Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

ChatGPT casually dropped an APP STORE 🤯 It can now: - browse the web (RIP Bing waitlist, cutoff) - write and run Python (RIP replit?) - access org info (RIP docsearch startups) - add third party plugins from OpenTable, Wolfram, Instacart, Zapier, etc) - developer SDK in preview

swyx

180,043 subscribers

1,859,330 Aufrufe • vor 3 Jahren •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von swyx /dd

swyx /ddvor 3 Jahren

When I talked about the AI Red Wedding last year ( I was talking about AI offerings undercutting existing human-based or manual business processes. Now the AI Red Wedding is coming for companies building atop foundation model companies. @OpenAI is flexing that they can integrate you faster and better and safer than you can integrate them.

Profilbild von swyx /dd

swyx /ddvor 3 Jahren

Actually, calling it a "Developer SDK" is stretching it: 1. Define API with OpenAPI (heheh not to be confused with OpenAI) 2. Explain what the API is for and what the methods do. that's it, no step 3. ChatGPT can figure out when and how to use it correctly now. @karpathy called it, English is the hottest new programming language.

Profilbild von swyx /dd

swyx /ddvor 3 Jahren

@karpathy IT RUNS FFMPEG. CHATGPT RUNS FFMPEG. I think people aren't properly appreciating it's ability to run -and execute- Python. IT RUNS FFMPEG IT RUNS FREAKING FFMPEG. inside CHATGPT. CHATGPT IS AN AI COMPUTE PLATFORM NOW. what. is. happening.

Profilbild von Jon Abrams 🤷‍♂️

Jon Abrams 🤷‍♂️vor 3 Jahren

Once the ChatGPT plugin for ChatGPT drops, we're all screwed.

Profilbild von Blake Campbell

Blake Campbellvor 3 Jahren

The pace of releases is crazy. It doesn't have to be perfect, they just want to be good and first.

Profilbild von Sherif Nada

Sherif Nadavor 3 Jahren

fr I can't keep up

Profilbild von swyx /dd

swyx /ddvor 3 Jahren

Airbyte ChatGPT plugin wen

Profilbild von Kristoph

Kristophvor 3 Jahren

1. It’s not open to the public yet. Presumably won’t be open to the public before Bing Chat is GA. 2. It can write and run python, one shot. Best case it’s an integrated playground. No risk for @Replit ( other than less motivation to be a developer ) 3. Big corporations keep all their content behind firewall. They will want their own LLM’s. Docsearch startups do need to be already testing LLM’s.

Profilbild von Rally Hudson

Rally Hudsonvor 3 Jahren

How are you accessing websites? My plus says it cannot.

Profilbild von swyx /dd

swyx /ddvor 3 Jahren

there is a new "Browsing" model

Ähnliche Videos

I just built an app inside ChatGPT 🤯 I simply typed my idea, and Replit ⠕ handled everything behind the scenes. Describe what you want → Replit builds it → live preview appears → refine with more messages. You can now access Replit directly in ChatGPT — ideas become apps in one conversation. Replit ⠕

I just built an app inside ChatGPT 🤯 I simply typed my idea, and Replit ⠕ handled everything behind the scenes. Describe what you want → Replit builds it → live preview appears → refine with more messages. You can now access Replit directly in ChatGPT — ideas become apps in one conversation. Replit ⠕

HR Swati sharma

16,398 Aufrufe • vor 7 Monaten

BREAKING: Replit ⠕ is officially an app inside ChatGPT! Now you can kick off app builds directly within a ChatGPT conversation. Idea → research → prototype in ChatGPT. Then refine and deploy in Replit. I went from "I want to start a coffee shop in Austin" to a live website in under 7 minutes: - ChatGPT researched the neighborhood - Told me what to offer and what to name it - Built a preview using the Replit app - Then I refined and deployed in Replit Websites, slide decks, AI-powered apps - you can start it all in ChatGPT. When you're ready to refine and publish, Replit makes it easy. Go build something!! 👇

BREAKING: Replit ⠕ is officially an app inside ChatGPT! Now you can kick off app builds directly within a ChatGPT conversation. Idea → research → prototype in ChatGPT. Then refine and deploy in Replit. I went from "I want to start a coffee shop in Austin" to a live website in under 7 minutes: - ChatGPT researched the neighborhood - Told me what to offer and what to name it - Built a preview using the Replit app - Then I refined and deployed in Replit Websites, slide decks, AI-powered apps - you can start it all in ChatGPT. When you're ready to refine and publish, Replit makes it easy. Go build something!! 👇

Manny Bernabe

20,864 Aufrufe • vor 7 Monaten

I just built a finance app without touching code using Replit inside ChatGPT. I typed one line: Replit ⠕, Create a lightweight app that helps users track expenses, categorize spending, and see monthly summaries. Immediately: → The app began building. → Logic + storage were set up. → A working preview appeared inside ChatGPT. Then I refined it by talking: → Add spending categories. → Show monthly breakdowns. → Improve the dashboard. You can: • Start in ChatGPT. • Keep iterating in the same conversation. • Or open it in Replit to publish and scale. It genuinely makes you think: “I could build an app right now.” If you’ve ever had an idea but didn’t know where to start, this removes the friction. 👉 Try it:

I just built a finance app without touching code using Replit inside ChatGPT. I typed one line: Replit ⠕, Create a lightweight app that helps users track expenses, categorize spending, and see monthly summaries. Immediately: → The app began building. → Logic + storage were set up. → A working preview appeared inside ChatGPT. Then I refined it by talking: → Add spending categories. → Show monthly breakdowns. → Improve the dashboard. You can: • Start in ChatGPT. • Keep iterating in the same conversation. • Or open it in Replit to publish and scale. It genuinely makes you think: “I could build an app right now.” If you’ve ever had an idea but didn’t know where to start, this removes the friction. 👉 Try it:

Aakash Verma

23,357 Aufrufe • vor 7 Monaten

sarah achieves the most impossible developer events - she got a bunch of developers at a writers meetup to sit together…. … and actually write 🤯 thanks to anhtho 🍊 for being our 3rd Writing Mentor! allen helped with AV and will upload both her and Corey Quinn video soon

sarah achieves the most impossible developer events - she got a bunch of developers at a writers meetup to sit together…. … and actually write 🤯 thanks to anhtho 🍊 for being our 3rd Writing Mentor! allen helped with AV and will upload both her and Corey Quinn video soon

swyx

14,508 Aufrufe • vor 4 Monaten

wow. Apple might just have fixed Siri. and beat OpenAI to the first AI phone. and commoditized OpenAI with Google. and casually dropped a video understanding model. incredibly well executed. (see @smol_ai writeup below for deltas from WWDC)

wow. Apple might just have fixed Siri. and beat OpenAI to the first AI phone. and commoditized OpenAI with Google. and casually dropped a video understanding model. incredibly well executed. (see @smol_ai writeup below for deltas from WWDC)

swyx 🇸🇬 AIE Singapore!

695,984 Aufrufe • vor 1 Jahr

🤯 with OpenAI Whisper + TTS + GPT4V, you can just permanently share your screen with an AI and talk to it to get help on anything on screen. a generally intelligent assistant for your digital life. with a bit more engineering you could probably feed it extra docs and context based on the currently active tab/app.

🤯 with OpenAI Whisper + TTS + GPT4V, you can just permanently share your screen with an AI and talk to it to get help on anything on screen. a generally intelligent assistant for your digital life. with a bit more engineering you could probably feed it extra docs and context based on the currently active tab/app.

swyx

1,051,687 Aufrufe • vor 2 Jahren

Wow. GitHub CEO Thomas Dohmke just announced GitHub Copilot X: - Copilot Chat - "ChatGPT-like experience in your editor" powered by GPT-4 - Copilot for Pull Requests - AI-generated descriptions for pull requests on GitHub - GitHub Copilot for Docs - chat for *any* company's repos and docs, starting with React/Azure/MDN - GitHub Copilot CLI - compose commands and loops, and throw around obscure find flags to satisfy your query. as Benedict Evans might say, the incumbents are embracing and integrating AI into existing form factors faster than startups can build them. To win, startups have to create -new- form factors from first principles.

Wow. GitHub CEO Thomas Dohmke just announced GitHub Copilot X: - Copilot Chat - "ChatGPT-like experience in your editor" powered by GPT-4 - Copilot for Pull Requests - AI-generated descriptions for pull requests on GitHub - GitHub Copilot for Docs - chat for any company's repos and docs, starting with React/Azure/MDN - GitHub Copilot CLI - compose commands and loops, and throw around obscure find flags to satisfy your query. as Benedict Evans might say, the incumbents are embracing and integrating AI into existing form factors faster than startups can build them. To win, startups have to create -new- form factors from first principles.

swyx

2,052,250 Aufrufe • vor 3 Jahren

Q: What's better than Mixture of Experts? A: Mixture of Mixture of Experts! Introducing GodMode: the AI Chat Browser Fast, Free, Access to ChatGPT, Bing, Bard, Claude, YouChat, Poe, Perplexity, Phind, and Local/GGML Models like Vicuna and Alpaca No API keys, Full Webapp Features We've been heads down rewriting the Smol AI menubar into a full fledged "AI Chat Browser" this past month. Our sincere belief is that every chat in the world should be one keyboard shortcut away and run simultaneously to tap into the global superintelligence. And ofc, free and open source. Releasing this as a "beta" today because a bunch of polish features aren't yet done, but we want to get something out there for feedback. Roadmap: - model voting -> global/personal leaderboard - add even more models, eg Inflection - PromptCritic - AI assisted prompt improvement Heavy thanks to Sean Oliver and Alec Dewitz for working with me this past month on this and our upcoming Super Secret next project (see if you can find it in the menu!)

Q: What's better than Mixture of Experts? A: Mixture of Mixture of Experts! Introducing GodMode: the AI Chat Browser Fast, Free, Access to ChatGPT, Bing, Bard, Claude, YouChat, Poe, Perplexity, Phind, and Local/GGML Models like Vicuna and Alpaca No API keys, Full Webapp Features We've been heads down rewriting the Smol AI menubar into a full fledged "AI Chat Browser" this past month. Our sincere belief is that every chat in the world should be one keyboard shortcut away and run simultaneously to tap into the global superintelligence. And ofc, free and open source. Releasing this as a "beta" today because a bunch of polish features aren't yet done, but we want to get something out there for feedback. Roadmap: - model voting -> global/personal leaderboard - add even more models, eg Inflection - PromptCritic - AI assisted prompt improvement Heavy thanks to Sean Oliver and Alec Dewitz for working with me this past month on this and our upcoming Super Secret next project (see if you can find it in the menu!)

swyx

340,980 Aufrufe • vor 3 Jahren

🐣 Introducing `smol-developer`! ▸ Human-centric, coherent whole program synthesis ▸ your own junior developer ▸ develop, debug, decompile ▸ open source: ▸ 200 LOC, half english Insights: 💡 100k context can summarize both content and codebases 💡 Markdown is the best prompting DSL 💡 Copy and paste your errors as prompts 💡 Copy and paste curl output as prompts 💡 write CSS animation by describing what u want 💡 GPT4 >>> GPT3.5/Anthropic Claude for codegen see README for more thoughts!

🐣 Introducing `smol-developer`! ▸ Human-centric, coherent whole program synthesis ▸ your own junior developer ▸ develop, debug, decompile ▸ open source: ▸ 200 LOC, half english Insights: 💡 100k context can summarize both content and codebases 💡 Markdown is the best prompting DSL 💡 Copy and paste your errors as prompts 💡 Copy and paste curl output as prompts 💡 write CSS animation by describing what u want 💡 GPT4 >>> GPT3.5/Anthropic Claude for codegen see README for more thoughts!

swyx

1,590,973 Aufrufe • vor 3 Jahren

Recorded my first walkthrough video for App Publishing via Manus 👉👈✨ You can now package and share your app for testing on Google Play Store and the Apple App store without setting up Xcode, Android Studio, or wrestling with build configurations. Supported platforms: • Android → Google Play (Internal Testing) • iOS → App Store (TestFlight) Ready to try it? Here's how 👇 ➡️Google Play: Prerequisites: Google Play Developer account ($25 one-time fee) Steps: 1. In Manus, click Publish → select the Android tab 2. Click Build APK — Manus packages your app in AAB format 3. Go to your Google Play Console and navigate to Internal testing 4. Click Create new release and upload the AAB file 5. Under Testers, add your email address (or create an email list for your team) 6. Copy the opt-in link 7. Open the link on your Android device, accept the invite, and install ➡️App Store: Prerequisites: • Apple Developer account ($99/year) • iPhone with TestFlight installed Steps: 1. In Manus, click Publish → select the iOS tab 2. Click Create app and follow the prompts to connect your Apple Developer account 3. Manus will package and upload your app to App Store Connect automatically 4. Wait for Apple to process your build 5. You'll receive an email from TestFlight when it's ready 6. Open the email on your iPhone, tap the link, and install via TestFlight 🔗 Full guide: Let me know what else you'd like to see next!

Recorded my first walkthrough video for App Publishing via Manus 👉👈✨ You can now package and share your app for testing on Google Play Store and the Apple App store without setting up Xcode, Android Studio, or wrestling with build configurations. Supported platforms: • Android → Google Play (Internal Testing) • iOS → App Store (TestFlight) Ready to try it? Here's how 👇 ➡️Google Play: Prerequisites: Google Play Developer account ($25 one-time fee) Steps: 1. In Manus, click Publish → select the Android tab 2. Click Build APK — Manus packages your app in AAB format 3. Go to your Google Play Console and navigate to Internal testing 4. Click Create new release and upload the AAB file 5. Under Testers, add your email address (or create an email list for your team) 6. Copy the opt-in link 7. Open the link on your Android device, accept the invite, and install ➡️App Store: Prerequisites: • Apple Developer account ($99/year) • iPhone with TestFlight installed Steps: 1. In Manus, click Publish → select the iOS tab 2. Click Create app and follow the prompts to connect your Apple Developer account 3. Manus will package and upload your app to App Store Connect automatically 4. Wait for Apple to process your build 5. You'll receive an email from TestFlight when it's ready 6. Open the email on your iPhone, tap the link, and install via TestFlight 🔗 Full guide: Let me know what else you'd like to see next!

Natalie 🇸🇬

313,056 Aufrufe • vor 6 Monaten

THIS GUY UPDATED AN OPEN SOURCE TOOL FOR CLAUDE FABLE 5 THAT TAKES A SINGLE IMAGE AND AUTOMATICALLY REBUILDS IT AS A PREMIUM SCROLL LINKED WEB ANIMATION Instead of slicing videos by hand or exporting individual frames, you just hand it an image and it recreates the entire sequence as a pure scroll mapped experience - Pick an anchor image and set your overall creative direction - The tool automatically scales it into motion clips and uses ffmpeg to rip out every frame in the background - Maps the frames directly to your scroll position, tracking the cursor for an ultra smooth user experience - AND its open source, so you can drop the skill into your own terminal workspace He tested it on a highly detailed origami style travel website and it came out genuinely good for something built completely in one shot Turning a single photo into an automated frame mapped scrolling app is the kind of thing that used to take a developer hours

THIS GUY UPDATED AN OPEN SOURCE TOOL FOR CLAUDE FABLE 5 THAT TAKES A SINGLE IMAGE AND AUTOMATICALLY REBUILDS IT AS A PREMIUM SCROLL LINKED WEB ANIMATION Instead of slicing videos by hand or exporting individual frames, you just hand it an image and it recreates the entire sequence as a pure scroll mapped experience - Pick an anchor image and set your overall creative direction - The tool automatically scales it into motion clips and uses ffmpeg to rip out every frame in the background - Maps the frames directly to your scroll position, tracking the cursor for an ultra smooth user experience - AND its open source, so you can drop the skill into your own terminal workspace He tested it on a highly detailed origami style travel website and it came out genuinely good for something built completely in one shot Turning a single photo into an automated frame mapped scrolling app is the kind of thing that used to take a developer hours

0xMarioNawfal

111,254 Aufrufe • vor 1 Monat

GROK AI APP HITS iOS—ANDROID USERS, STANDBY! Grok AI just dropped as a standalone app! iPhone users in the US, Australia, and India can download it now from the App Store. Android users? The app is listed on Google Play, but it's still in pre-registration mode—so hang tight! Not in one of those regions? No worries—Grok is still fully accessible inside the 𝕏 app on both iOS and Android. What makes Grok different? Real-time knowledge – Always up-to-date, no stale info. Image generation – Bring ideas to life with AI-powered visuals. Smart text & code tools – Summarize, write, and code like a pro. A curious mind – Designed to be truthful, useful, and actually interesting. The future of AI is here—and it’s in your pocket. Source: 𝕏

GROK AI APP HITS iOS—ANDROID USERS, STANDBY! Grok AI just dropped as a standalone app! iPhone users in the US, Australia, and India can download it now from the App Store. Android users? The app is listed on Google Play, but it's still in pre-registration mode—so hang tight! Not in one of those regions? No worries—Grok is still fully accessible inside the 𝕏 app on both iOS and Android. What makes Grok different? Real-time knowledge – Always up-to-date, no stale info. Image generation – Bring ideas to life with AI-powered visuals. Smart text & code tools – Summarize, write, and code like a pro. A curious mind – Designed to be truthful, useful, and actually interesting. The future of AI is here—and it’s in your pocket. Source: 𝕏

Mario Nawfal

47,222 Aufrufe • vor 1 Jahr

Claude Code on desktop just added an embedded loop that can run your dev server, view the app, review local changes, and watch pull requests until they merge. It can now preview a running app inside the desktop UI while it iterates on fixes. It can also monitor CI for an open PR and either fix failures or merge when checks go green. Earlier “agentic coding” workflows usually bounced between a terminal, a browser, and GitHub, so the model could not directly see what the app rendered or stay attached to CI results without manual babysitting. The new server preview flow starts and stops dev servers from a Preview control, shows the app in an embedded browser, reads logs, and can interact with the page to verify changes. That closes a common gap where a model edits code but cannot reliably confirm the UI and runtime behavior match the intent. The local “Review code” step runs before pushing, and it leaves inline comments on the diff so basic bugs and risky changes get caught earlier. For PR monitoring, the desktop app will track status and CI checks, and it can use auto-fix to attempt repairs and auto-merge to land the PR once checks pass, using GitHub tooling under the hood. Session mobility adds a /desktop command to move a CLI session into the desktop app, and sessions can be pushed to the cloud to resume from web or phone.

Claude Code on desktop just added an embedded loop that can run your dev server, view the app, review local changes, and watch pull requests until they merge. It can now preview a running app inside the desktop UI while it iterates on fixes. It can also monitor CI for an open PR and either fix failures or merge when checks go green. Earlier “agentic coding” workflows usually bounced between a terminal, a browser, and GitHub, so the model could not directly see what the app rendered or stay attached to CI results without manual babysitting. The new server preview flow starts and stops dev servers from a Preview control, shows the app in an embedded browser, reads logs, and can interact with the page to verify changes. That closes a common gap where a model edits code but cannot reliably confirm the UI and runtime behavior match the intent. The local “Review code” step runs before pushing, and it leaves inline comments on the diff so basic bugs and risky changes get caught earlier. For PR monitoring, the desktop app will track status and CI checks, and it can use auto-fix to attempt repairs and auto-merge to land the PR once checks pass, using GitHub tooling under the hood. Session mobility adds a /desktop command to move a CLI session into the desktop app, and sessions can be pushed to the cloud to resume from web or phone.

Rohan Paul

33,431 Aufrufe • vor 5 Monaten

RIP OpenClaw. How to use Claude Opus 4.6 + n8n to create a secure, autonomous agent available on all your devices: Step 1: Install Desktop Commander (Docker) Step 2: Configure permissions (mounted folders) Step 3: Create a secure connection Works today: - Run mcp-proxy - Set up a Cloudflare tunnel - Use a custom domain (from $5/year) An alternative coming soon: Use Desktop Commander Remote (free, Beta) Step 4: Create an n8n agent with Opus 4.6: - n8n VPS ($4.99/mo) - Add a Telegram trigger - Add Desktop Commander MCP - Plug integrations (Gmail, Drive, Notion, Stripe) - Add memory, subagents, and the Ralph Wiggum loop - Consider one extra sandbox (Docker, the same VPS) Done. In this setup your agent: - Can't access your API keys - Can't modify its environment - Can't access folders you haven't shared - Can't access tools you haven't approved - Must get your confirmation, e.g., when sending emails Unlike in OpenClaw, those are hard guardrails, not suggestions anyone can hack. But it can still: - Reply to your Telegram or Slack messages - Access selected folders from your laptop - Access Gmail, Drive, Notion, Linear, etc. - Install new local tools in a sandbox - Run autonomously for hours - Create multiple subagents - Learn from experience - Wake up regularly Want a detailed guide? I will break everything down + setup instructions + n8n templates on Monday. Follow + 🔔to get notified: Paweł Huryn

RIP OpenClaw. How to use Claude Opus 4.6 + n8n to create a secure, autonomous agent available on all your devices: Step 1: Install Desktop Commander (Docker) Step 2: Configure permissions (mounted folders) Step 3: Create a secure connection Works today: - Run mcp-proxy - Set up a Cloudflare tunnel - Use a custom domain (from $5/year) An alternative coming soon: Use Desktop Commander Remote (free, Beta) Step 4: Create an n8n agent with Opus 4.6: - n8n VPS ($4.99/mo) - Add a Telegram trigger - Add Desktop Commander MCP - Plug integrations (Gmail, Drive, Notion, Stripe) - Add memory, subagents, and the Ralph Wiggum loop - Consider one extra sandbox (Docker, the same VPS) Done. In this setup your agent: - Can't access your API keys - Can't modify its environment - Can't access folders you haven't shared - Can't access tools you haven't approved - Must get your confirmation, e.g., when sending emails Unlike in OpenClaw, those are hard guardrails, not suggestions anyone can hack. But it can still: - Reply to your Telegram or Slack messages - Access selected folders from your laptop - Access Gmail, Drive, Notion, Linear, etc. - Install new local tools in a sandbox - Run autonomously for hours - Create multiple subagents - Learn from experience - Wake up regularly Want a detailed guide? I will break everything down + setup instructions + n8n templates on Monday. Follow + 🔔to get notified: Paweł Huryn

Paweł Huryn

210,466 Aufrufe • vor 6 Monaten

Notion just unveiled their next evolution of AI features at Notion - AI columns seamlessly integrating (and reactively updating! cc Geoffrey Litt) with Notion databases. in this demo Kenny clips something with the Web Clipper, and a summary shows up running a custom prompt 🤯

Notion just unveiled their next evolution of AI features at Notion - AI columns seamlessly integrating (and reactively updating! cc Geoffrey Litt) with Notion databases. in this demo Kenny clips something with the Web Clipper, and a summary shows up running a custom prompt 🤯

swyx

186,378 Aufrufe • vor 3 Jahren

surprised to hear Sherwin Wu come right out and say he was short vector dbs and now is short rl environment startups. saying the quiet part out loud!! appropriately spicy for Bill Gurley and Brad Gerstner only the agent labs survive

surprised to hear Sherwin Wu come right out and say he was short vector dbs and now is short rl environment startups. saying the quiet part out loud!! appropriately spicy for Bill Gurley and Brad Gerstner only the agent labs survive

swyx

33,976 Aufrufe • vor 11 Monaten

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

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

58,186 Aufrufe • vor 2 Monaten

i'm fixing the devrel shortage by making more of them Last time I held this Writers Retreat was in 2022 and graduates have on to run/do devrel at Cerebras, Baseten, Together, Airbyte, and more — though the memories and skills last longer and connections go deeper than just mere jobs. deep thanks to Stainless, Mintlify, Amazon Web Services, and others who helped make this possible!

i'm fixing the devrel shortage by making more of them Last time I held this Writers Retreat was in 2022 and graduates have on to run/do devrel at Cerebras, Baseten, Together, Airbyte, and more — though the memories and skills last longer and connections go deeper than just mere jobs. deep thanks to Stainless, Mintlify, Amazon Web Services, and others who helped make this possible!

swyx 🇸🇬 sg!

24,283 Aufrufe • vor 8 Monaten

excited to kick off the year by dropping Thariq's full Claude Agent SDK workshop from AlE CODE POV video to give you an idea of how insanely packed this one was also peek at the incredible venue at Datadog, Inc. - was very grateful to have their support esp since they were right above the conf venue + accepted our badges!

excited to kick off the year by dropping Thariq's full Claude Agent SDK workshop from AlE CODE POV video to give you an idea of how insanely packed this one was also peek at the incredible venue at Datadog, Inc. - was very grateful to have their support esp since they were right above the conf venue + accepted our badges!

swyx

29,720 Aufrufe • vor 7 Monaten