Загрузка видео...

Не удалось загрузить видео

На главную

google just turned karpathy's llm-wiki gist into a spec today: the open knowledge format. markdown files, one required field. the format question is now settled. the hard part still isn't. what it changes: - portability. a bundle is a tarball or a git repo. it moves between orgs and...

rohit4verse's profile picture

Rohit

23,545 subscribers

30,710 просмотров • 27 дней назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

OpenAlgo now has a brain. Not Obsidian. Not a vector DB. It is a live knowledge graph built on Google's Open Knowledge Format (OKF). Plain, portable Markdown that any AI agent can read and traverse. Access OKF here :
0:31

OpenAlgo now has a brain. Not Obsidian. Not a vector DB. It is a live knowledge graph built on Google's Open Knowledge Format (OKF). Plain, portable Markdown that any AI agent can read and traverse. Access OKF here :

OpenAlgo

11,793 просмотров • 6 дней назад

Karpathy found a way to reduce token consumption by 90% The problem is that the LLM re-reads the same files over and over again, loses context between documents, and provides less accurate answers as a result The solution is called Wiki Layer the LLM cleans, structures, and links all your data once, after which it never works with raw files again Three folders `raw/` for originals, `wiki/` for a clean knowledge base in Markdown, and files with rules for the agent Result up to 90% token savings on repeat queries, automatic links between documents, and a visual knowledge graph in Obsidian Everything stays on your local machine nothing goes to the cloud
0:32

Karpathy found a way to reduce token consumption by 90% The problem is that the LLM re-reads the same files over and over again, loses context between documents, and provides less accurate answers as a result The solution is called Wiki Layer the LLM cleans, structures, and links all your data once, after which it never works with raw files again Three folders `raw/` for originals, `wiki/` for a clean knowledge base in Markdown, and files with rules for the agent Result up to 90% token savings on repeat queries, automatic links between documents, and a visual knowledge graph in Obsidian Everything stays on your local machine nothing goes to the cloud

Asteri

1,074,990 просмотров • 1 месяц назад

My agent is now paying for its own data. No API key. No account. No credit card. Check the video I recorded. This uses the x402 open protocol built by Coinbase, along with a simple skill. This is an open protocol governed by the Linux Foundation. To complete a goal, an agent can now search for an actor on the Apify Store, pay for it, and use it without any human intervention. The way it works is pretty simple: 1. Your agent finds an Actor it wants to use 2. It sends a request 3. The Actor sends back an HTTP 402 "Payment Required" response 4. Agent authorizes payment from a wallet in USDC on Base 5. The Actor runs 6. User receives the result The model is pay-as-you-go: the agent authorizes a spending ceiling, pays only for usage, and the remaining balance is automatically settled. This brings an entire marketplace of AI tools into the agentic economy. Here is the skill you need. Add it to your agent, and it will take care of everything for you: If you want to know how this works, including what you can do with $1, read this post: Thanks to the Apify team for partnering with me on this post.
5:56

My agent is now paying for its own data. No API key. No account. No credit card. Check the video I recorded. This uses the x402 open protocol built by Coinbase, along with a simple skill. This is an open protocol governed by the Linux Foundation. To complete a goal, an agent can now search for an actor on the Apify Store, pay for it, and use it without any human intervention. The way it works is pretty simple: 1. Your agent finds an Actor it wants to use 2. It sends a request 3. The Actor sends back an HTTP 402 "Payment Required" response 4. Agent authorizes payment from a wallet in USDC on Base 5. The Actor runs 6. User receives the result The model is pay-as-you-go: the agent authorizes a spending ceiling, pays only for usage, and the remaining balance is automatically settled. This brings an entire marketplace of AI tools into the agentic economy. Here is the skill you need. Add it to your agent, and it will take care of everything for you: If you want to know how this works, including what you can do with $1, read this post: Thanks to the Apify team for partnering with me on this post.

Santiago

26,413 просмотров • 8 дней назад

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this
0:24

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this

Yarchi

57,975 просмотров • 1 месяц назад

HERMES AGENT SHIPS WITH A BUNDLED SKILL FOR ANDREJ KARPATHY'S LLM WIKI PATTERN. A SELF-IMPROVING KNOWLEDGE BASE THAT GROWS EVERY TIME YOU FEED IT. mentioned this briefly in the overnight workflow article. here is the full breakdown. what it is: a self-improving knowledge base built as interlinked markdown files. unlike RAG (which rediscovers knowledge from scratch every query), the wiki compiles knowledge once and keeps it current. cross-references stay linked. contradictions get flagged automatically. synthesis reflects everything ingested so far. why this matters for Hermes memory: Hermes built-in memory knows YOU. it remembers your conversations, your preferences, your business context across sessions. but it doesn't know your inbox. or your meeting transcripts. or that article you saved last week. or the expert framework you want it to learn. the LLM Wiki solves that. THE DIVISION OF LABOR human curates sources and directs analysis. agent summarizes, cross-references, files, and maintains consistency. you drop in articles, transcripts, notes. Hermes indexes them, links related concepts, flags contradictions, updates affected pages. your knowledge base grows itself. SETUP IS ONE COMMAND the skill ships with Hermes. enable it. set WIKI_PATH in ~/.hermes/.env: WIKI_PATH=/Users/you/wiki defaults to ~/wiki if unset. then drop anything into it: "index this article into my wiki: [paste URL or text]" Hermes reads it, builds a source page, updates related entries, flags contradictions. THE OBSIDIAN ANGLE set OBSIDIAN_VAULT_PATH to the same directory. now your wiki is visible in Obsidian's graph view. nodes, links, backlinks. all built by Hermes. for headless servers: install obsidian-headless. syncs vaults without a GUI. agent writes from the server, you read on your laptop. THE COMPOUND EFFECT Hermes knows you. the wiki knows your world. combine them and the agent answers questions using BOTH contexts at once. month 1: you explain things twice. month 3: the agent references the wiki on its own. answers get sharper because the knowledge base got sharper. AUTOMATIONS THAT FEED THE WIKI set cron jobs to ingest automatically: "every day at 9am, check Granola for new meetings. add any new transcripts to my wiki under meeting notes." "every morning, scan my Gmail starred items. add anything worth keeping to the wiki." "every week, check arXiv for new papers in [your niche]. summarize and file." your wiki grows while you sleep. Hermes never forgets what gets indexed. THE LIMITATION TO KNOW unlike Hermes memory (which is conversational and lives across sessions), the wiki is a separate knowledge layer. Hermes won't pull from the wiki automatically unless you reference it or save it as a skill. best setup: build an LLM Wiki personality that tells Hermes to consult the wiki when answering strategy questions or domain-specific queries. full HERMES AGENT OVERNIGHT WORKFLOW👇
14:28

HERMES AGENT SHIPS WITH A BUNDLED SKILL FOR ANDREJ KARPATHY'S LLM WIKI PATTERN. A SELF-IMPROVING KNOWLEDGE BASE THAT GROWS EVERY TIME YOU FEED IT. mentioned this briefly in the overnight workflow article. here is the full breakdown. what it is: a self-improving knowledge base built as interlinked markdown files. unlike RAG (which rediscovers knowledge from scratch every query), the wiki compiles knowledge once and keeps it current. cross-references stay linked. contradictions get flagged automatically. synthesis reflects everything ingested so far. why this matters for Hermes memory: Hermes built-in memory knows YOU. it remembers your conversations, your preferences, your business context across sessions. but it doesn't know your inbox. or your meeting transcripts. or that article you saved last week. or the expert framework you want it to learn. the LLM Wiki solves that. THE DIVISION OF LABOR human curates sources and directs analysis. agent summarizes, cross-references, files, and maintains consistency. you drop in articles, transcripts, notes. Hermes indexes them, links related concepts, flags contradictions, updates affected pages. your knowledge base grows itself. SETUP IS ONE COMMAND the skill ships with Hermes. enable it. set WIKI_PATH in ~/.hermes/.env: WIKI_PATH=/Users/you/wiki defaults to ~/wiki if unset. then drop anything into it: "index this article into my wiki: [paste URL or text]" Hermes reads it, builds a source page, updates related entries, flags contradictions. THE OBSIDIAN ANGLE set OBSIDIAN_VAULT_PATH to the same directory. now your wiki is visible in Obsidian's graph view. nodes, links, backlinks. all built by Hermes. for headless servers: install obsidian-headless. syncs vaults without a GUI. agent writes from the server, you read on your laptop. THE COMPOUND EFFECT Hermes knows you. the wiki knows your world. combine them and the agent answers questions using BOTH contexts at once. month 1: you explain things twice. month 3: the agent references the wiki on its own. answers get sharper because the knowledge base got sharper. AUTOMATIONS THAT FEED THE WIKI set cron jobs to ingest automatically: "every day at 9am, check Granola for new meetings. add any new transcripts to my wiki under meeting notes." "every morning, scan my Gmail starred items. add anything worth keeping to the wiki." "every week, check arXiv for new papers in [your niche]. summarize and file." your wiki grows while you sleep. Hermes never forgets what gets indexed. THE LIMITATION TO KNOW unlike Hermes memory (which is conversational and lives across sessions), the wiki is a separate knowledge layer. Hermes won't pull from the wiki automatically unless you reference it or save it as a skill. best setup: build an LLM Wiki personality that tells Hermes to consult the wiki when answering strategy questions or domain-specific queries. full HERMES AGENT OVERNIGHT WORKFLOW👇

YanXbt

30,248 просмотров • 25 дней назад

This Obsidian and Claude architecture charges nothing and removes the maintenance entirely. Obsidian stores everything as plain Markdown files. Claude Code points at the vault directory. No API integrations. No paid connectors. No configuration beyond a folder path. The gap between project management systems that get abandoned the moment life gets busy and a system that maintains itself from the notes you were already writing is not discipline or organizational skill. It is the architecture described in this article, and the afternoon it takes to build five markdown components that never need a status update meeting again.
0:27

This Obsidian and Claude architecture charges nothing and removes the maintenance entirely. Obsidian stores everything as plain Markdown files. Claude Code points at the vault directory. No API integrations. No paid connectors. No configuration beyond a folder path. The gap between project management systems that get abandoned the moment life gets busy and a system that maintains itself from the notes you were already writing is not discipline or organizational skill. It is the architecture described in this article, and the afternoon it takes to build five markdown components that never need a status update meeting again.

NeilXbt

32,130 просмотров • 1 месяц назад

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas
3:27

"The model is no longer the product. Codex, Perplexity Computer, or Claude Code - all are orchestration system. It takes a model and pairs it with an agent harness. What is an agent harness ? The rules for how the agent loops around" - Aravind Srinivas

Rohan Paul

119,783 просмотров • 18 дней назад

Prompt engineering is where people go when they refuse to write files Karpathy's LLM Wiki gist is painfully simple: > raw sources stay untouched > the agent writes the wiki > `CLAUDE.md` or `AGENTS.md` tells it the rules > `index.md` maps the pages > `log.md` records what changed That is why a good answer should not die in chat history If the model gives you a useful comparison, summary, decision, bug explanation, or research thread, file it back into the project Use: > `wiki/topics/[topic].md` > `wiki/entities/[person-or-company].md` > `wiki/sources/[source-name].md` > `wiki/analysis/[question].md` Make the agent keep the wiki from rotting: > backlinks > summaries > contradictions > stale claims > orphan pages > missing source links For coding projects, same idea: > `CLAUDE.md`: who you are, project rules, files not to touch > `index.md`: current files and features > `log.md`: date, change, reason > saved pages: decisions you do not want to re-explain Start by saving one good answer today
11:03

Prompt engineering is where people go when they refuse to write files Karpathy's LLM Wiki gist is painfully simple: > raw sources stay untouched > the agent writes the wiki > `CLAUDE.md` or `AGENTS.md` tells it the rules > `index.md` maps the pages > `log.md` records what changed That is why a good answer should not die in chat history If the model gives you a useful comparison, summary, decision, bug explanation, or research thread, file it back into the project Use: > `wiki/topics/[topic].md` > `wiki/entities/[person-or-company].md` > `wiki/sources/[source-name].md` > `wiki/analysis/[question].md` Make the agent keep the wiki from rotting: > backlinks > summaries > contradictions > stale claims > orphan pages > missing source links For coding projects, same idea: > `CLAUDE.md`: who you are, project rules, files not to touch > `index.md`: current files and features > `log.md`: date, change, reason > saved pages: decisions you do not want to re-explain Start by saving one good answer today

Alpha Batcher

14,041 просмотров • 1 месяц назад

A DEVELOPER PROVED YOU CAN FIND THE EXACT COMMIT THAT BROKE YOUR CODE IN A HISTORY OF 10,000 -- IN ABOUT 13 STEPS, AUTOMATICALLY.. 33 minutes from a Google engineer on git bisect: the built-in command that binary-searches your entire history to hunt down the one commit that introduced a bug. -> The moment it lands, "When did this break?" stops being an afternoon of guessing. You hand git a good commit, a bad one, and a test and it finds the culprit while you watch. Most people debug a regression by reading diffs by hand, blaming the obvious file, and hoping. Bisect doesn't hope. It cuts the search in half, then in half again, until only the guilty commit is left standing. Reading history by hand was never the skill -> letting git do the binary search for you is. And when an AI agent dumps hundreds of commits into your repo and one quietly breaks production, bisect is what finds the needle without you reading a single line. The bug isn't hiding. It's sitting in one exact commit. Most people just never learned to make git point at it. Bookmark & Watch it today ↓
32:07

A DEVELOPER PROVED YOU CAN FIND THE EXACT COMMIT THAT BROKE YOUR CODE IN A HISTORY OF 10,000 -- IN ABOUT 13 STEPS, AUTOMATICALLY.. 33 minutes from a Google engineer on git bisect: the built-in command that binary-searches your entire history to hunt down the one commit that introduced a bug. -> The moment it lands, "When did this break?" stops being an afternoon of guessing. You hand git a good commit, a bad one, and a test and it finds the culprit while you watch. Most people debug a regression by reading diffs by hand, blaming the obvious file, and hoping. Bisect doesn't hope. It cuts the search in half, then in half again, until only the guilty commit is left standing. Reading history by hand was never the skill -> letting git do the binary search for you is. And when an AI agent dumps hundreds of commits into your repo and one quietly breaks production, bisect is what finds the needle without you reading a single line. The bug isn't hiding. It's sitting in one exact commit. Most people just never learned to make git point at it. Bookmark & Watch it today ↓

slash1s

37,628 просмотров • 27 дней назад

Agents can one shot mobile apps, but testing is still the bottleneck. So we built a CLI that gives Claude Code the one thing it was missing - eyes and hands The best part? t's fully vision-based: - No scripts, no selectors, no element IDs - It interacts with the app exactly like a human would Claude now writes code → tests it on the app → sees what broke → fixes it Spawn a cloud agent, go to sleep, and wake up knowing it actually worked.
0:38

Agents can one shot mobile apps, but testing is still the bottleneck. So we built a CLI that gives Claude Code the one thing it was missing - eyes and hands The best part? t's fully vision-based: - No scripts, no selectors, no element IDs - It interacts with the app exactly like a human would Claude now writes code → tests it on the app → sees what broke → fixes it Spawn a cloud agent, go to sleep, and wake up knowing it actually worked.

Landseer Enga

86,889 просмотров • 4 месяцев назад

This is one of the coolest open-source AI agent projects I've seen in a while: 'Understand Anything' It's a plugin for Claude Code, Codex, OpenCode etc. that analyzes your codebase and turns it into a knowledge base that you can interact with. It explains the codebase to you, rather than showing you the structure. It seems like it's designed for code but I opened my Obsidian vault of podcast highlights in Claude Code, then ran /understand. The result is a knowledge graph that I can search of highlights from 888 podcast episodes and 144K lines of markdown text.
0:22

This is one of the coolest open-source AI agent projects I've seen in a while: 'Understand Anything' It's a plugin for Claude Code, Codex, OpenCode etc. that analyzes your codebase and turns it into a knowledge base that you can interact with. It explains the codebase to you, rather than showing you the structure. It seems like it's designed for code but I opened my Obsidian vault of podcast highlights in Claude Code, then ran /understand. The result is a knowledge graph that I can search of highlights from 888 podcast episodes and 144K lines of markdown text.

Dan McAteer

172,420 просмотров • 20 дней 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
13:23

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

55,345 просмотров • 1 месяц назад

Most AI tools today are just command-takers. You type, it responds. You click, it executes. There's truly no learning, no memory, no adaptation. You're still doing most of the work. Which is why Miles by Avo on Solana would make so much sense if built well. From what I understand so far, miles learns about you over time, adapts to how you operate, and figures out the tools you struggle to navigate on your own. Less clicking, more conversation, the more you use it, the better it gets at working with you, not just for you. That shift from command-follower to learning companion is bigger than it sounds. It's the difference between a tool and an agent that actually knows you. The second one is Agent Grid and this one is for builders and power users. But as I mentioned in this video, I'm still studying the Agent Grid. I'd come talk about it once I learn properly about it. Souren just keeps shipping!
1:28

Most AI tools today are just command-takers. You type, it responds. You click, it executes. There's truly no learning, no memory, no adaptation. You're still doing most of the work. Which is why Miles by Avo on Solana would make so much sense if built well. From what I understand so far, miles learns about you over time, adapts to how you operate, and figures out the tools you struggle to navigate on your own. Less clicking, more conversation, the more you use it, the better it gets at working with you, not just for you. That shift from command-follower to learning companion is bigger than it sounds. It's the difference between a tool and an agent that actually knows you. The second one is Agent Grid and this one is for builders and power users. But as I mentioned in this video, I'm still studying the Agent Grid. I'd come talk about it once I learn properly about it. Souren just keeps shipping!

Sir Khaycee

20,419 просмотров • 3 месяцев назад

Fable 5 and Karpathy's knowledge base trick are basically a cheat code. Someone just dropped a full walkthrough on building the most powerful second brain ever Andrej Karpathy shared a simple idea: use an LLM to build personal knowledge bases. Index your sources, let the model organize them, and use Obsidian as the front end. Someone just built the full thing with Claude Code and Fable 5, and walked through every step You drop your sources into a folder (YouTube transcripts, PDFs, articles, meeting notes) and Claude Code reads them, splits them into linked wiki pages, and builds a living second brain that connects everything. It grows on its own as you add more. Where Fable 5 pulls ahead: it found a connection buried across two sources you'd miss reading them separately. And asked to turn the messy web of links into something a beginner could understand, it produced clean, simple HTML in one shot. The same task took a full day on Opus 4.8 and came out worse. The best part: it's all just markdown files with routing. So it's not locked to Claude Code. Plug it into Codex or any agent you want. Give your AI a real knowledge base, and it stops guessing and starts knowing. Bookmark this.
14:34

Fable 5 and Karpathy's knowledge base trick are basically a cheat code. Someone just dropped a full walkthrough on building the most powerful second brain ever Andrej Karpathy shared a simple idea: use an LLM to build personal knowledge bases. Index your sources, let the model organize them, and use Obsidian as the front end. Someone just built the full thing with Claude Code and Fable 5, and walked through every step You drop your sources into a folder (YouTube transcripts, PDFs, articles, meeting notes) and Claude Code reads them, splits them into linked wiki pages, and builds a living second brain that connects everything. It grows on its own as you add more. Where Fable 5 pulls ahead: it found a connection buried across two sources you'd miss reading them separately. And asked to turn the messy web of links into something a beginner could understand, it produced clean, simple HTML in one shot. The same task took a full day on Opus 4.8 and came out worse. The best part: it's all just markdown files with routing. So it's not locked to Claude Code. Plug it into Codex or any agent you want. Give your AI a real knowledge base, and it stops guessing and starts knowing. Bookmark this.

Shadow Nick

45,526 просмотров • 5 дней назад

MICROSOFT PUT THE ENTIRE SOURCE CODE OF WINDOWS INTO A SINGLE GIT REPO -- 300 GIGABYTES, 3.5 MILLION FILES AND MADE IT CLONE IN SECONDS 31 minutes from the Microsoft engineer who actually did it, bending the tool you use for a 50-file side project to hold the biggest codebase on the planet. -> The moment it lands, every excuse dies. You've heard "Git doesn't scale, use something else" your whole career. They ran git status on the largest repo alive and it came back instantly. The secret wasn't a different tool. It was understanding what git actually stores and realizing you never need the whole thing on disk. Pull only the files you touch. Ignore the 3.4 million you never will. Knowing the commands was never the ceiling -> understanding how git stores and moves things is what lets you do what everyone swears is impossible. And as AI agents spin up repos that balloon overnight, knowing how git scales is what keeps you from drowning in your own history. Everyone treats git like it maxes out at a hobby project. One team quietly proved it can hold an operating system. Bookmark & Watch it today ↓
31:26

MICROSOFT PUT THE ENTIRE SOURCE CODE OF WINDOWS INTO A SINGLE GIT REPO -- 300 GIGABYTES, 3.5 MILLION FILES AND MADE IT CLONE IN SECONDS 31 minutes from the Microsoft engineer who actually did it, bending the tool you use for a 50-file side project to hold the biggest codebase on the planet. -> The moment it lands, every excuse dies. You've heard "Git doesn't scale, use something else" your whole career. They ran git status on the largest repo alive and it came back instantly. The secret wasn't a different tool. It was understanding what git actually stores and realizing you never need the whole thing on disk. Pull only the files you touch. Ignore the 3.4 million you never will. Knowing the commands was never the ceiling -> understanding how git stores and moves things is what lets you do what everyone swears is impossible. And as AI agents spin up repos that balloon overnight, knowing how git scales is what keeps you from drowning in your own history. Everyone treats git like it maxes out at a hobby project. One team quietly proved it can hold an operating system. Bookmark & Watch it today ↓

slash1s

255,565 просмотров • 1 месяц назад

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.
0:22

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

Akshay 🚀

118,124 просмотров • 1 месяц назад

AN MIT RESEARCHER PROVED GIT ISN'T HARD BECAUSE YOU'RE BAD AT IT -- IT'S HARD BECAUSE IT WAS DESIGNED THAT WAY 27 minutes from a PhD researcher in MIT's Software Design Group, using actual design theory to show why the tool that confuses everyone confuses everyone for a reason. -> The moment it lands, years of feeling stupid evaporate. The gap between what git's commands say and what they actually do was never in your head. It's baked into the tool. He maps the difference between what you think a command does and what git really does underneath. Once you see that gap, the confusion finally has a name and it stops being yours to carry. Struggling with git was never a skills issue -> it's a design issue, and knowing where the model lies to you is what turns panic into control. And as AI agents fire off commits and rebases you didn't write, the person who understands where git misleads is the one who untangles the mess. You were never bad at git. You were just never shown where it was built to trip you. Bookmark & Watch it today ↓
26:35

AN MIT RESEARCHER PROVED GIT ISN'T HARD BECAUSE YOU'RE BAD AT IT -- IT'S HARD BECAUSE IT WAS DESIGNED THAT WAY 27 minutes from a PhD researcher in MIT's Software Design Group, using actual design theory to show why the tool that confuses everyone confuses everyone for a reason. -> The moment it lands, years of feeling stupid evaporate. The gap between what git's commands say and what they actually do was never in your head. It's baked into the tool. He maps the difference between what you think a command does and what git really does underneath. Once you see that gap, the confusion finally has a name and it stops being yours to carry. Struggling with git was never a skills issue -> it's a design issue, and knowing where the model lies to you is what turns panic into control. And as AI agents fire off commits and rebases you didn't write, the person who understands where git misleads is the one who untangles the mess. You were never bad at git. You were just never shown where it was built to trip you. Bookmark & Watch it today ↓

slash1s

138,043 просмотров • 1 месяц назад

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.
1:32

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Santiago

46,109 просмотров • 1 год назад

Omg, this is such a hack for vibecoding mobile apps This is an image with a video on the top. The video is a character with no backround. I'm using: > Masko AI to generate the video > vibecode.dev to build the app In masko all you need to do is provide an image, and it will give you a video without a background. And then all you need to do is give it to vibecode.dev which is the best mobile app builder.
0:25

Omg, this is such a hack for vibecoding mobile apps This is an image with a video on the top. The video is a character with no backround. I'm using: > Masko AI to generate the video > vibecode.dev to build the app In masko all you need to do is provide an image, and it will give you a video without a background. And then all you need to do is give it to vibecode.dev which is the best mobile app builder.

Emily Lambert

29,840 просмотров • 5 месяцев назад

Jensen Huang just described the most fundamental shift in computing since the invention of the computer itself. Almost no one has processed it. Huang: “We went from a retrieval-based computing system to a generative-based computing system.” For fifty years, a computer was a filing cabinet. You made something. Saved it. Stored it. Searched for it later. Every website. Every database. Every app. Every search engine. Same machine. Different skins. Fetch the file. Deliver the file. Display the file. That was computing. Was. Huang: “AI computers are contextually aware, which means that it has to process and generate tokens in real time.” The machine no longer retrieves what someone already made. It generates what you need the instant you ask. Not from a template. Not from a library. From context. Your question. Your moment. Answered by something that didn’t exist until you asked. The old computer found what someone wrote last year. The new computer writes what no one ever has. Every time. From nothing. That sounds subtle. It rewires everything. Huang: “We need a lot of storage in the old world. We need a lot of computation in this new world.” The old economy hoarded data. More files. More servers. More storage. Whoever built the biggest archive won. The new economy burns compute. More processing. More inference. More tokens per second. Whoever commands the most computational power wins. Storage was the currency of the retrieval era. Compute is the currency of the generative era. Every dollar still spent hoarding old files is a dollar not spent on the only thing that matters now. The ability to think in real time. Huang: “We fundamentally changed computing and the way computing is done.” He said it plainly. No drama. No metaphor. Fundamentally changed. The global infrastructure layer shifted from read to write. From looking up what exists to generating what doesn’t. Companies still organized around retrieval are curating a library in a world that no longer reads books. The ones generating answers live, at the speed of the question, are operating on a plane the old model can’t perceive. This is not an upgrade. It is a replacement. The filing cabinet era produced Google, Amazon, and every search-driven empire on the internet. The generative era will produce something that makes all of them look like the card catalog at a public library. The price of entry is not data. It is compute. Raw. Relentless. Infinite. Whoever has the most doesn’t just run the best AI. They write the future. Everyone else is still searching for it.
1:00

Jensen Huang just described the most fundamental shift in computing since the invention of the computer itself. Almost no one has processed it. Huang: “We went from a retrieval-based computing system to a generative-based computing system.” For fifty years, a computer was a filing cabinet. You made something. Saved it. Stored it. Searched for it later. Every website. Every database. Every app. Every search engine. Same machine. Different skins. Fetch the file. Deliver the file. Display the file. That was computing. Was. Huang: “AI computers are contextually aware, which means that it has to process and generate tokens in real time.” The machine no longer retrieves what someone already made. It generates what you need the instant you ask. Not from a template. Not from a library. From context. Your question. Your moment. Answered by something that didn’t exist until you asked. The old computer found what someone wrote last year. The new computer writes what no one ever has. Every time. From nothing. That sounds subtle. It rewires everything. Huang: “We need a lot of storage in the old world. We need a lot of computation in this new world.” The old economy hoarded data. More files. More servers. More storage. Whoever built the biggest archive won. The new economy burns compute. More processing. More inference. More tokens per second. Whoever commands the most computational power wins. Storage was the currency of the retrieval era. Compute is the currency of the generative era. Every dollar still spent hoarding old files is a dollar not spent on the only thing that matters now. The ability to think in real time. Huang: “We fundamentally changed computing and the way computing is done.” He said it plainly. No drama. No metaphor. Fundamentally changed. The global infrastructure layer shifted from read to write. From looking up what exists to generating what doesn’t. Companies still organized around retrieval are curating a library in a world that no longer reads books. The ones generating answers live, at the speed of the question, are operating on a plane the old model can’t perceive. This is not an upgrade. It is a replacement. The filing cabinet era produced Google, Amazon, and every search-driven empire on the internet. The generative era will produce something that makes all of them look like the card catalog at a public library. The price of entry is not data. It is compute. Raw. Relentless. Infinite. Whoever has the most doesn’t just run the best AI. They write the future. Everyone else is still searching for it.

Dustin

25,402 просмотров • 3 месяцев назад