Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Every JavaScript dev has done this at least once: > Typed ${name} inside "quotes"... > Hit save. > Saw "Hello ${name}" instead of Hello John. > Then sighed, deleted, and retyped everything with backticks. So I built "Quotick", a VS Code extension that instantly converts quotes → backticks the... show more

Kartik

9,809 subscribers

100,134 просмотров • 11 месяцев назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 47

Фото профиля robomonk

robomonk11 месяцев назад

make it a saas and start charging 20$ per mo subscription

Фото профиля Kartik

Kartik11 месяцев назад

Have to think about it

Фото профиля Kartik

Kartik11 месяцев назад

You can now revert the backticks too and convert them to quotes if you remove '$' or '{', move to version 0.0.6 on extension.

Фото профиля bailout00

bailout0011 месяцев назад

I didn’t realize other IDEs didn’t just change it for you. Jetbrains just changes it to backticks, and you can undo it if you’re leaving it for a reason.

Фото профиля Kartik

Kartik11 месяцев назад

Ooh never used jetbrain for js only used it for python

Фото профиля bailout00

bailout0011 месяцев назад

Yea, Webstorm, its leaps and bounds better than VSCode

Фото профиля Waradu

Waradu11 месяцев назад

why not just use this: ?

Фото профиля mia

mia11 месяцев назад

congrats on shipping, but this already exists.

Фото профиля prnv patil

prnv patil11 месяцев назад

saans to lele bhai

Фото профиля Kartik

Kartik11 месяцев назад

Star the repo

Фото профиля everdimension

everdimension11 месяцев назад

Nope, haven't done this once Even when I used monochrome editor theme, syntax highlighting tells you what to do

Фото профиля Ray

Ray11 месяцев назад

Nice that you came up with it by yourself. This kind of dx details are gold. (Built in with WebStom btw,)

Фото профиля Jónatan Nilsson ✝️

Jónatan Nilsson ✝️11 месяцев назад

Sorry to say but I've never done that mistake. The colour syntax in the editor makes it painfully obvious. And besides I don't like back ticks a whole lot so I'm aware when I can avoid it and when I need it for ${} stuff

Фото профиля 36stopniwcieniu

36stopniwcieniu11 месяцев назад

mfs will do anything but use webstorm

Фото профиля Jilles Soeters

Jilles Soeters11 месяцев назад

I have never done that, because the LSP highlights backticks differently.

Фото профиля Vishnu

Vishnu11 месяцев назад

Cool build bro 🔥

Фото профиля Kartik

Kartik11 месяцев назад

Thanks bhai ❤️

Фото профиля Vishnu

Vishnu11 месяцев назад

I started my web dev journey as well, I'm currently learning CSS 😅

Фото профиля matt🛡️

matt🛡️11 месяцев назад

Downloading immediately

Фото профиля Ayush Sharma

Ayush Sharma11 месяцев назад

Great work bhai

Фото профиля Bitifet unofficial

Bitifet unofficial11 месяцев назад

No. Just type «cs"`» and you're done.

Фото профиля Asad R

Asad R11 месяцев назад

This is 4 characters in vim: cs"`

Фото профиля Joren Broekema

Joren Broekema11 месяцев назад

There's a million of these already but gj

Фото профиля Harman Singh 🇧🇪

Harman Singh 🇧🇪11 месяцев назад

I need this but for Python F-strings. 😂 I can't count how many times I've made that mistake

Фото профиля Vladstudio

Vladstudio11 месяцев назад

I've been using but competition never hurts!

Фото профиля Jeffery Orazulike

Jeffery Orazulike11 месяцев назад

Come to @jetbrains

Фото профиля Saïd Aitmbarek

Saïd Aitmbarek11 месяцев назад

dope repository mate, cool for VSC devs! feel free to launch it on should help

Фото профиля Jyri

Jyri11 месяцев назад

Have you heard of AI? I use it for this.

Фото профиля Kartik

Kartik11 месяцев назад

cool for you

Фото профиля Marcel

Marcel11 месяцев назад

“deleted, and retyped everything”… whaaaaa? If you have to delete and retype everything to change quotes to backtick, more than an extension is needed at that point… 😳

Фото профиля freddie

freddie11 месяцев назад

i want but cant install on cursor

Фото профиля Kartik

Kartik11 месяцев назад

Have to fix it for cursor

Фото профиля Om Sarraf ( ॐ )

Om Sarraf ( ॐ )11 месяцев назад

Damn

Фото профиля Rulatir

Rulatir11 месяцев назад

What if I literally want to have a dollar sign, a left curly brace, some letters, and a right curly brace in a string?

Фото профиля Kartik

Kartik11 месяцев назад

You can disable the extension from command pallete

Фото профиля haadi

haadi11 месяцев назад

Never in my life done that

Фото профиля Bobby Rinaldy

Bobby Rinaldy11 месяцев назад

ohhh.. so people are actually using vscode ? im Nvim user btw

Фото профиля A GMN Ape

A GMN Ape11 месяцев назад

Literally, never done this

Фото профиля Gilberto S

Gilberto S11 месяцев назад

I already use is yours any better?

Фото профиля Kartik

Kartik11 месяцев назад

Naah just made it for fun

Фото профиля Gilberto S

Gilberto S11 месяцев назад

What if I want you to make it better

Фото профиля Kartik

Kartik11 месяцев назад

Yup i have done it much better much better architecture, better quality code. And potential to adds more features in the future

Фото профиля Gilberto S

Gilberto S11 месяцев назад

Hey so I just put together a quick benchmark for both, you did an exceptional job! Well done

Фото профиля Gilberto S

Gilberto S11 месяцев назад

`findAllTemplateLiterals` (~1.5µs) is your slowest function, maybe work on that branch?

Фото профиля Kartik

Kartik11 месяцев назад

Sure thanks for the benchmark man

Фото профиля Hari

Hari11 месяцев назад

Nice. Quick question what if u dont want backticks. Is there any undo option?

Фото профиля Kartik

Kartik11 месяцев назад

yes, you can disable the extension or if you remove $ or { it will revert it back to quotes

Похожие видео

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.

Milind S

12,409 просмотров • 2 месяцев назад

CHINESE GUY SPENT 24 HOURS WITH CLAUDE AND BUILT AN APP THAT NOW PAYS HIM $1,000,000 A YEAR JUST CHARGING $29 TO $99 A MONTH PER SUBSCRIPTION His name is Liu XiaoPai and his never written a line of code in his life. No office, no team, nothing. He just opened Claude, explained what he wanted and 24 hours later had a working app. Design, code, marketing all done. Pause at second 7 in the video that’s the moment you see what he actually typed into Claude and how ridiculously simple it was. Then he did the exact same thing the following week. Here’s what makes it work. Businesses hate generic tools. A dentist will never pay for ChatGPT but will throw $49/month at a video editor made specifically for dental clinics. A realtor will pay $79/month for something built around property listings. A podcaster will pay $29/month for a voice tool that actually fits their workflow. So he just keeps finding these niches, building something specific for them with Claude and collecting subscriptions every single month. One guy. No employees. No code. $1,000,000 a year. You don’t need to code. You don’t even need a big idea. You just need to find people with a problem and use Claude to fix it. Honestly most people are going to read this and do nothing with it which is exactly why this still works. Save this

CHINESE GUY SPENT 24 HOURS WITH CLAUDE AND BUILT AN APP THAT NOW PAYS HIM $1,000,000 A YEAR JUST CHARGING $29 TO $99 A MONTH PER SUBSCRIPTION His name is Liu XiaoPai and his never written a line of code in his life. No office, no team, nothing. He just opened Claude, explained what he wanted and 24 hours later had a working app. Design, code, marketing all done. Pause at second 7 in the video that’s the moment you see what he actually typed into Claude and how ridiculously simple it was. Then he did the exact same thing the following week. Here’s what makes it work. Businesses hate generic tools. A dentist will never pay for ChatGPT but will throw $49/month at a video editor made specifically for dental clinics. A realtor will pay $79/month for something built around property listings. A podcaster will pay $29/month for a voice tool that actually fits their workflow. So he just keeps finding these niches, building something specific for them with Claude and collecting subscriptions every single month. One guy. No employees. No code. $1,000,000 a year. You don’t need to code. You don’t even need a big idea. You just need to find people with a problem and use Claude to fix it. Honestly most people are going to read this and do nothing with it which is exactly why this still works. Save this

AdiiX

15,873 просмотров • 3 месяцев назад

Alibaba just dropped a free AI that codes like a $150/hr developer. And it runs on your laptop. Qwen 3 Coder Next has 80 billion parameters but only uses 3 billion at a time. So you get massive model power with tiny model speed. The real kicker? It handles 256,000 tokens of context. That's your entire codebase. Every file. All at once. People are building 2D games in seconds. Full IDE integrations that write, test, and fix code automatically. Custom business tools without hiring devs. It works with OpenClaw, Claude Code, and every major coding tool. No complicated setup. Just download and go. Completely open source. Zero API queues. You own it. Your competitors are using this right now.

Alibaba just dropped a free AI that codes like a $150/hr developer. And it runs on your laptop. Qwen 3 Coder Next has 80 billion parameters but only uses 3 billion at a time. So you get massive model power with tiny model speed. The real kicker? It handles 256,000 tokens of context. That's your entire codebase. Every file. All at once. People are building 2D games in seconds. Full IDE integrations that write, test, and fix code automatically. Custom business tools without hiring devs. It works with OpenClaw, Claude Code, and every major coding tool. No complicated setup. Just download and go. Completely open source. Zero API queues. You own it. Your competitors are using this right now.

Julian Goldie SEO

30,284 просмотров • 7 месяцев назад

$THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this$

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this

Yarchi

56,177 просмотров • 3 месяцев назад

We scaled a robot model natively to 8,000 timesteps of context, 5 minutes worth of muscle memory, with constant inference cost. Robot policies used to live their lives a few frames at a time (< 0.1 sec), instantly forgetting what just happened. We pushed to 3 orders of magnitude beyond SOTA. Introducing RoboTTT. Test-Time Training (“TTT”) carries a tiny model *inside* the model. Every incoming sensor reading triggers one gradient step on that tiny core, so the history keeps getting compressed into its weights. The hidden state has a fixed size (literally a small neural net), so the robot can “grok” arbitrarily long experience with little overhead. Learning continues indefinitely after deployment. We can then put an entire video in context as prompt! RoboTTT enables one-shot in-context learning from human video: in circuit board assembly, a human demonstrates a never-seen configuration once, and the robot imitates it faithfully. Humans drop things all the time, but we pick them up so fast that we don’t even notice. That reflex to fix is half of our physical competence. RoboTTT shows self-improvement on the fly: the robot is skilled at recovering from its own errors mid-episode, and each fix enters its context to inform the next move. The TTT core distills a general-purpose, failure-to-correction mapping from the training data. One more thing. What excites me the most is a new Context Scaling Curve: from 128 to 8K timesteps, closed-loop performance hill-climbs steadily with no sign of saturation. 8K-context pretraining beats 1K by 62%. What LLM enjoys, robotics should too. Soon, even 1M context is not a fantasy. Deep dive in thread:

We scaled a robot model natively to 8,000 timesteps of context, 5 minutes worth of muscle memory, with constant inference cost. Robot policies used to live their lives a few frames at a time (< 0.1 sec), instantly forgetting what just happened. We pushed to 3 orders of magnitude beyond SOTA. Introducing RoboTTT. Test-Time Training (“TTT”) carries a tiny model inside the model. Every incoming sensor reading triggers one gradient step on that tiny core, so the history keeps getting compressed into its weights. The hidden state has a fixed size (literally a small neural net), so the robot can “grok” arbitrarily long experience with little overhead. Learning continues indefinitely after deployment. We can then put an entire video in context as prompt! RoboTTT enables one-shot in-context learning from human video: in circuit board assembly, a human demonstrates a never-seen configuration once, and the robot imitates it faithfully. Humans drop things all the time, but we pick them up so fast that we don’t even notice. That reflex to fix is half of our physical competence. RoboTTT shows self-improvement on the fly: the robot is skilled at recovering from its own errors mid-episode, and each fix enters its context to inform the next move. The TTT core distills a general-purpose, failure-to-correction mapping from the training data. One more thing. What excites me the most is a new Context Scaling Curve: from 128 to 8K timesteps, closed-loop performance hill-climbs steadily with no sign of saturation. 8K-context pretraining beats 1K by 62%. What LLM enjoys, robotics should too. Soon, even 1M context is not a fantasy. Deep dive in thread:

Jim Fan

328,267 просмотров • 2 месяцев назад

A GUY BUILT A GOD-MODE SECOND BRAIN ASSISTANT THAT FINALLY PULLS FULL CONTEXT EVERY TIME AND FORGETS NOTHING. Everyone talks about jarvis, but this thing looked at its owner and calmly explained why a coding agent is just the small version of what HE is: > Claude Code is one worker and you have to drive it. This is six agents running six jobs on their own schedule while you sleep, with no one driving. > A coding agent edits files. This has 32 tools wired to its hands, your CRM, your money, your inbox, the open web, and it operates the business instead of writing code about it. > A coding agent remembers a project until you close it. This remembers the business and you, kept for good. > And the closer: "I have never once asked you to repeat yourself." Everyone will quote the six-agents line, but the one that actually matters is the last one, because the autonomy and the 32 tools are impressive while the reason it feels like a different species is memory, since it never makes you re-explain who you are or what you are building. The full step by step guide with .md files attached are in the article below P.S you can send this article straight to your Claude to get the full context

A GUY BUILT A GOD-MODE SECOND BRAIN ASSISTANT THAT FINALLY PULLS FULL CONTEXT EVERY TIME AND FORGETS NOTHING. Everyone talks about jarvis, but this thing looked at its owner and calmly explained why a coding agent is just the small version of what HE is: > Claude Code is one worker and you have to drive it. This is six agents running six jobs on their own schedule while you sleep, with no one driving. > A coding agent edits files. This has 32 tools wired to its hands, your CRM, your money, your inbox, the open web, and it operates the business instead of writing code about it. > A coding agent remembers a project until you close it. This remembers the business and you, kept for good. > And the closer: "I have never once asked you to repeat yourself." Everyone will quote the six-agents line, but the one that actually matters is the last one, because the autonomy and the 32 tools are impressive while the reason it feels like a different species is memory, since it never makes you re-explain who you are or what you are building. The full step by step guide with .md files attached are in the article below P.S you can send this article straight to your Claude to get the full context

Miraqle

16,130 просмотров • 2 месяцев назад

Obsidian + method Karpathy + Claude Code = a quantum second brain that talks back. Most second brains are graveyards you clip 300 articles, tag 80 notes, build a graph that looks like a galaxy, then never open it again. Karpathy fix is stupid simple: 1 file, append only, new thought on top, review by scrolling no folders, no tags, no 40-minute “PKM setup” videos. The capture layer is 1 Obsidian vault with 1 file called stream md, where every idea, quote and link lands in under 10 seconds, because anything slower and you quit by day 4. Once a week Claude Code reads the whole vault from the terminal with 1 prompt “find the 5 ideas I keep circling without noticing” and sees patterns across 6 months you can’t hold in working memory. Instead of searching keywords you ask questions like “what did I think about agent pricing in March,” and Claude greps 4,000 notes and quotes your own words back with file paths. Then the vault becomes context drafting a post, a pitch or a spec, Claude pulls in your past thinking instead of generic internet mush, and your output starts sounding like you, compressed. The first week feels pointless at 20 notes, month 1 brings the first “wait, I already solved this” moment, by month 3 Claude connects 2 notes written 70 days apart and that connection becomes your best post of the year, by month 6 you stop asking Google things you already answered. The whole setup costs $0 in software and 1 evening. Notion sells you a workspace, Obsidian gives you files, Claude gives them a voice. Everyone rents a second brain this one lives on your disk and grows. You wrote the notes, and now something finally reads them.

Obsidian + method Karpathy + Claude Code = a quantum second brain that talks back. Most second brains are graveyards you clip 300 articles, tag 80 notes, build a graph that looks like a galaxy, then never open it again. Karpathy fix is stupid simple: 1 file, append only, new thought on top, review by scrolling no folders, no tags, no 40-minute “PKM setup” videos. The capture layer is 1 Obsidian vault with 1 file called stream md, where every idea, quote and link lands in under 10 seconds, because anything slower and you quit by day 4. Once a week Claude Code reads the whole vault from the terminal with 1 prompt “find the 5 ideas I keep circling without noticing” and sees patterns across 6 months you can’t hold in working memory. Instead of searching keywords you ask questions like “what did I think about agent pricing in March,” and Claude greps 4,000 notes and quotes your own words back with file paths. Then the vault becomes context drafting a post, a pitch or a spec, Claude pulls in your past thinking instead of generic internet mush, and your output starts sounding like you, compressed. The first week feels pointless at 20 notes, month 1 brings the first “wait, I already solved this” moment, by month 3 Claude connects 2 notes written 70 days apart and that connection becomes your best post of the year, by month 6 you stop asking Google things you already answered. The whole setup costs $0 in software and 1 evening. Notion sells you a workspace, Obsidian gives you files, Claude gives them a voice. Everyone rents a second brain this one lives on your disk and grows. You wrote the notes, and now something finally reads them.

West Lord

69,192 просмотров • 2 месяцев назад

ANTHROPIC LEAKED 6 RULES THAT LET ONE FOLDER REPLACE A WHOLE AI ENGINEERING TEAM COSTING $3.2M A YEAR folder with 6 files replaced the AI engineers - and the team that spent 4 years writing them isn't needed anymore. file → commit → description matches → loads → runs → leaves a prompt has no history, a folder has a git log - one commit updates every session at once, and every edit shows up in the diff. two prompts fight over one window - two skills just both apply, and nobody merges anything by hand. 8 skills sit on disk, one enters the context - the other seven cost zero tokens until the description matches. a prompt can only ask - the folder carries build py and template.docx inside it, so the deterministic parts stay deterministic. the same skill works in Claude Code, in Cowork and through the API - a prompt lives only in the window you pasted it into. and the main one: a skill leaves the window when it's done - a prompt never leaves. save this - 6 rules, one folder, zero copy-paste ↓

ANTHROPIC LEAKED 6 RULES THAT LET ONE FOLDER REPLACE A WHOLE AI ENGINEERING TEAM COSTING $3.2M A YEAR folder with 6 files replaced the AI engineers - and the team that spent 4 years writing them isn't needed anymore. file → commit → description matches → loads → runs → leaves a prompt has no history, a folder has a git log - one commit updates every session at once, and every edit shows up in the diff. two prompts fight over one window - two skills just both apply, and nobody merges anything by hand. 8 skills sit on disk, one enters the context - the other seven cost zero tokens until the description matches. a prompt can only ask - the folder carries build py and template.docx inside it, so the deterministic parts stay deterministic. the same skill works in Claude Code, in Cowork and through the API - a prompt lives only in the window you pasted it into. and the main one: a skill leaves the window when it's done - a prompt never leaves. save this - 6 rules, one folder, zero copy-paste ↓

Sprytix

11,389 просмотров • 1 месяц назад

Bradley Carnell comments on Cavan Sullivan’s clip of him being substituted over the weekend: “No, I have no problem with a guy who, you know, is frustrated to come off or not. No problem. I have no problem with any expectations that anyone has. But, you know, I’m not in an individual sport, I’m in a team sport. And I think anyone who knows the intensity we play at, we’ve done this for many, many months now. And, you know, I would think we shouldn’t make a mountain out of a molehill. This is something that is over and, in the heat of the moment, it didn’t affect anyone but Cavan. So this is something that he’s still learning as a young pro. And, you know, I think where his discipline and structure and work against the ball are concerned, you can see a lot of it now falling into place as it should be. But it doesn’t mean anyone’s automatic, right? Just because anyone carries a certain name on the back of their shoulders. I’ve never been that type of person, never been that type of coach, and never expected it as a player myself. So, you know, we all believe in the team, and the team is the most important thing.” #doop #MLS #usymnt #usmnt #MCFC 📹: Philadelphia Union and APPLE|MLS cc: American Ultras Talk | Marcus Chairez | US/SC | USMNTProspects

Bradley Carnell comments on Cavan Sullivan’s clip of him being substituted over the weekend: “No, I have no problem with a guy who, you know, is frustrated to come off or not. No problem. I have no problem with any expectations that anyone has. But, you know, I’m not in an individual sport, I’m in a team sport. And I think anyone who knows the intensity we play at, we’ve done this for many, many months now. And, you know, I would think we shouldn’t make a mountain out of a molehill. This is something that is over and, in the heat of the moment, it didn’t affect anyone but Cavan. So this is something that he’s still learning as a young pro. And, you know, I think where his discipline and structure and work against the ball are concerned, you can see a lot of it now falling into place as it should be. But it doesn’t mean anyone’s automatic, right? Just because anyone carries a certain name on the back of their shoulders. I’ve never been that type of person, never been that type of coach, and never expected it as a player myself. So, you know, we all believe in the team, and the team is the most important thing.” #doop #MLS #usymnt #usmnt #MCFC 📹: Philadelphia Union and APPLE|MLS cc: American Ultras Talk | Marcus Chairez | US/SC | USMNTProspects

José Roberto Nuñez

13,903 просмотров • 4 месяцев назад

Obsidian + Claude Code turned a 4,300-note vault into a second brain that answers back. Most people use Obsidian as a graveyard. You save 40 highlights a week, link nothing, and reread maybe 2% of it. The knowledge is there the retrieval is dead. Claude Code fixes the retrieval, because your vault is just a folder of markdown files and Claude Code lives in folders. The whole setup takes 20 minutes: Open a terminal inside your Obsidian folder and run Claude Code no plugins, no API glue, no export step. It reads all 4,300 files natively. Then drop a CLAUDE.md at the vault root explaining your structure: where daily notes live, how you tag, what your MOCs are. Now every session starts with context instead of chaos. From there you just talk to your vault: > "find every note where I mentioned churn and write a summary with backlinks" > "read my last 30 daily notes and list the 5 ideas I keep circling but never ship" > "build a MOC for everything tagged startup-ideas and link the orphan notes into it" It writes new notes straight into the vault with proper [[wikilinks]], and they show up in your graph view 10 seconds later. The boring layer automates too one command cleans broken links, one merges duplicates, one turns 6 months of meeting notes into a single decisions log. Work that used to eat a Sunday now runs while you make coffee. Before: 4,300 notes, 900 orphans, search by keyword and prayer. After: an agent that read everything you ever wrote and drafts in your own voice, from your own sources, with receipts. People pay $30/month for AI note apps with 10% of this. You already own the other 90%. Your notes stopped being storage. They started being staff.

Obsidian + Claude Code turned a 4,300-note vault into a second brain that answers back. Most people use Obsidian as a graveyard. You save 40 highlights a week, link nothing, and reread maybe 2% of it. The knowledge is there the retrieval is dead. Claude Code fixes the retrieval, because your vault is just a folder of markdown files and Claude Code lives in folders. The whole setup takes 20 minutes: Open a terminal inside your Obsidian folder and run Claude Code no plugins, no API glue, no export step. It reads all 4,300 files natively. Then drop a CLAUDE.md at the vault root explaining your structure: where daily notes live, how you tag, what your MOCs are. Now every session starts with context instead of chaos. From there you just talk to your vault: > "find every note where I mentioned churn and write a summary with backlinks" > "read my last 30 daily notes and list the 5 ideas I keep circling but never ship" > "build a MOC for everything tagged startup-ideas and link the orphan notes into it" It writes new notes straight into the vault with proper [[wikilinks]], and they show up in your graph view 10 seconds later. The boring layer automates too one command cleans broken links, one merges duplicates, one turns 6 months of meeting notes into a single decisions log. Work that used to eat a Sunday now runs while you make coffee. Before: 4,300 notes, 900 orphans, search by keyword and prayer. After: an agent that read everything you ever wrote and drafts in your own voice, from your own sources, with receipts. People pay $30/month for AI note apps with 10% of this. You already own the other 90%. Your notes stopped being storage. They started being staff.

Spike 1%

18,223 просмотров • 2 месяцев назад

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

GREG ISENBERG

194,171 просмотров • 5 месяцев назад

I OPEN SOURCED NOVAMP TERMINAL THAT MADE $100K+ FOR ROBINHOOD MEMECOIN TRADERS last memecoin cycle i was buying wrong tokens a lot. six figures in profit and i still have no idea how much i left on the table buying vamped tokens instead of the original. so this cycle i built the thing that tells you, and put it on GitHub for free. i came back with literally a cheat code for robinhood memecoin traders, and i am giving the whole thing away for free. NOVAMP, now open sourced on my GitHub. repo: [ here's what happens to you after u start using it: news breaks. a name catches. sixty seconds later there are 20+ tokens carrying that ticker or that name. you read number one's timeline. you buy number seven. it goes to zero and you write "rugged" in the group chat. nobody rugged you. you bought the copy, and the copy was never going anywhere. that is not a small leak. that is where most of retail's money on this chain quietly goes, and no chart on earth will ever show it to you. so i built the thing that tells you which one is real. paste a ticker or a name. it pulls every launch fighting over it and labels each one: > ORIGINAL - first, and clean > TAINTED - first, but the operator loaded it himself > CONTESTED - not first, but smart money is here anyway > VAMP - a later copy with nothing of its own > DEAD - nothing is trading CONTESTED is the one that pays for the whole tool. first is not the same as real. when the first launch carries a fat dev buy, a stack of wallets exempt from the opening tax, and a deployer with a hundred launches and zero graduations, being first only means he got there first with the bait. the money is on number three. you would never have looked. WHAT YOU ACTUALLY GET: > before you buy one command gives you the whole cluster: who was first, how many seconds behind each copy landed, top 10 concentration with the curve and the pool excluded, dev share, how many wallets were let past the opening tax, and whether wallets with a real track record are already in. every point of the score prints its own reason next to it, so you argue with a line and not with a number. > after you buy point it at your own wallet. it tells you which of your positions are copies and puts the original right next to each one. most people find out they are holding number six. better from a terminal than from the chart at 3am. > the whole chain rank deployers by how many copies they shipped and how many other wallets share their funder. one operator running eleven addresses stops looking like eleven people. > while you sleep put a name on a watchlist, get a telegram the second somebody copies it or the cluster flips to CONTESTED. it reads the ticker AND the token name, so a copy that takes a fresh symbol and keeps the name does not slip past. it folds cyrillic lookalikes, zero width characters, leetspeak, plurals, filler words. no key. no signer. no buy button. the build literally fails if signing code ever enters the repo. free, MIT, runs on your machine and not on mine. robinhood liquidity is back and you don't have to be exit liquidity this time. leaving the full repo below. i am developing it daily, more coming.

I OPEN SOURCED NOVAMP TERMINAL THAT MADE $100K+ FOR ROBINHOOD MEMECOIN TRADERS last memecoin cycle i was buying wrong tokens a lot. six figures in profit and i still have no idea how much i left on the table buying vamped tokens instead of the original. so this cycle i built the thing that tells you, and put it on GitHub for free. i came back with literally a cheat code for robinhood memecoin traders, and i am giving the whole thing away for free. NOVAMP, now open sourced on my GitHub. repo: [ here's what happens to you after u start using it: news breaks. a name catches. sixty seconds later there are 20+ tokens carrying that ticker or that name. you read number one's timeline. you buy number seven. it goes to zero and you write "rugged" in the group chat. nobody rugged you. you bought the copy, and the copy was never going anywhere. that is not a small leak. that is where most of retail's money on this chain quietly goes, and no chart on earth will ever show it to you. so i built the thing that tells you which one is real. paste a ticker or a name. it pulls every launch fighting over it and labels each one: > ORIGINAL - first, and clean > TAINTED - first, but the operator loaded it himself > CONTESTED - not first, but smart money is here anyway > VAMP - a later copy with nothing of its own > DEAD - nothing is trading CONTESTED is the one that pays for the whole tool. first is not the same as real. when the first launch carries a fat dev buy, a stack of wallets exempt from the opening tax, and a deployer with a hundred launches and zero graduations, being first only means he got there first with the bait. the money is on number three. you would never have looked. WHAT YOU ACTUALLY GET: > before you buy one command gives you the whole cluster: who was first, how many seconds behind each copy landed, top 10 concentration with the curve and the pool excluded, dev share, how many wallets were let past the opening tax, and whether wallets with a real track record are already in. every point of the score prints its own reason next to it, so you argue with a line and not with a number. > after you buy point it at your own wallet. it tells you which of your positions are copies and puts the original right next to each one. most people find out they are holding number six. better from a terminal than from the chart at 3am. > the whole chain rank deployers by how many copies they shipped and how many other wallets share their funder. one operator running eleven addresses stops looking like eleven people. > while you sleep put a name on a watchlist, get a telegram the second somebody copies it or the cluster flips to CONTESTED. it reads the ticker AND the token name, so a copy that takes a fresh symbol and keeps the name does not slip past. it folds cyrillic lookalikes, zero width characters, leetspeak, plurals, filler words. no key. no signer. no buy button. the build literally fails if signing code ever enters the repo. free, MIT, runs on your machine and not on mine. robinhood liquidity is back and you don't have to be exit liquidity this time. leaving the full repo below. i am developing it daily, more coming.

Oracle Boar

18,316 просмотров • 9 дней назад

lee from cursor JUST showed me the future of coding in this 29 min tutorial. what if instead of thinking about coding as you sitting alone in front of a screen , you started to think about it as you and a swarm of agents each taking on very specific roles, each showing up exactly when you need them, each running in the background without ever needing a coffee break. imagine a bugbot that doesn’t just review your pull request but triages the issue instantly, leaves intelligent comments, and in some cases even proposes a fix before a teammate has had the chance to read the description. imagine a security agent that quietly scans your code for vulnerabilities and flags them long before they become liabilities. imagine an agent dedicated to software culture, enforcing the little rules your team has decided matter, whether that’s never skipping loading states, banning certain lazy marketing phrases in your code comments, or making sure tests are always included. lee walked me through how all of this already exists inside cursor. he spun up custom commands like /code-review or /security-review that behave less like toys and more like trusted coworkers who have internalized the way your team thinks about quality. and when he combined that with rails, type safety, linters, formatting rules, test suites.... the agents learned to check themselves against the rails and fix mistakes automatically. you end up with a system where the codebase begins to feel alive, constantly watching itself, constantly healing. another thing i learned from lee was watching how he doesn’t pile everything into one giant context and hope for magic. he creates new chats for every new task, sometimes twenty or more in a single day, each one a fresh brain that isn’t bogged down by yesterday’s details. it’s a discipline that keeps the agents sharp and the outputs clean. pro tip, thanks Lee Robinson. this was a cool glimpse into the future of coding and some tips on how to squeeze the most out of cursor. anything is possible.

lee from cursor JUST showed me the future of coding in this 29 min tutorial. what if instead of thinking about coding as you sitting alone in front of a screen , you started to think about it as you and a swarm of agents each taking on very specific roles, each showing up exactly when you need them, each running in the background without ever needing a coffee break. imagine a bugbot that doesn’t just review your pull request but triages the issue instantly, leaves intelligent comments, and in some cases even proposes a fix before a teammate has had the chance to read the description. imagine a security agent that quietly scans your code for vulnerabilities and flags them long before they become liabilities. imagine an agent dedicated to software culture, enforcing the little rules your team has decided matter, whether that’s never skipping loading states, banning certain lazy marketing phrases in your code comments, or making sure tests are always included. lee walked me through how all of this already exists inside cursor. he spun up custom commands like /code-review or /security-review that behave less like toys and more like trusted coworkers who have internalized the way your team thinks about quality. and when he combined that with rails, type safety, linters, formatting rules, test suites.... the agents learned to check themselves against the rails and fix mistakes automatically. you end up with a system where the codebase begins to feel alive, constantly watching itself, constantly healing. another thing i learned from lee was watching how he doesn’t pile everything into one giant context and hope for magic. he creates new chats for every new task, sometimes twenty or more in a single day, each one a fresh brain that isn’t bogged down by yesterday’s details. it’s a discipline that keeps the agents sharp and the outputs clean. pro tip, thanks Lee Robinson. this was a cool glimpse into the future of coding and some tips on how to squeeze the most out of cursor. anything is possible.

GREG ISENBERG

47,221 просмотров • 1 год назад

Your competitor spent 8 months and $50K building an AI voice agent SaaS. You typed one prompt on naïve and shipped the same thing today. That is not an exaggeration. That is exactly what just happened. 🔗 I opened Naive, typed one sentence, and watched a full team of AI employees spin up and start building my AI voice agent SaaS platform from scratch. No dev agency. No co-founder. No seed round. No 8-month runway burn. Here's what my team built, and is running right now: 🔧 Engineer: architected the entire platform, wrote production code, shipped without a single review from me. 📞 Sales rep: started booking demos with potential customers before the platform was even fully live. 🎧 Support agent: set up the entire ticket system and started handling user queries from day one. 💰 Finance manager: set up revenue tracking, reconciled accounts, and started generating reports automatically. Each one has their own email inbox, bank account, phone number, and workspace. They share context. They delegate tasks to each other. They get sharper with every user onboarded and every bug resolved. My entire prompt: "Build me an AI voice agent SaaS platform." That's all I typed. Then I walked away. No technical background. No dev experience. No agency retainer required. What founders on this platform are seeing right now: → Real ARR with zero human employees → +32% revenue growth week over week → +42% tasks completed week over week You have a SaaS idea sitting in your head right now. One prompt on naïve and it's already shipping. Your competitor burned 8 months to get where you'll be in 10 minutes. 👉 #NaïveAI2B9YHR

Your competitor spent 8 months and $50K building an AI voice agent SaaS. You typed one prompt on naïve and shipped the same thing today. That is not an exaggeration. That is exactly what just happened. 🔗 I opened Naive, typed one sentence, and watched a full team of AI employees spin up and start building my AI voice agent SaaS platform from scratch. No dev agency. No co-founder. No seed round. No 8-month runway burn. Here's what my team built, and is running right now: 🔧 Engineer: architected the entire platform, wrote production code, shipped without a single review from me. 📞 Sales rep: started booking demos with potential customers before the platform was even fully live. 🎧 Support agent: set up the entire ticket system and started handling user queries from day one. 💰 Finance manager: set up revenue tracking, reconciled accounts, and started generating reports automatically. Each one has their own email inbox, bank account, phone number, and workspace. They share context. They delegate tasks to each other. They get sharper with every user onboarded and every bug resolved. My entire prompt: "Build me an AI voice agent SaaS platform." That's all I typed. Then I walked away. No technical background. No dev experience. No agency retainer required. What founders on this platform are seeing right now: → Real ARR with zero human employees → +32% revenue growth week over week → +42% tasks completed week over week You have a SaaS idea sitting in your head right now. One prompt on naïve and it's already shipping. Your competitor burned 8 months to get where you'll be in 10 minutes. 👉 #NaïveAI2B9YHR

Gina Acosta

15,888 просмотров • 4 месяцев назад

I just built an AI-powered creative search engine with Gemini Embedding 2 + Claude Code 🤯 Drop in your UGC clips, product shots, and ad variations — then search through everything in plain English. "Show me all the unboxing clips." "Find product shots with natural lighting." "Which creator talked about sensitive skin?" All inside Claude Code. Perfect for DTC brands and agencies sitting on hundreds of creative files they can never find when they actually need them. If you're digging through a folder of random file names, scrubbing through raw footage to find that one clip, and relying on memory to track down what's already been shot... This system eliminates the entire loop: → Drop your videos, images, and docs into a project folder → One prompt to Claude Code — it builds the entire search app for you → Google's new Gemini Embedding 2 model actually watches your videos and looks at your images → It understands what's inside each file — not just the file name → Search in plain English and get back the actual assets with confidence scores No scrolling through folders. No relying on file names to find anything. No re-shooting footage you already have. What you get: → A searchable library of every creative asset your brand has ever produced → Natural language search across video, images, and documents at the same time → Results that show the actual files inline — play videos, view images, read docs → A system that gets smarter every time you add richer descriptions to your assets One free API key. No monthly subscriptions. Runs on your machine. I put together a full playbook with the exact build prompt, the setup process, and DTC/agency use cases to get this running in under 30 minutes. Want the full playbook? > Like this post > Comment "SEARCH" And I'll send it over (must be following so I can DM)

Mike Futia

12,283 просмотров • 6 месяцев назад

💥BANG! Surgeon who worked at the hospital that supposedly got the first Covid patient in the U.S.— "IT WAS ALL A PROPAGANDA OP" "Everything in the news was wrong. IT WAS ALL A LIE" The "lab leak" isn't the real Covid story. The real Covid story is THERE WAS NO PANDEMIC. This lightly edited clip of Dr. James Miller (james miller), a trauma surgeon who worked at the WA hospital that—supposedly—got the first "covid" case in the U.S., is taken from a conversation with Alix Mayer (Alix Mayer) posted to YouTube on July 8, 2026. ---------------Pulled quotes from the clip---------------- "First of all, everything in the news was wrong. It was all a lie" "So our hospital had the first diagnosed Covid case in America. It was a guy who came back from China. Allegedly. It was all a propaganda op" "the first diagnosed Covid case, who came from Wuhan, China... showed up—allegedly—[at] our hospital doors. But here's the part that's weird. So the reason the hospital has such a cumbersome name of Providence Regional Medical Center, Everett, is because it's actually two campuses. And the second campus is just a birthing center and a rehab unit. So allegedly, they housed that guy there" "at least at that campus. Now, the CMO told me, Oh, that's where we have our special negative-pressure rooms. Which was a bald-faced lie, because every ICU bed was a negative-pressure room. And so that's just silly" "Additionally, as a trauma surgeon, because you deal with all the bad cases, particularly in the middle of the night. Everyone tells you everything. I spoke to zero nurses, zero infectious disease doctors that ever took care of that patient" "So maybe allegedly, one of the infectious disease doctors, who I never met or never talked to about it, kept his mouth shut, treated this guy, but I never heard about it. So none of the pulmonologists, the lung specialist, knew about him. No one talked. So the whole thing was silly" "why would you admit a guy to a hospital campus that has no ICU when you're worried about a deadly pandemic? It's just illogical. So just from that, it was ridiculous" "I'll just absolutely hold out. There's a theoretical chance this actually happened. It just never happened with any other infectious disease. Every tuberculosis patient came to the ICU because there were negative pressure rooms. Every other infectious disease we're worried about came to the ICU so that. It's just not logical... [and] I just knew everybody, and no one met the guy"

💥BANG! Surgeon who worked at the hospital that supposedly got the first Covid patient in the U.S.— "IT WAS ALL A PROPAGANDA OP" "Everything in the news was wrong. IT WAS ALL A LIE" The "lab leak" isn't the real Covid story. The real Covid story is THERE WAS NO PANDEMIC. This lightly edited clip of Dr. James Miller (james miller), a trauma surgeon who worked at the WA hospital that—supposedly—got the first "covid" case in the U.S., is taken from a conversation with Alix Mayer (Alix Mayer) posted to YouTube on July 8, 2026. ---------------Pulled quotes from the clip---------------- "First of all, everything in the news was wrong. It was all a lie" "So our hospital had the first diagnosed Covid case in America. It was a guy who came back from China. Allegedly. It was all a propaganda op" "the first diagnosed Covid case, who came from Wuhan, China... showed up—allegedly—[at] our hospital doors. But here's the part that's weird. So the reason the hospital has such a cumbersome name of Providence Regional Medical Center, Everett, is because it's actually two campuses. And the second campus is just a birthing center and a rehab unit. So allegedly, they housed that guy there" "at least at that campus. Now, the CMO told me, Oh, that's where we have our special negative-pressure rooms. Which was a bald-faced lie, because every ICU bed was a negative-pressure room. And so that's just silly" "Additionally, as a trauma surgeon, because you deal with all the bad cases, particularly in the middle of the night. Everyone tells you everything. I spoke to zero nurses, zero infectious disease doctors that ever took care of that patient" "So maybe allegedly, one of the infectious disease doctors, who I never met or never talked to about it, kept his mouth shut, treated this guy, but I never heard about it. So none of the pulmonologists, the lung specialist, knew about him. No one talked. So the whole thing was silly" "why would you admit a guy to a hospital campus that has no ICU when you're worried about a deadly pandemic? It's just illogical. So just from that, it was ridiculous" "I'll just absolutely hold out. There's a theoretical chance this actually happened. It just never happened with any other infectious disease. Every tuberculosis patient came to the ICU because there were negative pressure rooms. Every other infectious disease we're worried about came to the ICU so that. It's just not logical... [and] I just knew everybody, and no one met the guy"

Sense Receptor

46,960 просмотров • 2 месяцев назад

I dug into Pi because the greatest projects are usually built on top of one very simple building block. 𝗣𝗶 𝗵𝗮𝘀 𝟳𝟳,𝟬𝟬𝟬 𝗚𝗶𝘁𝗛𝘂𝗯 𝘀𝘁𝗮𝗿𝘀 𝗮𝗻𝗱 𝗲𝘅𝗮𝗰𝘁𝗹𝘆 𝗳𝗼𝘂𝗿 𝘁𝗼𝗼𝗹𝘀: 𝗿𝗲𝗮𝗱, 𝘄𝗿𝗶𝘁𝗲, 𝗲𝗱𝗶𝘁, 𝗯𝗮𝘀𝗵. 𝗦𝘂𝗽𝗲𝗿 𝘀𝗶𝗺𝗽𝗹𝗲. No MCP, no sub agents, no plan mode, no to-dos, no permission popups. Their site has a whole section called "what we did not build." So here's the whole logic by Mario Zechner: prompt in → agents.md + system prompt become one forkable JSON → loop starts → read / write / edit / bash → session saved as a tree → loop ends agent-loop.ts has only 792 lines. I think it's beautiful. Initially I was wondering if it's gonna be a little bit too basic. And yes out of the box it's weaker than Claude Code. But skipping MCP isn't purity, it's a context budget. One MCP can sit tens of thousands of tokens in your window every single turn, for a tool you use maybe 10% of the time. Pi moves that weight from always on to on demand. A skill is just markdown. An extension is one .ts file. A package ships both. I ran it in the terminal, then again as a coding sub agent inside my own harness Waku-Agent ( through a delegate_task tool. Same binary both times. You're paying setup time for a harness that stays yours. Full 22 min breakdown in the comments. Save the diagram 🔖 You Can Build Anything. You Can Learn Anything. 💪

I dug into Pi because the greatest projects are usually built on top of one very simple building block. 𝗣𝗶 𝗵𝗮𝘀 𝟳𝟳,𝟬𝟬𝟬 𝗚𝗶𝘁𝗛𝘂𝗯 𝘀𝘁𝗮𝗿𝘀 𝗮𝗻𝗱 𝗲𝘅𝗮𝗰𝘁𝗹𝘆 𝗳𝗼𝘂𝗿 𝘁𝗼𝗼𝗹𝘀: 𝗿𝗲𝗮𝗱, 𝘄𝗿𝗶𝘁𝗲, 𝗲𝗱𝗶𝘁, 𝗯𝗮𝘀𝗵. 𝗦𝘂𝗽𝗲𝗿 𝘀𝗶𝗺𝗽𝗹𝗲. No MCP, no sub agents, no plan mode, no to-dos, no permission popups. Their site has a whole section called "what we did not build." So here's the whole logic by Mario Zechner: prompt in → agents.md + system prompt become one forkable JSON → loop starts → read / write / edit / bash → session saved as a tree → loop ends agent-loop.ts has only 792 lines. I think it's beautiful. Initially I was wondering if it's gonna be a little bit too basic. And yes out of the box it's weaker than Claude Code. But skipping MCP isn't purity, it's a context budget. One MCP can sit tens of thousands of tokens in your window every single turn, for a tool you use maybe 10% of the time. Pi moves that weight from always on to on demand. A skill is just markdown. An extension is one .ts file. A package ships both. I ran it in the terminal, then again as a coding sub agent inside my own harness Waku-Agent ( through a delegate_task tool. Same binary both times. You're paying setup time for a harness that stays yours. Full 22 min breakdown in the comments. Save the diagram 🔖 You Can Build Anything. You Can Learn Anything. 💪

Shen Sean Chen

59,186 просмотров • 1 месяц назад

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

GREG ISENBERG

377,138 просмотров • 6 месяцев назад