, and formatting. Your only job is a 60-second QA check before shipping to the client.

MICROSOFT JUST RELEASED A FREE TOOL THAT SLASHES CLAUDE TOKEN COSTS BY 70% LLMs: eating 3,000 tokens per PDF page just to parse broken tables. context windows burned before you ask the first question. one MCP server command. zero manual copy-pasting. Microsoft's "MarkItDown" auto-converts PDFs, Excel sheets, and YouTube videos into raw Markdown. 10 clients at $1,500/month automated content engine = $15,000/month. from a single n8n workflow. while you sleep. > MarkItDown . Claude Code . n8n agencies are firing human copywriters because of token limits. this setup didn't. HOW TO BUILD A 1-MAN B2B CONTENT FACTORY (STEP-BY-STEP) 👇 1/ THE PROBLEM When you feed Claude a raw PDF or YouTube URL, it wastes massive computational power scraping junk formatting. You are literally burning money on token overhead. 2/ THE PIPELINE Inbound: Client drops raw webinars, technical docs, or zoom recordings into a Google Drive folder. The Clean: MarkItDown auto-triggers via Python script, stripping images and converting everything into clean .md. The Scale: Claude processes the native Markdown instantly, saving 70% on context limits. 3/ THE PRODUCT LINE The Knowledge Base: Turning chaotic corporate files into a structured Obsidian/Notion workspace. The Content Engine: Turn ONE 60-minute client webinar into 1 long-form article, 5 TG posts, and 3 high-engagement X threads. 4/ THE COLD OUTBOUND HACK Pick an expert's YouTube video. Run it through MarkItDown + Claude. DM them the polished, high-value thread with: "Hey, turned your video into this in 5 minutes. I can ship 30 of these a month. Let’s talk." 5/ INFRASTRUCTURE Once the prompt logic is dialed in, spin up AI agents via n8n to handle fetching, converting, and formatting. Your only job is a 60-second QA check before shipping to the client.

Ridark

17,371 次观看 • 1 个月前

Anduril's Jeff Miller breaks down the rules for their new autonomous drone-flying contest, where the prize is a job at Anduril: "All the drones have to be the same. The only differentiator is the software, the code - the ability to build autonomy." "The way we're doing this is, we're working with the Drone Champions League - the foremost operator of AI drone racing in the world. We've got them as our official race operator, and we're working off of the model that they've built, tested, and forged a really viable path." "It starts with virtual qualifiers. Anyone can compete in these virtual qualifiers... That will lead to a physical qualifier where you're going to have gates that you have to go through. The top teams that qualify, both from the university level and across the globe, because it's going to be an open competition, those will qualify for the first official AIGP in Columbus, Ohio." "There, you're going to have time to prep and refine your code leading up to the actual race day. And that's where - all systems go."

Anduril's Jeff Miller breaks down the rules for their new autonomous drone-flying contest, where the prize is a job at Anduril: "All the drones have to be the same. The only differentiator is the software, the code - the ability to build autonomy." "The way we're doing this is, we're working with the Drone Champions League - the foremost operator of AI drone racing in the world. We've got them as our official race operator, and we're working off of the model that they've built, tested, and forged a really viable path." "It starts with virtual qualifiers. Anyone can compete in these virtual qualifiers... That will lead to a physical qualifier where you're going to have gates that you have to go through. The top teams that qualify, both from the university level and across the globe, because it's going to be an open competition, those will qualify for the first official AIGP in Columbus, Ohio." "There, you're going to have time to prep and refine your code leading up to the actual race day. And that's where - all systems go."

TBPN

19,111 次观看 • 5 个月前

THIS VETERAN DEVELOPER PUT 2 MAC MINIS ON HIS DESK FOR $1,198 AND TURNED HERMES INTO A LOCAL AI WORKSPACE THAT DOESN’T NEED A $210/MONTH AGENT STACK he is not flexing hardware. he is showing the part most people still miss: once Hermes runs locally, the laptop stops being a chat window and starts acting like a workspace with memory, tools and saved skills two Mac minis, one local setup, zero cloud agent dashboard. research tasks, summaries, client notes and workflow steps stay on his machine instead of disappearing every time a session ends most people keep paying for Claude, wrappers, API calls and automation tools just to repeat the same instructions every day. Hermes cuts the waste by saving the process once and pulling it back when the same job returns the math is ugly for cloud tools. $210/month turns into $2,520/year before you even count extra tokens. his version is hardware once, local workflows after, and no panic when rate limits hit the quiet winners will not be the people with the cleanest chatbot tab. it will be the people who own the machine, the memory and the workflow before everyone else realizes that is the product

THIS VETERAN DEVELOPER PUT 2 MAC MINIS ON HIS DESK FOR $1,198 AND TURNED HERMES INTO A LOCAL AI WORKSPACE THAT DOESN’T NEED A $210/MONTH AGENT STACK he is not flexing hardware. he is showing the part most people still miss: once Hermes runs locally, the laptop stops being a chat window and starts acting like a workspace with memory, tools and saved skills two Mac minis, one local setup, zero cloud agent dashboard. research tasks, summaries, client notes and workflow steps stay on his machine instead of disappearing every time a session ends most people keep paying for Claude, wrappers, API calls and automation tools just to repeat the same instructions every day. Hermes cuts the waste by saving the process once and pulling it back when the same job returns the math is ugly for cloud tools. $210/month turns into $2,520/year before you even count extra tokens. his version is hardware once, local workflows after, and no panic when rate limits hit the quiet winners will not be the people with the cleanest chatbot tab. it will be the people who own the machine, the memory and the workflow before everyone else realizes that is the product

Gipp 🦅

60,173 次观看 • 1 个月前

This scene always makes me think about what markets do once a simple asset story is no longer enough. At first people buy the thing itself. Then, at some point, that stops being exciting enough. So the market starts building layers around it. A structure. A wrapper. A more financial version of the same idea. That is why MSTR comes to mind for me here. Not because it is the same as a synthetic CDO. It obviously is not. But because the instinct feels familiar. If you believe in Bitcoin, the clean path is simple. You buy Bitcoin. If you want a more traditional route, you buy the ETF. That should be enough. But MSTR is something else entirely. It is Bitcoin, turned into a corporate vehicle, then turned into a capital markets machine, then turned into a narrative people are willing to value differently from the asset underneath it. And that is where it starts feeling less like pure exposure and more like financial engineering built around exposure. We have seen this movie before in different forms. Markets love taking a real asset, wrapping it in a new story, and then assigning the wrapper a value that starts drifting away from the thing it actually holds. As long as that premium stays alive, the machine keeps working. More demand for the structure. More capital raised. More accumulation. Bigger story. More believers. On the way up, it all looks brilliant. That is always the seductive part. In strong markets, even very simple reflexive loops can look like genius. The real question only shows up later, when the mood changes and people start asking whether the value was in the underlying asset all along, or in the extra meaning the market temporarily assigned to the structure built around it. That is why I find this clip so relevant. It is not just a reminder of 2008. It is a reminder of a deeper market habit. People rarely stop at owning the thing. They almost always find a way to build another layer on top of it. And to me, that is the more interesting question around MSTR. Not how much more Bitcoin it can buy. But how long the market will keep rewarding the wrapper more than the thing inside it.

This scene always makes me think about what markets do once a simple asset story is no longer enough. At first people buy the thing itself. Then, at some point, that stops being exciting enough. So the market starts building layers around it. A structure. A wrapper. A more financial version of the same idea. That is why MSTR comes to mind for me here. Not because it is the same as a synthetic CDO. It obviously is not. But because the instinct feels familiar. If you believe in Bitcoin, the clean path is simple. You buy Bitcoin. If you want a more traditional route, you buy the ETF. That should be enough. But MSTR is something else entirely. It is Bitcoin, turned into a corporate vehicle, then turned into a capital markets machine, then turned into a narrative people are willing to value differently from the asset underneath it. And that is where it starts feeling less like pure exposure and more like financial engineering built around exposure. We have seen this movie before in different forms. Markets love taking a real asset, wrapping it in a new story, and then assigning the wrapper a value that starts drifting away from the thing it actually holds. As long as that premium stays alive, the machine keeps working. More demand for the structure. More capital raised. More accumulation. Bigger story. More believers. On the way up, it all looks brilliant. That is always the seductive part. In strong markets, even very simple reflexive loops can look like genius. The real question only shows up later, when the mood changes and people start asking whether the value was in the underlying asset all along, or in the extra meaning the market temporarily assigned to the structure built around it. That is why I find this clip so relevant. It is not just a reminder of 2008. It is a reminder of a deeper market habit. People rarely stop at owning the thing. They almost always find a way to build another layer on top of it. And to me, that is the more interesting question around MSTR. Not how much more Bitcoin it can buy. But how long the market will keep rewarding the wrapper more than the thing inside it.

Mercek

14,644 次观看 • 3 个月前

THE OBSIDIAN CEO BUILT 5 CLAUDE CODE SKILLS, AND NOW A 2,400 NOTE VAULT CAN SORT ITSELF AT 7 A.M., FIX BROKEN LINKS, AND RESURFACE IDEAS FROM 2019 IN 10 SECONDS 00:06 he loads the obsidian skill inside claude code, and the graph stops being decoration. claude can read markdown, follow backlinks, edit canvas files, repair dead links, pull project context, and move through the vault like it understands the workspace instead of guessing from one prompt. most people do not have a note problem. they have an abandoned memory problem: 800 notes, 12 folders, 40 unfinished drafts, and a beautiful graph view that never actually helps. the article shows a 33 year old editor with 2,400 markdown files, 8 years of thinking, and zero useful access for a full year. that is why the ceo angle matters. this is not another random plugin. it is claude code learning obsidian’s actual language: backlinks, daily notes, canvas boards, raw captures, processed ideas, broken references, and old drafts buried so deep they might as well be gone. a real system only needs a few rules. one inbox for messy thoughts, one raw folder nobody edits, three backlinks on every new note, and a 7 a.m. run that sorts yesterday before you even open the laptop. weekly synthesis is where it gets dangerous. claude can compress 7 days of notes into one file with themes, contradictions, abandoned ideas, repeated promises, and the exact old note where the next article was hiding. bookmark this before your second brain becomes 2,400 dead files with a pretty graph.

THE OBSIDIAN CEO BUILT 5 CLAUDE CODE SKILLS, AND NOW A 2,400 NOTE VAULT CAN SORT ITSELF AT 7 A.M., FIX BROKEN LINKS, AND RESURFACE IDEAS FROM 2019 IN 10 SECONDS 00:06 he loads the obsidian skill inside claude code, and the graph stops being decoration. claude can read markdown, follow backlinks, edit canvas files, repair dead links, pull project context, and move through the vault like it understands the workspace instead of guessing from one prompt. most people do not have a note problem. they have an abandoned memory problem: 800 notes, 12 folders, 40 unfinished drafts, and a beautiful graph view that never actually helps. the article shows a 33 year old editor with 2,400 markdown files, 8 years of thinking, and zero useful access for a full year. that is why the ceo angle matters. this is not another random plugin. it is claude code learning obsidian’s actual language: backlinks, daily notes, canvas boards, raw captures, processed ideas, broken references, and old drafts buried so deep they might as well be gone. a real system only needs a few rules. one inbox for messy thoughts, one raw folder nobody edits, three backlinks on every new note, and a 7 a.m. run that sorts yesterday before you even open the laptop. weekly synthesis is where it gets dangerous. claude can compress 7 days of notes into one file with themes, contradictions, abandoned ideas, repeated promises, and the exact old note where the next article was hiding. bookmark this before your second brain becomes 2,400 dead files with a pretty graph.

Gipp 🦅

17,790 次观看 • 9 天前

If you're hitting Claude Code's context limit, check your terminal output before blaming your project size. Every command Claude runs dumps raw output into your context window. git status : 76% of it is noise. A failed cargo test : 155 lines becomes 3. A grep across your codebase : same story You're not running out of context because your code is too big. You're running out because the commands are bleeding you dry before you get anywhere. RTK intercepts that output, compresses it, and hands Claude a clean version instead. 60–90% fewer tokens. Same information. Runs in the background after a one-command setup. Real numbers from 2,900+ commands: average 89% compression across the board. MIT license. Free. 39k GitHub stars. rtk init -g That's it. Restart Claude Code and every command is compressed automatically.

If you're hitting Claude Code's context limit, check your terminal output before blaming your project size. Every command Claude runs dumps raw output into your context window. git status : 76% of it is noise. A failed cargo test : 155 lines becomes 3. A grep across your codebase : same story You're not running out of context because your code is too big. You're running out because the commands are bleeding you dry before you get anywhere. RTK intercepts that output, compresses it, and hands Claude a clean version instead. 60–90% fewer tokens. Same information. Runs in the background after a one-command setup. Real numbers from 2,900+ commands: average 89% compression across the board. MIT license. Free. 39k GitHub stars. rtk init -g That's it. Restart Claude Code and every command is compressed automatically.

Charlie Hills

16,666 次观看 • 2 个月前

Read the actual Anthropic piece. It's wilder than the hype precisely because it's so measured. As of last month, Claude writes more than 80% of the code Anthropic merges into its own codebase. Their engineers now ship roughly 8x the code per day they did in 2024. On a fixed test they run every release (take some training code, make it run faster), the model went from ~3x a year ago to ~52x. A skilled human gets about 4x in a few hours. And when a researcher hits a wrong turn mid-investigation, the newest model now picks the better next step 64% of the time. The honest part the hype skips is that Anthropic says we are NOT at self-improvement yet. Claude still can't decide which problems are worth solving. That research taste is the last thing keeping a human in the loop. But they openly map the moment it closes, when agents can build and train models themselves and Claude starts improving Claude. And the loudest signal in the whole thing sits at the end: the company building this is the one asking for a working pause button before the loop closes.

Read the actual Anthropic piece. It's wilder than the hype precisely because it's so measured. As of last month, Claude writes more than 80% of the code Anthropic merges into its own codebase. Their engineers now ship roughly 8x the code per day they did in 2024. On a fixed test they run every release (take some training code, make it run faster), the model went from ~3x a year ago to ~52x. A skilled human gets about 4x in a few hours. And when a researcher hits a wrong turn mid-investigation, the newest model now picks the better next step 64% of the time. The honest part the hype skips is that Anthropic says we are NOT at self-improvement yet. Claude still can't decide which problems are worth solving. That research taste is the last thing keeping a human in the loop. But they openly map the moment it closes, when agents can build and train models themselves and Claude starts improving Claude. And the loudest signal in the whole thing sits at the end: the company building this is the one asking for a working pause button before the loop closes.

Alex Veremeyenko

33,666 次观看 • 1 个月前