Video yükleniyor...

Video Yüklenemedi

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

Ana Sayfaya Dön

Tidewave Web goes full-stack: now supports React with Rails/Phoenix backends. The revamped Inspector shows DOM & framework overlays and auto-fixes Vite crashes. Whether you're using components or templates, we send all relevant info to the model for smoother agentic coding! 🌊

José Valim

55,166 subscribers

19,677 görüntüleme • 1 yıl önce •via X (Twitter)

Sağlık & İyilik Bilim & Teknoloji Eğitim

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

It is finally here: Tidewave now supports Claude Code and OpenAI Codex. Tidewave unlocks the full-stack potential of your favorite coding agent by tightly integrating it with your web app and web framework at every layer, from UI to database. More info 👇

It is finally here: Tidewave now supports Claude Code and OpenAI Codex. Tidewave unlocks the full-stack potential of your favorite coding agent by tightly integrating it with your web app and web framework at every layer, from UI to database. More info 👇

José Valim

93,596 görüntüleme • 10 ay önce

Introducing Tidewave Web for Rails and Phoenix: a coding agent that runs in the browser alongside your web application, with full page and code context. Tidewave deeply integrates with your stack, from the database to the UI, making AI development more seamless and efficient.

Introducing Tidewave Web for Rails and Phoenix: a coding agent that runs in the browser alongside your web application, with full page and code context. Tidewave deeply integrates with your stack, from the database to the UI, making AI development more seamless and efficient.

José Valim

101,287 görüntüleme • 1 yıl önce

Claude Code Templates now has a web interface for browsing and contributing templates 🙌 What it does: Install templates for different languages/frameworks to get started with Claude Code faster. How to use: - Go to - Run: npm install -g claude-code-templates - Pick a template from the site - Copy and run the template command - Start coding with Claude Code The whole thing runs on GitHub - no fancy backend, no hidden stuff. Everything you're installing is right there in the repo for you to inspect. Contributing: Want to add your own template? Just follow the contribution guide and send a PR. Once merged, it automatically shows up on the site. That's it... nothing fancy, just something to save a few minutes when starting new projects with Claude Code Repo:

Claude Code Templates now has a web interface for browsing and contributing templates 🙌 What it does: Install templates for different languages/frameworks to get started with Claude Code faster. How to use: - Go to - Run: npm install -g claude-code-templates - Pick a template from the site - Copy and run the template command - Start coding with Claude Code The whole thing runs on GitHub - no fancy backend, no hidden stuff. Everything you're installing is right there in the repo for you to inspect. Contributing: Want to add your own template? Just follow the contribution guide and send a PR. Once merged, it automatically shows up on the site. That's it... nothing fancy, just something to save a few minutes when starting new projects with Claude Code Repo:

Daniel San

60,766 görüntüleme • 1 yıl önce

Today we're excited to launch `create-llama` - a single CLI command that allows you to scaffold a full stack LLM app over your data, powered by LlamaIndex 🦙 🔥 It’s the equivalent of `create-react-app` for AI engineers. Choose from 3 different backends: ✅ FastAPI (w/ LlamaIndex 🦙 Python) ✅ ExpressJS (w/ LlamaIndex 🦙 TS) ✅ Next.js (w/ LlamaIndex 🦙 TS) The frontend is a Next.js template using initial chat components from the Vercel AI SDK - with full streaming support, + shadcn UI or vanilla HTML/CSS for styling. This is a full-stack starting point, from which you can customize any component to build the LLM app of your liking, whether it’s simple extensions (change data source) or complete revamps (upgraded chat UX)! Next steps 🔮: - We’re going to be coming out with more examples in the next few weeks showing what you can build. - We’re going to be upgrading `create-llama` with a variety of different templates Check out the video (also attached) to see how it works 🎥: Repo directory: Full blog post detailing the usage here:

Today we're excited to launch `create-llama` - a single CLI command that allows you to scaffold a full stack LLM app over your data, powered by LlamaIndex 🦙 🔥 It’s the equivalent of `create-react-app` for AI engineers. Choose from 3 different backends: ✅ FastAPI (w/ LlamaIndex 🦙 Python) ✅ ExpressJS (w/ LlamaIndex 🦙 TS) ✅ Next.js (w/ LlamaIndex 🦙 TS) The frontend is a Next.js template using initial chat components from the Vercel AI SDK - with full streaming support, + shadcn UI or vanilla HTML/CSS for styling. This is a full-stack starting point, from which you can customize any component to build the LLM app of your liking, whether it’s simple extensions (change data source) or complete revamps (upgraded chat UX)! Next steps 🔮: - We’re going to be coming out with more examples in the next few weeks showing what you can build. - We’re going to be upgrading `create-llama` with a variety of different templates Check out the video (also attached) to see how it works 🎥: Repo directory: Full blog post detailing the usage here:

Jerry Liu

259,026 görüntüleme • 2 yıl önce

Hell froze over: announcing FormKit for React. Secretly framework-agnostic since inception, today we’re open sourcing the most popular Vue form library…for React. Why is this a big deal? 1. Forms are still hard. We (the creators of FormKit) thought form libraries were no longer necessary, given the trajectory of coding agents. It turns out we were wrong, and we learned this the hard way. Need repeating conditional fields nested 3 layers deep inside a dynamic component, with accessibility, validation, internationalization, and backend error placement? Turns out coding agents aren’t great at that. It’s table stakes for FormKit. 2. Single component. This matters more than you would think, but FormKit doesn’t ship lots of different components each with its own props. Instead, it has a single one: and unified props. This was done to provide a better DX to human engineers. It makes it easy to spot when a given component was part of the form’s data structure vs a presentational component. It turns out this matters even more to coding agents than humans. No matter where your coding agent is, whenever it sees “FormKit” it immediately knows “oh, that’s part of the form’s data”. 3. No plumbing. FormKit doesn’t require any manual data collection, event listening, or state tracking. It does all this for you on a heavily tested, framework agnostic, self-assembling graph. The only code your agent needs to write is declarative templates and submission handlers that respond to the state. 4. Dense colocation. FormKit’s syntax happens to be ideal for coding agents; nearly everything you need to know about a given input is *on* the input: Colocation dramatically improves the efficacy of coding agents. 5. DOM. FormKit, unlike most form frameworks in React, renders the actual DOM. This also increases colocation and best practices, meaning your coding agent is far more likely to produce consistent and high-quality output that looks and acts the way its supposed to. 6. Schema. FormKit’s own inputs are not written using Vue or React — instead, FormKit has its own render schema — think of it like an AST for the DOM — and you can modify it on the fly. It’s not very human-friendly to write, but it turns out most models are already pretty well trained on FormKit’s schema. Want your inputs to look a bit different on one form than another? No problem, your coding agent can easily make those changes *without* modifying the JSX structure at all. Oh, and any inputs you create for Vue work with React and vice versa. 7. Plugins. FormKit leans into the unstructured tree graph hard. The graph doesn’t just collect data, it also passes down configuration and plugins. Want one form to work a bit differently than another one? No problem — just add a plugin to the top of that form or group and its children will all receive that feature. You can even mass assign props and configuration this way. Of course, FormKit has been solving these exact issues for a long time, but it wasn’t until we started using it on our own projects with coding agents that we realized what a huge advantage it is. With so many people using coding agents with React, it made sense to unveil FormKit for what it has always been — a completely framework-agnostic form framework that happens to unlock your coding agents. ➡️

Hell froze over: announcing FormKit for React. Secretly framework-agnostic since inception, today we’re open sourcing the most popular Vue form library…for React. Why is this a big deal? 1. Forms are still hard. We (the creators of FormKit) thought form libraries were no longer necessary, given the trajectory of coding agents. It turns out we were wrong, and we learned this the hard way. Need repeating conditional fields nested 3 layers deep inside a dynamic component, with accessibility, validation, internationalization, and backend error placement? Turns out coding agents aren’t great at that. It’s table stakes for FormKit. 2. Single component. This matters more than you would think, but FormKit doesn’t ship lots of different components each with its own props. Instead, it has a single one: and unified props. This was done to provide a better DX to human engineers. It makes it easy to spot when a given component was part of the form’s data structure vs a presentational component. It turns out this matters even more to coding agents than humans. No matter where your coding agent is, whenever it sees “FormKit” it immediately knows “oh, that’s part of the form’s data”. 3. No plumbing. FormKit doesn’t require any manual data collection, event listening, or state tracking. It does all this for you on a heavily tested, framework agnostic, self-assembling graph. The only code your agent needs to write is declarative templates and submission handlers that respond to the state. 4. Dense colocation. FormKit’s syntax happens to be ideal for coding agents; nearly everything you need to know about a given input is on the input: Colocation dramatically improves the efficacy of coding agents. 5. DOM. FormKit, unlike most form frameworks in React, renders the actual DOM. This also increases colocation and best practices, meaning your coding agent is far more likely to produce consistent and high-quality output that looks and acts the way its supposed to. 6. Schema. FormKit’s own inputs are not written using Vue or React — instead, FormKit has its own render schema — think of it like an AST for the DOM — and you can modify it on the fly. It’s not very human-friendly to write, but it turns out most models are already pretty well trained on FormKit’s schema. Want your inputs to look a bit different on one form than another? No problem, your coding agent can easily make those changes without modifying the JSX structure at all. Oh, and any inputs you create for Vue work with React and vice versa. 7. Plugins. FormKit leans into the unstructured tree graph hard. The graph doesn’t just collect data, it also passes down configuration and plugins. Want one form to work a bit differently than another one? No problem — just add a plugin to the top of that form or group and its children will all receive that feature. You can even mass assign props and configuration this way. Of course, FormKit has been solving these exact issues for a long time, but it wasn’t until we started using it on our own projects with coding agents that we realized what a huge advantage it is. With so many people using coding agents with React, it made sense to unveil FormKit for what it has always been — a completely framework-agnostic form framework that happens to unlock your coding agents. ➡️

Justin Schroeder

11,677 görüntüleme • 5 ay önce

CLAUDE + CURSOR + REPLIT = MAGIC (FULL VIDEO TUTORIAL) You can now write create complex web apps with just english (No copy - paste) using the BEST AI Code generation tool on the market - Cursor. The only problem with cursor for a coding beginner like me, is that its not that easy to deploy web apps. Well, Replit ⠕ makes deploying web apps and creating templates incredibly easy. In this video goes over how to sync Cursor and Replit. And then using our new template we made an AI version of Trello by Atlassian in like 6 or 7 cursor composer prompts. --------------------- In this video: 00:00 - Intro 04:08 - Syncing Cursor and Replit 07:40 - setting up Firebase 10:27 - Using Cursor and Replit to Create Trello Front End 19:41 - Setting up Backend API endpoint (we will make dedicated video on this soon w/template) 21:09 - Adding AI features to Trello!

CLAUDE + CURSOR + REPLIT = MAGIC (FULL VIDEO TUTORIAL) You can now write create complex web apps with just english (No copy - paste) using the BEST AI Code generation tool on the market - Cursor. The only problem with cursor for a coding beginner like me, is that its not that easy to deploy web apps. Well, Replit ⠕ makes deploying web apps and creating templates incredibly easy. In this video goes over how to sync Cursor and Replit. And then using our new template we made an AI version of Trello by Atlassian in like 6 or 7 cursor composer prompts. --------------------- In this video: 00:00 - Intro 04:08 - Syncing Cursor and Replit 07:40 - setting up Firebase 10:27 - Using Cursor and Replit to Create Trello Front End 19:41 - Setting up Backend API endpoint (we will make dedicated video on this soon w/template) 21:09 - Adding AI features to Trello!

Riley Brown

309,493 görüntüleme • 2 yıl önce

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!

Avi Chawla

11,982 görüntüleme • 5 ay önce

🎉 Introducing Designr 🥳7️⃣ – The Smarter Way to Create Designr is here to make design simpler and more intuitive, whether you're starting something new or refining your latest project. It’s all about creativity, without the complexity. ✨ With Designr, you can: - Create with ease using the dynamic editor that gives you full control - Find inspiration with hundreds of fresh templates added daily - Turn ideas into designs in seconds with our smart Text-to-Design AI - Export your work in any format, any size - Animate your designs easily with our animation tools 🌐 Coming soon to LinqHub! We can’t wait for you to try it. $LNQ

🎉 Introducing Designr 🥳7️⃣ – The Smarter Way to Create Designr is here to make design simpler and more intuitive, whether you're starting something new or refining your latest project. It’s all about creativity, without the complexity. ✨ With Designr, you can: - Create with ease using the dynamic editor that gives you full control - Find inspiration with hundreds of fresh templates added daily - Turn ideas into designs in seconds with our smart Text-to-Design AI - Export your work in any format, any size - Animate your designs easily with our animation tools 🌐 Coming soon to LinqHub! We can’t wait for you to try it. $LNQ

LinqAI

31,288 görüntüleme • 1 yıl önce

2am, July 2 — and we’re still shipping! We're excited to share our newest innovation: Genspark AI Docs — the world’s first full-agentic AI document creator: Instantly create any document with a single prompt — and freely edit it! Hundreds of designer templates, all free! Supports both Rich Text and Markdown formats! With AI Slides, AI Sheets, and now AI Docs, our classic productivity trio for the AI era is finally complete. We believe that in the AI era, eventually all work can be done with a simple prompt. We call this vibe working! Start vibe working today with Genspark — your all-in-one AI workspace. This is just about 10% of what we have planned. There’s another exciting product on the way — can’t wait to keep building and sharing more with everyone!

2am, July 2 — and we’re still shipping! We're excited to share our newest innovation: Genspark AI Docs — the world’s first full-agentic AI document creator: Instantly create any document with a single prompt — and freely edit it! Hundreds of designer templates, all free! Supports both Rich Text and Markdown formats! With AI Slides, AI Sheets, and now AI Docs, our classic productivity trio for the AI era is finally complete. We believe that in the AI era, eventually all work can be done with a simple prompt. We call this vibe working! Start vibe working today with Genspark — your all-in-one AI workspace. This is just about 10% of what we have planned. There’s another exciting product on the way — can’t wait to keep building and sharing more with everyone!

Eric Jing

2,497,860 görüntüleme • 1 yıl önce

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 görüntüleme • 6 ay önce

long time no posting, here's some of the stuff we released in helium recently: - customizable keyboard shortcuts on all platforms - automatic updates on windows - frameless mode (previously zen mode), with floating sidebar, is now out of beta and included in settings by default - improved fingerprint noising: fixed the canvas noising algorithm and added protections against analysis attacks (thank you Cynthia 🐈 for your report, research, and assistance) - tab URL copying, one or multiple, formatted as a list with line breaks - manual tab hibernation, with an option to hibernate all tabs except for selected/active ones - an option to close tabs to the left (or above, in vertical layout) - redesigned toast notifications, now anchored to the active web page, and no longer blinding in dark mode - toast notification about newly opened background tabs in frameless mode (can be disabled in settings) - redesigned the infobar, it no longer looks out of place - improved QR code generation, now it's actually useful - downloads bubble is now shown instead of the full page whenever applicable - kagi search now supports reverse image search from image context menu - frameless mode animations are now smoother - better color contrast in light and dark modes - a lot of bug fixes and other minor improvements all of these changes are present in the latest version of helium. if you're using helium on windows, please update to the latest version, so your browser can be updated automatically from now on!

long time no posting, here's some of the stuff we released in helium recently: - customizable keyboard shortcuts on all platforms - automatic updates on windows - frameless mode (previously zen mode), with floating sidebar, is now out of beta and included in settings by default - improved fingerprint noising: fixed the canvas noising algorithm and added protections against analysis attacks (thank you Cynthia 🐈 for your report, research, and assistance) - tab URL copying, one or multiple, formatted as a list with line breaks - manual tab hibernation, with an option to hibernate all tabs except for selected/active ones - an option to close tabs to the left (or above, in vertical layout) - redesigned toast notifications, now anchored to the active web page, and no longer blinding in dark mode - toast notification about newly opened background tabs in frameless mode (can be disabled in settings) - redesigned the infobar, it no longer looks out of place - improved QR code generation, now it's actually useful - downloads bubble is now shown instead of the full page whenever applicable - kagi search now supports reverse image search from image context menu - frameless mode animations are now smoother - better color contrast in light and dark modes - a lot of bug fixes and other minor improvements all of these changes are present in the latest version of helium. if you're using helium on windows, please update to the latest version, so your browser can be updated automatically from now on!

Helium

178,528 görüntüleme • 3 ay önce

🚀 Introducing AgentCPM-Explore: The First Open-Source 4B-Agent Model to Conquer GAIA & Complex Real-World Tasks! 🤗 Hugging Face: 🔗 GitHub: ✨ Key Highlights: ✅ SOTA Agentic Performance: Sets a new benchmark for 4B-scale agent models—outperforming all peers, surpassing 8B models, and rivaling select 30B+ and closed-source LLMs. 🧠 Deep Research Capability: Excels at long-horizon reasoning, supports 100+ turns of autonomous interaction with multi-source cross-validation, human-like self-correction, and dynamic tool use + strategy adaptation—just like a real researcher! 🔓 Full-Stack Open Source: We’re open-sourcing the entire end-to-end agent stack—not just the model! Empower your own innovations with - AgentRL: Asynchronous reinforcement learning framework - AgentDock: Secure, extensible tool sandbox - AgentToLeaP: An one-click evaluation platform for agent tool-learning capabilitie - Full training data pipeline & reproducible workflows #AgentCPM #OpenSourceAI #AgenticAI #AI #GAIA #LLM #OpenBMB #AIAgents #HuggingFace

🚀 Introducing AgentCPM-Explore: The First Open-Source 4B-Agent Model to Conquer GAIA & Complex Real-World Tasks! 🤗 Hugging Face: 🔗 GitHub: ✨ Key Highlights: ✅ SOTA Agentic Performance: Sets a new benchmark for 4B-scale agent models—outperforming all peers, surpassing 8B models, and rivaling select 30B+ and closed-source LLMs. 🧠 Deep Research Capability: Excels at long-horizon reasoning, supports 100+ turns of autonomous interaction with multi-source cross-validation, human-like self-correction, and dynamic tool use + strategy adaptation—just like a real researcher! 🔓 Full-Stack Open Source: We’re open-sourcing the entire end-to-end agent stack—not just the model! Empower your own innovations with - AgentRL: Asynchronous reinforcement learning framework - AgentDock: Secure, extensible tool sandbox - AgentToLeaP: An one-click evaluation platform for agent tool-learning capabilitie - Full training data pipeline & reproducible workflows #AgentCPM #OpenSourceAI #AgenticAI #AI #GAIA #LLM #OpenBMB #AIAgents #HuggingFace

OpenBMB

13,996 görüntüleme • 8 ay önce

Anthropic engineer: "Harness engineering is a really rare skill right now - and it's hard to know if you're even good at it." how he actually thinks about building the full system: • step 1 → the model. already smarter than we use it. "freeze development - you'd find new capabilities for another 6-12 months" • step 2 → the harness. delete the steering. "we stopped using plan mode - the model thinks correctly" • step 3 → the agents. workflows let Claude build its own harness per task and spin sub-agents. what didn't fit in one context window now runs across many • step 4 → the context. "RAG is an anti-pattern. use grep." memory via files, clean context window, prompt caching. that's the stack most people optimize step 1. he optimizes all four. Watch the full video, then read the guide below on how to build an agentic system.

Anthropic engineer: "Harness engineering is a really rare skill right now - and it's hard to know if you're even good at it." how he actually thinks about building the full system: • step 1 → the model. already smarter than we use it. "freeze development - you'd find new capabilities for another 6-12 months" • step 2 → the harness. delete the steering. "we stopped using plan mode - the model thinks correctly" • step 3 → the agents. workflows let Claude build its own harness per task and spin sub-agents. what didn't fit in one context window now runs across many • step 4 → the context. "RAG is an anti-pattern. use grep." memory via files, clean context window, prompt caching. that's the stack most people optimize step 1. he optimizes all four. Watch the full video, then read the guide below on how to build an agentic system.

Codez

44,590 görüntüleme • 2 ay önce

Announcing my new course: Agentic AI! Building AI agents is one of the most in-demand skills in the job market. This course, available now at teaches you how. You'll learn to implement four key agentic design patterns: - Reflection, in which an agent examines its own output and figures out how to improve it - Tool use, in which an LLM-driven application decides which functions to call to carry out web search, access calendars, send email, write code, etc. - Planning, where you'll use an LLM to decide how to break down a task into sub-tasks for execution, and - Multi-agent collaboration, in which you build multiple specialized agents — much like how a company might hire multiple employees — to perform a complex task You'll also learn to take a complex application and systematically decompose it into a sequence of tasks to implement using these design patterns. But here's what I think is the most important part of this course: Having worked with many teams on AI agents, I've found that the single biggest predictor of whether someone executes well is their ability to drive a disciplined process for evals and error analysis. In this course, you'll learn how to do this, so you can efficiently home in on which components to improve in a complex agentic workflow. Instead of guessing what to work on, you'll let evals data guide you. This will put you significantly ahead of the game compared to the vast majority of teams building agents. Together, we'll build a deep research agent that searches, synthesizes, and reports, using all of these agentic design patterns and best practices. This self-paced course is taught in a vendor neutral way, using raw Python - without hiding details in a framework. You'll see how each step works, and learn the core concepts that you can then implement using any popular agentic AI framework, or using no framework. The only prerequisite is familiarity with Python, though knowing a bit about LLMs helps. Come join me, and let's build some agentic AI systems! Sign up to get started:

Announcing my new course: Agentic AI! Building AI agents is one of the most in-demand skills in the job market. This course, available now at teaches you how. You'll learn to implement four key agentic design patterns: - Reflection, in which an agent examines its own output and figures out how to improve it - Tool use, in which an LLM-driven application decides which functions to call to carry out web search, access calendars, send email, write code, etc. - Planning, where you'll use an LLM to decide how to break down a task into sub-tasks for execution, and - Multi-agent collaboration, in which you build multiple specialized agents — much like how a company might hire multiple employees — to perform a complex task You'll also learn to take a complex application and systematically decompose it into a sequence of tasks to implement using these design patterns. But here's what I think is the most important part of this course: Having worked with many teams on AI agents, I've found that the single biggest predictor of whether someone executes well is their ability to drive a disciplined process for evals and error analysis. In this course, you'll learn how to do this, so you can efficiently home in on which components to improve in a complex agentic workflow. Instead of guessing what to work on, you'll let evals data guide you. This will put you significantly ahead of the game compared to the vast majority of teams building agents. Together, we'll build a deep research agent that searches, synthesizes, and reports, using all of these agentic design patterns and best practices. This self-paced course is taught in a vendor neutral way, using raw Python - without hiding details in a framework. You'll see how each step works, and learn the core concepts that you can then implement using any popular agentic AI framework, or using no framework. The only prerequisite is familiarity with Python, though knowing a bit about LLMs helps. Come join me, and let's build some agentic AI systems! Sign up to get started:

Andrew Ng

890,025 görüntüleme • 11 ay önce

Bitcoin is money AND digital gold. The two are not mutually exclusive. For Michael Saylor - it's the purest form of digital credit. For David Marcus - it's the payment rails of the future. "No one cares what humans think about how people need to Bitcoin because it's an unopinionated, code-based money platform." The Lightspark founder is forging ahead with building Bitcoin-based payment rails, while Saylor and Strategy are doubling down on Bitcoin-backed financial products. "I'm really grateful that Michael is really focused on the store of value use case, and he can do that, and I can be the one focused on bringing utility to Bitcoin. Both things will actually help one another to make Bitcoin more relevant to many more people and that's the beauty of building on an open network," Marcus told Robert Baggs and me on our latest Chain Reaction show. Marcus has been keenly focused on abstracting complexity away from payments using Bitcoin payments infrastructure with the launch of Lightspark Grid. "It's like Bitcoin as a network being used to move all kinds of other money, whether it's stablecoin or fiat at the edges, and you don't even understand that you're using Bitcoin. For instance, if you're a SoFi client in the US, and you want to send money to Europe or India, Brazil or Mexico, you send dollars and the other person on the other side receives Mexican peso, you have no clue you're using Bitcoin. And it's like magical TCP/IP for money between payment systems in the world." Bitcoin infrastructure works. Like most widely adopted technologies, the average person has no idea what's going on under the hood. That is the future that takes Bitcoin global. And it's being built in real-time.

Bitcoin is money AND digital gold. The two are not mutually exclusive. For Michael Saylor - it's the purest form of digital credit. For David Marcus - it's the payment rails of the future. "No one cares what humans think about how people need to Bitcoin because it's an unopinionated, code-based money platform." The Lightspark founder is forging ahead with building Bitcoin-based payment rails, while Saylor and Strategy are doubling down on Bitcoin-backed financial products. "I'm really grateful that Michael is really focused on the store of value use case, and he can do that, and I can be the one focused on bringing utility to Bitcoin. Both things will actually help one another to make Bitcoin more relevant to many more people and that's the beauty of building on an open network," Marcus told Robert Baggs and me on our latest Chain Reaction show. Marcus has been keenly focused on abstracting complexity away from payments using Bitcoin payments infrastructure with the launch of Lightspark Grid. "It's like Bitcoin as a network being used to move all kinds of other money, whether it's stablecoin or fiat at the edges, and you don't even understand that you're using Bitcoin. For instance, if you're a SoFi client in the US, and you want to send money to Europe or India, Brazil or Mexico, you send dollars and the other person on the other side receives Mexican peso, you have no clue you're using Bitcoin. And it's like magical TCP/IP for money between payment systems in the world." Bitcoin infrastructure works. Like most widely adopted technologies, the average person has no idea what's going on under the hood. That is the future that takes Bitcoin global. And it's being built in real-time.

Gareth Jenkinson

19,181 görüntüleme • 7 ay önce

So Gemini 2.5 Pro is now 100% free?! You can literally use the world's best AI model and one-shot web apps. All you need is a free Google account: - Select 2.5 Pro (experimental) from the list - Activate the Canvas option at the bottom (advanced) - Send your prompt and enjoy Example you can reuse: "Develop a fully functional customer relationship management (CRM) web application tailored for a mid-sized healthcare provider. The application should streamline patient communication, appointment scheduling, record management, and billing processes. As a team of experienced full-stack web developers specializing in healthcare technology solutions, you will design and build this application. The application should feature a user-friendly interface with distinct dashboards for administrators, doctors, and staff. Include functionalities such as patient profiles with medical history, a messaging system, insurance verification, and report generation on key performance indicators like patient acquisition and appointment adherence. The front-end should be built using React. Maintain a professional, solution-oriented, and technically precise tone throughout the development process."

So Gemini 2.5 Pro is now 100% free?! You can literally use the world's best AI model and one-shot web apps. All you need is a free Google account: - Select 2.5 Pro (experimental) from the list - Activate the Canvas option at the bottom (advanced) - Send your prompt and enjoy Example you can reuse: "Develop a fully functional customer relationship management (CRM) web application tailored for a mid-sized healthcare provider. The application should streamline patient communication, appointment scheduling, record management, and billing processes. As a team of experienced full-stack web developers specializing in healthcare technology solutions, you will design and build this application. The application should feature a user-friendly interface with distinct dashboards for administrators, doctors, and staff. Include functionalities such as patient profiles with medical history, a messaging system, insurance verification, and report generation on key performance indicators like patient acquisition and appointment adherence. The front-end should be built using React. Maintain a professional, solution-oriented, and technically precise tone throughout the development process."

Paul Couvert

401,067 görüntüleme • 1 yıl önce

Insane progress for small language models! MiniCPM5-2B is a dense 2B-parameter model by OpenBMB from China that's built for reasoning, coding, and tool use on resource-constrained hardware. The model specifically excels at coding and tool calling, two capabilities central to the shift from on-device LLMs to on-device agents. Instead of only answering prompts, it can use tools, generate code, carry information between steps, and complete multi-step tasks. I ran it 100% locally and connected it to a small investigation agent with one request: > Revenue dropped last week. Investigate what happened, quantify the impact, identify the likely cause, and produce an incident report with supporting evidence. The evidence was spread across orders, traffic, payments, refunds, and deployment logs. The model inspected the files, wrote its own queries, analyzed the intermediate results, and decided what to investigate next. Each tool result informed the next action, so the final report depended on the model maintaining a coherent investigation across the complete trajectory. The recording shows the actual task from beginning to end. It starts with the revenue question, follows the tool calls and supporting evidence, and ends with a quantified diagnosis and incident report. The data, tool execution, and model inference all remained on my machine. These capabilities were optimized through Agentic Pre-training, SFT, and large-scale RL. They do not come entirely from an application-level agent framework. MiniCPM5-2B supports SGLang, vLLM, llama(.)cpp, Ollama, iOS, Android, and HarmonyOS. OpenBMB has also released the model weights and parts of the training recipes and data resources behind it. Download MiniCPM5-2B: A 2B model can now maintain enough state to coordinate tools and complete a useful investigation on local hardware.

Insane progress for small language models! MiniCPM5-2B is a dense 2B-parameter model by OpenBMB from China that's built for reasoning, coding, and tool use on resource-constrained hardware. The model specifically excels at coding and tool calling, two capabilities central to the shift from on-device LLMs to on-device agents. Instead of only answering prompts, it can use tools, generate code, carry information between steps, and complete multi-step tasks. I ran it 100% locally and connected it to a small investigation agent with one request: > Revenue dropped last week. Investigate what happened, quantify the impact, identify the likely cause, and produce an incident report with supporting evidence. The evidence was spread across orders, traffic, payments, refunds, and deployment logs. The model inspected the files, wrote its own queries, analyzed the intermediate results, and decided what to investigate next. Each tool result informed the next action, so the final report depended on the model maintaining a coherent investigation across the complete trajectory. The recording shows the actual task from beginning to end. It starts with the revenue question, follows the tool calls and supporting evidence, and ends with a quantified diagnosis and incident report. The data, tool execution, and model inference all remained on my machine. These capabilities were optimized through Agentic Pre-training, SFT, and large-scale RL. They do not come entirely from an application-level agent framework. MiniCPM5-2B supports SGLang, vLLM, llama(.)cpp, Ollama, iOS, Android, and HarmonyOS. OpenBMB has also released the model weights and parts of the training recipes and data resources behind it. Download MiniCPM5-2B: A 2B model can now maintain enough state to coordinate tools and complete a useful investigation on local hardware.

Avi Chawla

13,954 görüntüleme • 4 gün önce