Загрузка видео...

Не удалось загрузить видео

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

На главную

Convex Chef can one-shot a fully collaborative Notion clone! Can any other codegen tool do that? (Chef isn't doing anything fancy, it's just using Convex and its component system. You could easily build the same thing yourself on Convex.)

James Cowling

6,474 subscribers

26,637 просмотров • 1 год назад •via X (Twitter)

Наука и технологии Образование

Anya Rossi• Live Now

Private livecam show

Комментарии: 12

Фото профиля Josh Abulafia

Josh Abulafia1 год назад

@convex_dev I was a fan of convex until I realised the cto is an Aussie. Now a super fan 🤣

Фото профиля James Cowling

James Cowling1 год назад

@convex_dev You had me worried in that first sentence mate

Фото профиля Matt Figdore

Matt Figdore2 лет назад

This is the biggest productivity cheat code right now. Kiss reading documents goodbye. You can get an instant summary of any document with this tool.

Фото профиля wearifulpoet

wearifulpoet1 год назад

@convex_dev Chef makes me question if I'm wrong about vibe coding

Фото профиля David Marquez

David Marquez1 год назад

Would love to see GitHub sync with Chef. I started a project with Chef, downloaded the repo and messed around with it, then wanted to sync it back to Chef to adjust the backend. Since it didn’t have it, I had to tinker with the project settings and then let Claude Code continue building the Convex features for me. I guess I would’ve been much more confident using Chef to make edits given its system prompts. 🙂

Фото профиля velocity

velocity1 год назад

@convex_dev Incredible work dude. Planning on messing around with it this weekend.

Фото профиля Paschal

Paschal1 год назад

@convex_dev Love the pfp Gordon Ramsey of Databases 😂

Фото профиля James Cowling

James Cowling1 год назад

@convex_dev With slightly less yelling at people

Фото профиля Will Chen

Will Chen1 год назад

@convex_dev is the collaborative feature thru a Convex component or Yjs ?

Фото профиля James Cowling

James Cowling1 год назад

@convex_dev The Convex component uses Tiptap or BlockNote, which are based on ProseMirror:

Фото профиля Raheem Gordon

Raheem Gordon1 год назад

@convex_dev The 1mb per document limit in convex is really crippling, pasting a couple of images using src= data:image/png;base64 could fill it up real quick

Фото профиля James Cowling

James Cowling1 год назад

@convex_dev I think there are scenarios where we need a larger document limit but storing images inside a database generally isn’t a great idea. Is the problem with Convex Storage that it’s more awkward to use?

Похожие видео

Wow very easy to create a Codex Site with a Convex DB that your agent can write to. You can make a todo list app that is hosted on Codex Sites, then tell Codex to make a skill that allows the agent to WRITE/EDIT to that todo list db. And then in any chat you can add to your list. Here's example.

Wow very easy to create a Codex Site with a Convex DB that your agent can write to. You can make a todo list app that is hosted on Codex Sites, then tell Codex to make a skill that allows the agent to WRITE/EDIT to that todo list db. And then in any chat you can add to your list. Here's example.

Riley Brown

54,081 просмотров • 1 месяц назад

I always wondered which Ollama model my machine could run properly. Now you can easily do that using llms-checker It's a CLI tool that checks your system specs and recommends the best models to run on Ollama based on what your machine npm install -g llm-checker

I always wondered which Ollama model my machine could run properly. Now you can easily do that using llms-checker It's a CLI tool that checks your system specs and recommends the best models to run on Ollama based on what your machine npm install -g llm-checker

Jaydeep

112,240 просмотров • 4 месяцев назад

He said Codex Computer Use on macOS isn't special. Omarchy can do the same thing. Challenge accepted. So I had Codex draw him a painting using only its mouse, no other tools. Holler at me when you can do this.

He said Codex Computer Use on macOS isn't special. Omarchy can do the same thing. Challenge accepted. So I had Codex draw him a painting using only its mouse, no other tools. Holler at me when you can do this.

am.will

64,077 просмотров • 2 месяцев назад

today, on the DL, Notion released WORKERS. workers are a generic code execution environment that let you build interfaces within Notion the first interface we're exposing is the ability to make your own custom agent tools you can now make a tool for a custom agent that executes arbitrary code... and if you can execute arbitrary code, you can do pretty much anything!

today, on the DL, Notion released WORKERS. workers are a generic code execution environment that let you build interfaces within Notion the first interface we're exposing is the ability to make your own custom agent tools you can now make a tool for a custom agent that executes arbitrary code... and if you can execute arbitrary code, you can do pretty much anything!

Sam Catania

81,830 просмотров • 4 месяцев назад

Notion 3.0 with Agents is out today! It's the first Knowledge Work Agent in the world. It works with Notion databases. It can do multi-step actions and autonomous work up to 20+ mins, and a brand-new memory system (using Notion pages and databases! 👌) With 3.0, Notion isn’t just your tool — it’s your teammate that works while you sleep. Two types of agents: Personal Agent: Can do anything you can do in Notion. Remembers and learns your preferences as you work. Has a little personality (accessories like a duck hat 🦆.) Custom Agents (early access): Spin up a small team. Hand them the repetitive stuff. They work while you sleep! And Notion Agents work across Notion Calendar, Notion Mail, plus MCP and more. Available today! Try it. Tell us what’s missing. We’ll keep shipping, so you can focus on your life’s work 🫡

Ivan Zhao

200,937 просмотров • 9 месяцев назад

This is the mistake they all make. Afua Asantewaa, Chef Faila, and now Chef Smith is doing the same. They're so focused on the fame and not the record-breaking. How can you stop cooking for over 1 minute just vibing to a musician singing for you? 🤣

This is the mistake they all make. Afua Asantewaa, Chef Faila, and now Chef Smith is doing the same. They're so focused on the fame and not the record-breaking. How can you stop cooking for over 1 minute just vibing to a musician singing for you? 🤣

Headless YouTuber

98,302 просмотров • 2 лет назад

Ilya and David Chalmers, the same vibe.. "Anything which I can learn, anything which any one of you can learn, the AI could do as well. The reason is that all of us have a brain, and the brain is a biological computer. So why can't the digital computer, do the same things?"

Ilya and David Chalmers, the same vibe.. "Anything which I can learn, anything which any one of you can learn, the AI could do as well. The reason is that all of us have a brain, and the brain is a biological computer. So why can't the digital computer, do the same things?"

Rohan Paul

119,333 просмотров • 8 месяцев назад

Factory is better than Devin, Codex, and Jules, and it's not even close. This is not just a fully autonomous software engineer but also a product manager and researcher. It's the entire package you need to build a new project or dramatically expand an existing one. I recorded a quick video so you can see how it works. You can use these autonomous Droids from Factory. Here is what they can do: 1. Build a full production-grade app from scratch 2. Develop new features for an existing codebase 3. Migrations or refactors on your codebase 4. Build integrations 5. Generate complete feature specifications 6. Solve and close issues from your issue management system 7. Do deep research on any software topics And Factory can connect to Linear, GitHub, Google Drive, Slack, Jira, Sentry, GitLab, and Notion to do its work. You can use any of the big models to do what you need.

Factory is better than Devin, Codex, and Jules, and it's not even close. This is not just a fully autonomous software engineer but also a product manager and researcher. It's the entire package you need to build a new project or dramatically expand an existing one. I recorded a quick video so you can see how it works. You can use these autonomous Droids from Factory. Here is what they can do: 1. Build a full production-grade app from scratch 2. Develop new features for an existing codebase 3. Migrations or refactors on your codebase 4. Build integrations 5. Generate complete feature specifications 6. Solve and close issues from your issue management system 7. Do deep research on any software topics And Factory can connect to Linear, GitHub, Google Drive, Slack, Jira, Sentry, GitLab, and Notion to do its work. You can use any of the big models to do what you need.

Santiago

70,099 просмотров • 1 год назад

Meet Data Scout. It's a $500k data scientist for every employee. One of those agents every business needs. > Has Snowflake access (+ Notion, Slack, Github) > Runs deep analysis on all user and account data > Can be called by other agents for recurring reports Data Scout is one of the most used agents at Notion. And you can build one.

Meet Data Scout. It's a $500k data scientist for every employee. One of those agents every business needs. > Has Snowflake access (+ Notion, Slack, Github) > Runs deep analysis on all user and account data > Can be called by other agents for recurring reports Data Scout is one of the most used agents at Notion. And you can build one.

Hurley

33,300 просмотров • 3 месяцев назад

Do you actually know what convex optimization is in the geometric, guarantee-theoretic sense or have you only met it through solvers and loss curves? Convexity is rare comfort in optimization...there are no spurious local minima, no surprise traps, and inequalities you can use like tools instead of prayers. So, what is this convexity? Let x = (x₁, x₂) and let f(x) be convex. Plot the surface z = f(x). Pick a contact point x₀. The local slope is the gradient p = ∇f(x₀). That p is exactly the data that defines the supporting plane: z = f(x₀) + p · (x − x₀). Thus, f is said to be convex because for every x, f(x) ≥ f(x₀) + p · (x − x₀). So the plane at x₀ can slide under the surface, but it never slices through it. Not near the point...everywhere. Now for here is the interesting part: The slope becomes a coordinate system! Rewrite the same plane as z = p · x − b, where b is the offset. Because the plane passes through (x₀, f(x₀)), the offset is forced to be b = p · x₀ − f(x₀). And that number isn’t just geometry trivia. It’s the convex conjugate: f*(p) = sup over x ( p · x − f(x) ). At a differentiable contact point, the supporting plane touches f tightly enough that the supremum is achieved at x₀, giving the identity f*(p) = p · x₀ − f(x₀) when p = ∇f(x₀). So one moving contact point gives two linked readouts: primal position x₀ dual position (slope) p = ∇f(x₀) dual offset f*(p) One surface. Two worlds. #ConvexOptimization #Optimization #MachineLearning #SignalProcessing #AppliedMath #Engineering

Do you actually know what convex optimization is in the geometric, guarantee-theoretic sense or have you only met it through solvers and loss curves? Convexity is rare comfort in optimization...there are no spurious local minima, no surprise traps, and inequalities you can use like tools instead of prayers. So, what is this convexity? Let x = (x₁, x₂) and let f(x) be convex. Plot the surface z = f(x). Pick a contact point x₀. The local slope is the gradient p = ∇f(x₀). That p is exactly the data that defines the supporting plane: z = f(x₀) + p · (x − x₀). Thus, f is said to be convex because for every x, f(x) ≥ f(x₀) + p · (x − x₀). So the plane at x₀ can slide under the surface, but it never slices through it. Not near the point...everywhere. Now for here is the interesting part: The slope becomes a coordinate system! Rewrite the same plane as z = p · x − b, where b is the offset. Because the plane passes through (x₀, f(x₀)), the offset is forced to be b = p · x₀ − f(x₀). And that number isn’t just geometry trivia. It’s the convex conjugate: f(p) = sup over x ( p · x − f(x) ). At a differentiable contact point, the supporting plane touches f tightly enough that the supremum is achieved at x₀, giving the identity f(p) = p · x₀ − f(x₀) when p = ∇f(x₀). So one moving contact point gives two linked readouts: primal position x₀ dual position (slope) p = ∇f(x₀) dual offset f*(p) One surface. Two worlds. #ConvexOptimization #Optimization #MachineLearning #SignalProcessing #AppliedMath #Engineering

Mathelirium

38,506 просмотров • 6 месяцев назад

Marc Andreessen on the question at the center of data center discourse & why it's so important: "Can you build anything in America anymore? Can you build a factory? Can you build a chip plant? Can you build a power plant? Can you build a refinery? Can you build a pipeline? Can you build housing?" "One of the common themes in American life for the last 30 years is the answer to those questions is generally, no, you can't do any of those things." "Take as an example, Silicon Valley, right? So all the chips are made in Taiwan. Well, 40 years ago, all the chips were made in California." "Can you build things in America? Can you build a factory? Can you build an energy plant? Can you build a data center? Can you build housing?" "And on every single one of those, there's this massive problem which is, right now in many cases, in many places, no you can't." Marc Andreessen 🇺🇸 with Joe Rogan

Marc Andreessen on the question at the center of data center discourse & why it's so important: "Can you build anything in America anymore? Can you build a factory? Can you build a chip plant? Can you build a power plant? Can you build a refinery? Can you build a pipeline? Can you build housing?" "One of the common themes in American life for the last 30 years is the answer to those questions is generally, no, you can't do any of those things." "Take as an example, Silicon Valley, right? So all the chips are made in Taiwan. Well, 40 years ago, all the chips were made in California." "Can you build things in America? Can you build a factory? Can you build an energy plant? Can you build a data center? Can you build housing?" "And on every single one of those, there's this massive problem which is, right now in many cases, in many places, no you can't." Marc Andreessen 🇺🇸 with Joe Rogan

a16z

136,851 просмотров • 1 месяц назад

President Trump: "The 2024 election is our one shot to save our country, and we need a leader who is ready to do that on day one... To change the whole system, you need a president that can take on the whole system."

President Trump: "The 2024 election is our one shot to save our country, and we need a leader who is ready to do that on day one... To change the whole system, you need a president that can take on the whole system."

Trump War Room

386,609 просмотров • 3 лет назад

EllioTrades thinks the dumbest thing a 24 year old can do is sit and plan. “If you're overthinking everything, you just won't get anything done in your life.” "Action should be the number one output that you're focused on." "Be cringe, put yourself out there, do stuff."

EllioTrades thinks the dumbest thing a 24 year old can do is sit and plan. “If you're overthinking everything, you just won't get anything done in your life.” "Action should be the number one output that you're focused on." "Be cringe, put yourself out there, do stuff."

zynn

27,270 просмотров • 3 месяцев назад

You can now delegate tasks to Cursor directly from Notion. It's built on the Cursor SDK, so every cloud agent runs on the same models, harness, and runtime that power Cursor. @Cursor on any spec or assign it a task to open a PR your whole team can review.

You can now delegate tasks to Cursor directly from Notion. It's built on the Cursor SDK, so every cloud agent runs on the same models, harness, and runtime that power Cursor. @Cursor on any spec or assign it a task to open a PR your whole team can review.

Cursor

312,021 просмотров • 20 дней назад

Starting your financial planning early is one of the smartest moves you can make, and the National Pension System (NPS) is a powerful tool to help you do that! Investing in NPS now means setting yourself up for a stress-free and prosperous future.

Starting your financial planning early is one of the smartest moves you can make, and the National Pension System (NPS) is a powerful tool to help you do that! Investing in NPS now means setting yourself up for a stress-free and prosperous future.

PFRDA

32,662,113 просмотров • 9 месяцев назад

"When you're arrested, you're told 'anything you say can and will be used against you in a court of law' Without privacy, any and everything you do onchain is the same thing. All that information is freely available." - mert

"When you're arrested, you're told 'anything you say can and will be used against you in a court of law' Without privacy, any and everything you do onchain is the same thing. All that information is freely available." - mert

Bankless

30,072 просмотров • 1 месяц назад

.Joe Lonsdale says the best thing Peter Thiel taught him was how to win with focus: “Effort on any project is convex.” “If you spend 80% of your time focused on something—that’s half as good as spending 90% of your time.” “Being 99th percentile is worth so much more than being 90th percentile. Because it means you’re number one.” “And being number one is worth a lot.” “Anything I invest in—someone really amazing is making it their main thing. The CEO has to be all in.” Via Chris Williamson

.Joe Lonsdale says the best thing Peter Thiel taught him was how to win with focus: “Effort on any project is convex.” “If you spend 80% of your time focused on something—that’s half as good as spending 90% of your time.” “Being 99th percentile is worth so much more than being 90th percentile. Because it means you’re number one.” “And being number one is worth a lot.” “Anything I invest in—someone really amazing is making it their main thing. The CEO has to be all in.” Via Chris Williamson

Jawwwn

150,853 просмотров • 14 дней назад

Last week I spent $20,000 on Mac Studios so I could run OpenClaw locally Fully powered by local AI models running 24/7 Now my agent: • Is doing tasks 24/7/365 • Doesn't cost any tokens • Is fully private In this video I cover how it works and how you can do the same thing:

Last week I spent $20,000 on Mac Studios so I could run OpenClaw locally Fully powered by local AI models running 24/7 Now my agent: • Is doing tasks 24/7/365 • Doesn't cost any tokens • Is fully private In this video I cover how it works and how you can do the same thing:

Alex Finn

573,232 просмотров • 5 месяцев назад

“You go surprise say one day, you will wake up and realise you don old without using your full youth to do anything…. Just because the government we have doesn’t give you the room to do any better thing….. Imagine a grown adult and graduate of fishery doing liquid soap?…”

“You go surprise say one day, you will wake up and realise you don old without using your full youth to do anything…. Just because the government we have doesn’t give you the room to do any better thing….. Imagine a grown adult and graduate of fishery doing liquid soap?…”

MaziTundeEdnutfan

13,452 просмотров • 1 месяц назад