Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Everyone's building mega-swarm systems. I just realized: a folder with a CLAUDE.md is already an agent. For Cora I have a source folder, a customer support folder, a bug investigation folder. Each is an agent. New discipline? New folder. No lock-in, no dependency. Orchestration is just one layer that... show more

Kieran Klaassen

18,347 subscribers

82,545 görüntüleme • 4 ay önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

THIS GUY VIBE CODED A MAC APP THAT AUTOMATICALLY SETS FOLDER ICONS BASED ON THEIR NAMES every folder on your mac looks the same (all blue folders) you have to read every name to find what you're looking for this app reads the folder name and automatically assigns a matching icon your "Photos" folder gets a camera icon. your "Music" folder gets a music icon. your "Projects" folder gets a code icon, all automatic it uses an LLM to understand the folder name and match it to the right icon so it works even with creative or unusual folder names the small details that make your workspace feel organized are the ones nobody builds because they seem too simple to charge for but anyone who has stared at 30 identical blue folders trying to find the right one knows THIS is a real problem mac used to have custom folder icons built in on older versions of macOS. apple removed it. this guy brought it back

THIS GUY VIBE CODED A MAC APP THAT AUTOMATICALLY SETS FOLDER ICONS BASED ON THEIR NAMES every folder on your mac looks the same (all blue folders) you have to read every name to find what you're looking for this app reads the folder name and automatically assigns a matching icon your "Photos" folder gets a camera icon. your "Music" folder gets a music icon. your "Projects" folder gets a code icon, all automatic it uses an LLM to understand the folder name and match it to the right icon so it works even with creative or unusual folder names the small details that make your workspace feel organized are the ones nobody builds because they seem too simple to charge for but anyone who has stared at 30 identical blue folders trying to find the right one knows THIS is a real problem mac used to have custom folder icons built in on older versions of macOS. apple removed it. this guy brought it back

Om Patel

80,225 görüntüleme • 2 ay önce

i keep telling people to build this and they nod politely and never do it... andrej karpathy posted how to fix this a while ago, and everyone just keeps working the old way the dumb thing is this... you pay to teach claude the same lessons over and over, every chat is a fresh amnesia patient, every contradiction it catches evaporates the second you close the tab, and you accept this like it's just how ai works 1. one folder is a graveyard for originals that nobody edits, another folder is claude's active memory that only claude writes to, a third folder is a two-page rulebook that keeps claude from confusing them 2. a raw file gets read the day it arrives and then it's done, claude never touches it again, everything it needed is already extracted into wiki pages with the source cited right there 3. every time claude notices your new answer clashes with your old one, it doesn't pick a side, it writes both with dates, and from then on it treats you like someone who might be wrong the raw folder is a museum... the wiki is the actual working brain full breakdown is in the article below

i keep telling people to build this and they nod politely and never do it... andrej karpathy posted how to fix this a while ago, and everyone just keeps working the old way the dumb thing is this... you pay to teach claude the same lessons over and over, every chat is a fresh amnesia patient, every contradiction it catches evaporates the second you close the tab, and you accept this like it's just how ai works 1. one folder is a graveyard for originals that nobody edits, another folder is claude's active memory that only claude writes to, a third folder is a two-page rulebook that keeps claude from confusing them 2. a raw file gets read the day it arrives and then it's done, claude never touches it again, everything it needed is already extracted into wiki pages with the source cited right there 3. every time claude notices your new answer clashes with your old one, it doesn't pick a side, it writes both with dates, and from then on it treats you like someone who might be wrong the raw folder is a museum... the wiki is the actual working brain full breakdown is in the article below

kai

32,120 görüntüleme • 18 gün önce

Here is a step-by-step introduction to building a workflow with a custom AI agent that uses MCP. I explain every component in the video: 1. Building the MCP server 2. Building the agent and an MCP client 3. Building a workflow that uses the agent The goal is simple: Generate a dialogue between two people and make one yell and the other answer with sarcasm. Kestra is sponsoring this video. They are an open-source orchestration platform (repo link below), and I used them to build the workflow that connects every component.

Here is a step-by-step introduction to building a workflow with a custom AI agent that uses MCP. I explain every component in the video: 1. Building the MCP server 2. Building the agent and an MCP client 3. Building a workflow that uses the agent The goal is simple: Generate a dialogue between two people and make one yell and the other answer with sarcasm. Kestra is sponsoring this video. They are an open-source orchestration platform (repo link below), and I used them to build the workflow that connects every component.

Santiago

51,527 görüntüleme • 1 yıl önce

Introducing Wikiwise: an open-source Mac app for managing your own Karpathy-style LLM wiki. Set up a new wiki in a few clicks: all you need is Wikiwise + your agent. It's infinitely customizable, just markdown/html under the hood, and one click to share your wiki publicly. Here's how it works: * Install Wikiwise for mac (it's built in Swift so super minimal and performant). In Karpathy's framework, Wikiwise is your IDE. * Start a new Wiki: it generates a new folder on your machine that's scaffolded in the wiki structure Andrej Karpathy describes (index.md, raw folder, wiki folder, CLAUDE.md/AGENTS.md, although it tries to be as un-opinionated as possible). * Then just point your agent (Codex, Claude Code, Cursor, etc) at the folder and tell it what to import -- files on your machine, connect to your Readwise account, or urls from the web. * Your agent creates wthe wiki for you: Your agent will know how to ingest your raw sources (via the AGENTS.md) and will immediately start writing+linking wiki pages for you. * Go crazy on customization! The rendered wiki pages live as static html/css in your folder too so just tell your agent to change stuff, and if you need any more customization Wikiwise is fully open source :) * Ask questions about your research with your agent, ask it to bring in new sources, write new documents, etc. * (optionally) Hit the Publish button to share your wiki with friends/colleagues at a custom URL === I tried to walk the line on a couple constraints with Wikiwise: 1. I wanted it to be easy to spin up new wikis, especially without chaining together a bunch of different apps. It takes me a few minutes to spin up a new wiki on a topic -- I already have five! 2. Infinitely Customizable: one great aspect of building a wiki as Karpathy described is that you can modify any aspect of your wiki with your agent. Every new wiki styling+structure is self-contained in the local folder, which allows you to preserve this. Wikiwise is just an IDE that makes the setup easier and includes a nice un-opinionated starting state. 3. Minimal: Wikiwise is built mostly in Swift, and the DMG you install to download it is only 2.6MB (!) 4. Easy Publishing: my colleague Eleanor Konik has been building her own LLM wikis for months, but has always really struggled to actually share them with her book club. There are tools to do it, but figuring out hosting is always a huge headache. This seemed like an ideal usecase for a tool like Wikiwise to solve. The process of building wikiwise was also pretty interesting -- I "bootstrapped" the app in a way by first building my own wiki based on Karpathy's tweet and other notes I had, and slowly formed the shape of the project in collaboration with my LLM. This was all done in 3 days over the latest Readwise company hackathon we had. Truly an incredible time to be alive. Anyways, curious what you think! Links in next tweet.

Introducing Wikiwise: an open-source Mac app for managing your own Karpathy-style LLM wiki. Set up a new wiki in a few clicks: all you need is Wikiwise + your agent. It's infinitely customizable, just markdown/html under the hood, and one click to share your wiki publicly. Here's how it works: * Install Wikiwise for mac (it's built in Swift so super minimal and performant). In Karpathy's framework, Wikiwise is your IDE. * Start a new Wiki: it generates a new folder on your machine that's scaffolded in the wiki structure Andrej Karpathy describes (index.md, raw folder, wiki folder, CLAUDE.md/AGENTS.md, although it tries to be as un-opinionated as possible). * Then just point your agent (Codex, Claude Code, Cursor, etc) at the folder and tell it what to import -- files on your machine, connect to your Readwise account, or urls from the web. * Your agent creates wthe wiki for you: Your agent will know how to ingest your raw sources (via the AGENTS.md) and will immediately start writing+linking wiki pages for you. * Go crazy on customization! The rendered wiki pages live as static html/css in your folder too so just tell your agent to change stuff, and if you need any more customization Wikiwise is fully open source :) * Ask questions about your research with your agent, ask it to bring in new sources, write new documents, etc. * (optionally) Hit the Publish button to share your wiki with friends/colleagues at a custom URL === I tried to walk the line on a couple constraints with Wikiwise: 1. I wanted it to be easy to spin up new wikis, especially without chaining together a bunch of different apps. It takes me a few minutes to spin up a new wiki on a topic -- I already have five! 2. Infinitely Customizable: one great aspect of building a wiki as Karpathy described is that you can modify any aspect of your wiki with your agent. Every new wiki styling+structure is self-contained in the local folder, which allows you to preserve this. Wikiwise is just an IDE that makes the setup easier and includes a nice un-opinionated starting state. 3. Minimal: Wikiwise is built mostly in Swift, and the DMG you install to download it is only 2.6MB (!) 4. Easy Publishing: my colleague Eleanor Konik has been building her own LLM wikis for months, but has always really struggled to actually share them with her book club. There are tools to do it, but figuring out hosting is always a huge headache. This seemed like an ideal usecase for a tool like Wikiwise to solve. The process of building wikiwise was also pretty interesting -- I "bootstrapped" the app in a way by first building my own wiki based on Karpathy's tweet and other notes I had, and slowly formed the shape of the project in collaboration with my LLM. This was all done in 3 days over the latest Readwise company hackathon we had. Truly an incredible time to be alive. Anyways, curious what you think! Links in next tweet.

Tristan

96,213 görüntüleme • 4 ay önce

ANTHROPIC KILLED THE VECTOR DATABASE AND REPLACED IT WITH A FOLDER no embeddings. no black-box retrieval. no special memory tools. the agent just reads and writes a folder the insight: your agent already knows how to use a filesystem. so Anthropic made long-term memory a directory of small markdown files, mounted straight into the agent's sandbox at /mnt/memory the agent manages it with the tools it already has, bash, read, write, edit, grep, and Anthropic auto-injects a note into the system prompt so the agent always knows the memory is there and where to look the result: > every change is an immutable version: full audit trail, point-in-time recovery, redaction > read-only or read-write per store, so many agents can safely share one memory > workspace-scoped and persistent, memory that survives every session end most teams bolt on a vector DB and pray retrieval works. Anthropic went the opposite way: compiled knowledge as plain, human-readable files you can open, diff, and edit yourself and there's a second layer. Anthropic's "Dreaming" runs offline, reviews past sessions and the store, and rewrites it into a cleaner, higher-signal version. the agent literally consolidates memory in its sleep. bookmark this. the most production-grade agent memory right now is just a well-organized folder, and Anthropic proved it.

ANTHROPIC KILLED THE VECTOR DATABASE AND REPLACED IT WITH A FOLDER no embeddings. no black-box retrieval. no special memory tools. the agent just reads and writes a folder the insight: your agent already knows how to use a filesystem. so Anthropic made long-term memory a directory of small markdown files, mounted straight into the agent's sandbox at /mnt/memory the agent manages it with the tools it already has, bash, read, write, edit, grep, and Anthropic auto-injects a note into the system prompt so the agent always knows the memory is there and where to look the result: > every change is an immutable version: full audit trail, point-in-time recovery, redaction > read-only or read-write per store, so many agents can safely share one memory > workspace-scoped and persistent, memory that survives every session end most teams bolt on a vector DB and pray retrieval works. Anthropic went the opposite way: compiled knowledge as plain, human-readable files you can open, diff, and edit yourself and there's a second layer. Anthropic's "Dreaming" runs offline, reviews past sessions and the store, and rewrites it into a cleaner, higher-signal version. the agent literally consolidates memory in its sleep. bookmark this. the most production-grade agent memory right now is just a well-organized folder, and Anthropic proved it.

NO1ennn

13,359 görüntüleme • 11 gün önce

I present to you my AI automation that converts your Google Drive folder to RAG vector database. It also updates the RAG vector database whenever a new file is added or deleted from the Google Drive folder. You can download the workflow for free (link in comment)

I present to you my AI automation that converts your Google Drive folder to RAG vector database. It also updates the RAG vector database whenever a new file is added or deleted from the Google Drive folder. You can download the workflow for free (link in comment)

Victor

261,537 görüntüleme • 1 yıl önce

Here's Operator from OpenAI building a Due Diligence portal for an M&A transaction of TikTok on Box. The Agent creates a folder structure, the initial set of docs, and then researches on the web for data. In the future, AI Agents just do work for you in the background.

Here's Operator from OpenAI building a Due Diligence portal for an M&A transaction of TikTok on Box. The Agent creates a folder structure, the initial set of docs, and then researches on the web for data. In the future, AI Agents just do work for you in the background.

Aaron Levie

196,150 görüntüleme • 1 yıl önce

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 görüntüleme • 9 gün önce

YOUR HERMES AGENT IS FLYING BLIND WITHOUT A MAP THAT LOOKS LIKE THIS hundreds of nodes, every connection visible, spectral data mapped in real time so nothing gets lost your vault has the same complexity under the hood, your agent just can’t see it I learned this the hard way, one task took 2 minutes opening wrong files for a brief from 3 months ago one index file per major folder fixed it, dropped to 10 seconds build the map, the agent finds everything full breakdown in the article below ↓

YOUR HERMES AGENT IS FLYING BLIND WITHOUT A MAP THAT LOOKS LIKE THIS hundreds of nodes, every connection visible, spectral data mapped in real time so nothing gets lost your vault has the same complexity under the hood, your agent just can’t see it I learned this the hard way, one task took 2 minutes opening wrong files for a brief from 3 months ago one index file per major folder fixed it, dropped to 10 seconds build the map, the agent finds everything full breakdown in the article below ↓

leopardracer

247,908 görüntüleme • 1 ay önce

One thing I don’t want from AI filmmaking is another folder full of beautiful clips. I want an editable sequence. Seedance 2.5 is already available on CapCut, and Seedance 2.5 1080p is now live. So I’d start by thinking about the timeline first. #CapCutPC #CapCutSeedance25

One thing I don’t want from AI filmmaking is another folder full of beautiful clips. I want an editable sequence. Seedance 2.5 is already available on CapCut, and Seedance 2.5 1080p is now live. So I’d start by thinking about the timeline first. #CapCutPC #CapCutSeedance25

Sallam Mendes

169,876 görüntüleme • 5 gün önce

Reporting automation with Claude Cowork: Step 1: Install Claude for desktop (Pro version is available for 20$ a month) Step 2: Create folder in move all files containing datas source and you want to manage. For example I moved my historical finanicals, budgets, forecast and data where I have operational drivers, events, changes in business etc.. Step 3: Upload folder in Claude cowork and write a prompt

Reporting automation with Claude Cowork: Step 1: Install Claude for desktop (Pro version is available for 20$ a month) Step 2: Create folder in move all files containing datas source and you want to manage. For example I moved my historical finanicals, budgets, forecast and data where I have operational drivers, events, changes in business etc.. Step 3: Upload folder in Claude cowork and write a prompt

Bojan Radojicic

52,579 görüntüleme • 6 ay önce

BREAKING 🚨: Anthropic is planning to release Projects for Claude Cowork! Projects will have a dedicated local folder to work with, as well as a new section for project-specific scheduled tasks for Cowork.

BREAKING 🚨: Anthropic is planning to release Projects for Claude Cowork! Projects will have a dedicated local folder to work with, as well as a new section for project-specific scheduled tasks for Cowork.

🚨 AI News | TestingCatalog

144,443 görüntüleme • 5 ay önce

OpenAI just launched Atlas, a browser that has AI agents as a native capability. Now you can let browser agents take over your software and automate anything. Here's the agent using Box to automate folder creation for an M&A due diligence process (sped up).

OpenAI just launched Atlas, a browser that has AI agents as a native capability. Now you can let browser agents take over your software and automate anything. Here's the agent using Box to automate folder creation for an M&A due diligence process (sped up).

Aaron Levie

353,829 görüntüleme • 10 ay önce

I am so happy this is being implemented. If every tab being named `page` in Next.js/Sveltekit folder based routing makes you go loopy, this new VS Code feature is going to be a life saver!

I am so happy this is being implemented. If every tab being named `page` in Next.js/Sveltekit folder based routing makes you go loopy, this new VS Code feature is going to be a life saver!

Wes Bos

130,496 görüntüleme • 2 yıl önce

I just watched Replit ⠕'s Agent 3 fix a bug and test it visually in a browser. That is not an assistant. That is a collaborator. 🤯

I just watched Replit ⠕'s Agent 3 fix a bug and test it visually in a browser. That is not an assistant. That is a collaborator. 🤯

Code With Antonio

41,161 görüntüleme • 11 ay önce

Launching 'Folders and Connect'. Day 8 of 12 Days of Agent Two. Everywhere else, getting someone to work with you means buying them a seat on your plan. And once they're in, they can see everything you're making. Folders and Connect fixes both. You invite anyone - inside or outside your organization - into one folder, without adding seats to your plan, and that folder is all they see. The team on the sensitive IP film can't see the launch campaign, and vice versa. And collaborative work still happens seamlessly. Folders & Connect is live for everyone on Team and Enterprise plans. Agent Two is frontier intelligence for creative work. 4x faster, at half the price.

Launching 'Folders and Connect'. Day 8 of 12 Days of Agent Two. Everywhere else, getting someone to work with you means buying them a seat on your plan. And once they're in, they can see everything you're making. Folders and Connect fixes both. You invite anyone - inside or outside your organization - into one folder, without adding seats to your plan, and that folder is all they see. The team on the sensitive IP film can't see the launch campaign, and vice versa. And collaborative work still happens seamlessly. Folders & Connect is live for everyone on Team and Enterprise plans. Agent Two is frontier intelligence for creative work. 4x faster, at half the price.

Invideo

671,294 görüntüleme • 13 gün önce

The gap between a PM getting AI slop from Claude Code and one getting 10x output is about one hour of file structure. Three folders. > A knowledge folder with static context: who you work with, what each stakeholder cares about, reference material that rarely changes. > A projects folder where every task accumulates research, drafts, and artifacts that load instantly into your next session. > And a people folder that auto-updates from meeting transcripts through Granola's MCP. The people folder is the part that compounds. Build a skill that pulls what each person said in your last meeting, what they pushed back on, what they committed to. Now when you draft a message to your VP of Engineering, Claude Code already knows their communication preferences from 30 real conversations. That's context no prompt can replicate. Carl walked through this system on the episode and the compounding math stuck with me. Day 1, Claude Code knows nothing about your work. Day 30, it knows your stakeholders, your project history, your patterns. Day 90, it's surfacing connections across your work you haven't consciously noticed. Then layer on skills. A standup command that pulls from GitHub, Linear, your calendar, and your task folder in one shot. Website traffic compared against your LinkedIn posts this week. Analyses that would be impossible clicking between individual UIs, running before your first meeting. One hour of setup. Compounding returns every day after. The PMs typing prompts into a blank terminal and the PMs who built the operating system around it are already producing completely different categories of work. Build the operating system.

The gap between a PM getting AI slop from Claude Code and one getting 10x output is about one hour of file structure. Three folders. > A knowledge folder with static context: who you work with, what each stakeholder cares about, reference material that rarely changes. > A projects folder where every task accumulates research, drafts, and artifacts that load instantly into your next session. > And a people folder that auto-updates from meeting transcripts through Granola's MCP. The people folder is the part that compounds. Build a skill that pulls what each person said in your last meeting, what they pushed back on, what they committed to. Now when you draft a message to your VP of Engineering, Claude Code already knows their communication preferences from 30 real conversations. That's context no prompt can replicate. Carl walked through this system on the episode and the compounding math stuck with me. Day 1, Claude Code knows nothing about your work. Day 30, it knows your stakeholders, your project history, your patterns. Day 90, it's surfacing connections across your work you haven't consciously noticed. Then layer on skills. A standup command that pulls from GitHub, Linear, your calendar, and your task folder in one shot. Website traffic compared against your LinkedIn posts this week. Analyses that would be impossible clicking between individual UIs, running before your first meeting. One hour of setup. Compounding returns every day after. The PMs typing prompts into a blank terminal and the PMs who built the operating system around it are already producing completely different categories of work. Build the operating system.

Aakash Gupta

82,865 görüntüleme • 4 ay önce

A full x86_64 Linux VM sandbox in WASM with host OS read-only folder mount, accessible via native tool calls by a WebGPU LLM. Video is real time. There is no server, no privacy concerns, no “escapes”. Comfortably in a browser tab. Sandboxes work. If they don’t: Not a sandbox.

A full x86_64 Linux VM sandbox in WASM with host OS read-only folder mount, accessible via native tool calls by a WebGPU LLM. Video is real time. There is no server, no privacy concerns, no “escapes”. Comfortably in a browser tab. Sandboxes work. If they don’t: Not a sandbox.

remy🐀

43,599 görüntüleme • 10 gün önce