正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

You should really stop using Zapier or Make. Deploying Python scripts on Replit takes less than 5 min and is cheaper. Just describe what you want to automate and AI takes care of writing the code. For example, I created an automation that merges all the PDFs in a... show more

Paul Couvert

220,580 subscribers

163,002 次观看 • 1 年前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

10 条评论

Prompter 的头像

Prompter1 年前

you're so right! I save hundreds a month by ditching my SaaS and building my own automations. here's an AI assistant that lives in my email inbox and extracts receipt / invoices data and populates my expense sheets! took me maybe 30 mins to build!

Paul Couvert 的头像

Paul Couvert1 年前

Love the idea! Looks like a huge time saver.

Jeff Burke ⠕ 的头像

Jeff Burke ⠕1 年前

This is cool!!! Some helpful notes. If you upgrade to Replit Core: - You can use Claude 3.5 directly in our AI pane - You can deploy to a “Scheduled” deployment which will run at whatever frequency you want Plus, you can use the “Secrets” pane to store API keys. Great job!

Paul Couvert 的头像

Paul Couvert1 年前

Didn't know about the 2nd feature, thanks for the update! Will 100% upgrade to Core. Agent justifies it all by itself.

Jeremy Nguyen ✍🏼 🚢 的头像

Jeremy Nguyen ✍🏼 🚢1 年前

How does it keep running at scheduled intervals? Do you run it as a cron job or something, Paul?

Paul Couvert 的头像

Paul Couvert1 年前

There are 2 ways to do this I think: - Hard code it like in the video and just deploy the app with Replit - With Replit Core you can deploy whenever you want at whatever frequency you want (learned this yesterday from Jeff)

Amira Zairi 的头像

Amira Zairi1 年前

This is super helpful! Thanks for sharing

Paul Couvert 的头像

Paul Couvert1 年前

My pleasure, Amira. Thanks for watching!

positiveblue ⚡️🍠 的头像

positiveblue ⚡️🍠1 年前

Really cool tutorial but you are wrong about @zapier The future is more people using BOTH

Paul Couvert 的头像

Paul Couvert1 年前

That's what I thought as well a few weeks ago. But given how fast AI coding is improving I don't think that's the case for Zapier (in its current form).

相关视频

You should really stop using Zapier, Make or n8n Generating a Python script and running it is much faster (and cheaper) using: - o3-mini / Claude / Gemini to create the script - Python Code Runner (free Chrome extension) to run it And it only takes a few minutes. Link below

You should really stop using Zapier, Make or n8n Generating a Python script and running it is much faster (and cheaper) using: - o3-mini / Claude / Gemini to create the script - Python Code Runner (free Chrome extension) to run it And it only takes a few minutes. Link below

Paul Couvert

166,508 次观看 • 1 年前

Free and open source Alternative to Cursor's composer feature directly in Replit Cursor's composer is getting a lot of buzz because it lets anyone create apps using just English. "Aider" lets you do exactly the same thing: - Without having to pay a subscription - Using Claude 3.5 Sonnet - Right in Replit You don't need to know how to write a single line of code to use it. Nor do you have to synchronize anything: You generate the code, test and deploy your app all in one place! -------------- Let me know if you'd like a quick tutorial on how to install it in Replit (less than 2 minutes).

Free and open source Alternative to Cursor's composer feature directly in Replit Cursor's composer is getting a lot of buzz because it lets anyone create apps using just English. "Aider" lets you do exactly the same thing: - Without having to pay a subscription - Using Claude 3.5 Sonnet - Right in Replit You don't need to know how to write a single line of code to use it. Nor do you have to synchronize anything: You generate the code, test and deploy your app all in one place! -------------- Let me know if you'd like a quick tutorial on how to install it in Replit (less than 2 minutes).

Paul Couvert

85,985 次观看 • 1 年前

AI agents are a real paradigm shift You can literally make your computer work for you to do any task. All I've used is: - Replit to get it running - Browser Use (free & open source) - Google AI Studio for the API - DeepSeek R1 to implement it (I'm not paying $200 for ChatGPT sorry) Here the AI agent fetches information on its own and reuses it to write new content. But you can use it for literally any industry. Run it once or schedule it at regular intervals... you're in total control And it's nothing like automating on Make or Zapier: AI agents adapt to every situation and can handle far more complex scenarios.

AI agents are a real paradigm shift You can literally make your computer work for you to do any task. All I've used is: - Replit to get it running - Browser Use (free & open source) - Google AI Studio for the API - DeepSeek R1 to implement it (I'm not paying $200 for ChatGPT sorry) Here the AI agent fetches information on its own and reuses it to write new content. But you can use it for literally any industry. Run it once or schedule it at regular intervals... you're in total control And it's nothing like automating on Make or Zapier: AI agents adapt to every situation and can handle far more complex scenarios.

Paul Couvert

76,636 次观看 • 1 年前

Instructions for syncing Replit with Cursor This looks like a lot but it takes 3 minutes once you get it down. HUGE shout out to @anshnanda_ for showing me how to do this. Open Repl or Create with our Template Go to Cursor - Click Terminal - Click CMD K - Type "Generate an SSH Key For Replit, name it Replit, and copy the public key to the clipboard" - if prompted to overwrite put "y", then enter - it'll prompt about passphrase, just press enter - it'll prompt about passphrase again, just press enter - this automatically copies the ssh key to clipboard Go to Replit - plus sign (new tab) and type SSH - go to SSH panel - Click Keys - Add SSH Key - Give it Label (doesn't matter what you call it) - Paste in that code from cursor that was automatically added to your clipboard in previous process. Should be a fat chunk of text. (If its smaller, you didn't specify the public key) - Go to connect tab in same panel - Copy the Shell command Go Back to Cursor - Open with SSH - Paste that shell command on top - Click Add new SSH Host - Paste the command again - Enter - Click the first option that pops up - Bottom Right of screen click connect - Click Continue - Open Folder - Click name of Replit Project (Repl) If you are using the template just set up firebase as I do quickly and you are set up with database authentication and storage.

Instructions for syncing Replit with Cursor This looks like a lot but it takes 3 minutes once you get it down. HUGE shout out to @anshnanda_ for showing me how to do this. Open Repl or Create with our Template Go to Cursor - Click Terminal - Click CMD K - Type "Generate an SSH Key For Replit, name it Replit, and copy the public key to the clipboard" - if prompted to overwrite put "y", then enter - it'll prompt about passphrase, just press enter - it'll prompt about passphrase again, just press enter - this automatically copies the ssh key to clipboard Go to Replit - plus sign (new tab) and type SSH - go to SSH panel - Click Keys - Add SSH Key - Give it Label (doesn't matter what you call it) - Paste in that code from cursor that was automatically added to your clipboard in previous process. Should be a fat chunk of text. (If its smaller, you didn't specify the public key) - Go to connect tab in same panel - Copy the Shell command Go Back to Cursor - Open with SSH - Paste that shell command on top - Click Add new SSH Host - Paste the command again - Enter - Click the first option that pops up - Bottom Right of screen click connect - Click Continue - Open Folder - Click name of Replit Project (Repl) If you are using the template just set up firebase as I do quickly and you are set up with database authentication and storage.

Riley Brown

41,111 次观看 • 1 年前

BREAKING: Replit just launched mobile apps. Now you can build in Replit ⠕ and submit straight to the App Store for review. Describe your app → build it on Replit → test on your phone → publish to the App Store. I built a unicorn pet app for my niece: - Worked with Replit Agent to build it out - Scanned a QR code to download and test on my phone - One click to send to App Store Connect for review - A couple submissions later, it's live in the App Store! 🙌 I didn't write a single line of code! Just described what I wanted to Agent. Amazing! 😅 Go build something!! 👇

BREAKING: Replit just launched mobile apps. Now you can build in Replit ⠕ and submit straight to the App Store for review. Describe your app → build it on Replit → test on your phone → publish to the App Store. I built a unicorn pet app for my niece: - Worked with Replit Agent to build it out - Scanned a QR code to download and test on my phone - One click to send to App Store Connect for review - A couple submissions later, it's live in the App Store! 🙌 I didn't write a single line of code! Just described what I wanted to Agent. Amazing! 😅 Go build something!! 👇

Manny Bernabe

30,925 次观看 • 6 个月前

Open AI released Operator, an agent that can use the browser to perform and automate tasks for you! I have built an Open Source version of Operator using Browser Use, running locally on your computer. 100% Open Source

Open AI released Operator, an agent that can use the browser to perform and automate tasks for you! I have built an Open Source version of Operator using Browser Use, running locally on your computer. 100% Open Source

Sumanth

62,485 次观看 • 1 年前

Finally, a browser automation framework for Agents that actually works in production (open-source)! Typical browser automation tools like Selenium or Playwright require you to hard-code automation. These are brittle since one change in the website can disrupt the full workflow. On the other hand, high-level Agents like OpenAI Operator can be unpredictable in production. Stagehand is an open-source framework that bridges the gap between: - brittle traditional automation like Playwright, Selenium, etc. and - unpredictable full-agent solutions like OpenAI Operator. Key features: - Use AI when you want to navigate unfamiliar pages. - Use code (Playwright) when you know exactly what to do. - Preview AI actions before running them. - Cache repeatable actions to save tokens. - Compatible with SOTA computer use models with just one line of code. - Available in both Python and TypeScript SDK. Stagehand also has an open-source MCP server. Find a link to the repo in the comments! 👉 Over to you: Would you use this instead of Selenium?

Finally, a browser automation framework for Agents that actually works in production (open-source)! Typical browser automation tools like Selenium or Playwright require you to hard-code automation. These are brittle since one change in the website can disrupt the full workflow. On the other hand, high-level Agents like OpenAI Operator can be unpredictable in production. Stagehand is an open-source framework that bridges the gap between: - brittle traditional automation like Playwright, Selenium, etc. and - unpredictable full-agent solutions like OpenAI Operator. Key features: - Use AI when you want to navigate unfamiliar pages. - Use code (Playwright) when you know exactly what to do. - Preview AI actions before running them. - Cache repeatable actions to save tokens. - Compatible with SOTA computer use models with just one line of code. - Available in both Python and TypeScript SDK. Stagehand also has an open-source MCP server. Find a link to the repo in the comments! 👉 Over to you: Would you use this instead of Selenium?

Avi Chawla

101,419 次观看 • 1 年前

Imagine a computer where you don’t need to learn 10 apps to get work done. You just tell it what you want, and it adapts to how you work. I tested Happycapy with a real use case and created an image and a video. No coding, no complex software. Do this: - Build automations that run on schedule - Deploy agent teams that work for you AI molds how you work, not the other way around. If you can use a computer, you can make anything happen. Start your first Automation and Agent teams today.

Imagine a computer where you don’t need to learn 10 apps to get work done. You just tell it what you want, and it adapts to how you work. I tested Happycapy with a real use case and created an image and a video. No coding, no complex software. Do this: - Build automations that run on schedule - Deploy agent teams that work for you AI molds how you work, not the other way around. If you can use a computer, you can make anything happen. Start your first Automation and Agent teams today.

Aaliya

17,042 次观看 • 5 个月前

Announcing Native Mobile App support on Replit. Now you can build iOS and Android apps that you can take all the way to the App Store without writing any code, powered by Replit Assistant. This is early access—full Agent support coming soon!

Announcing Native Mobile App support on Replit. Now you can build iOS and Android apps that you can take all the way to the App Store without writing any code, powered by Replit Assistant. This is early access—full Agent support coming soon!

Amjad Masad

812,779 次观看 • 1 年前

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

309,237 次观看 • 1 年前

You can use a 100% open source and MUCH cheaper/free alternative to Claude Code and Opus 4.5 OpenCode + MiniMax M2.1 can even build a 3D website using pure vibe coding. Steps are really simple: 1. Install OpenCode using the command 'npm i -g opencode-ai' 2. Get your MiniMax API key here: 3. Configure the MiniMax (official) mode Just type "opencode connect minimax" Coding plans start at $2… 10x cheaper than Claude Code (yes). You can also invite friends so they can get 10% off and you’ll get 10% API credits. (You can also use it locally if you have the config) And you're ready to build and iterate almost endlessly since the model is both way faster and cheaper than Opus in CC.

You can use a 100% open source and MUCH cheaper/free alternative to Claude Code and Opus 4.5 OpenCode + MiniMax M2.1 can even build a 3D website using pure vibe coding. Steps are really simple: 1. Install OpenCode using the command 'npm i -g opencode-ai' 2. Get your MiniMax API key here: 3. Configure the MiniMax (official) mode Just type "opencode connect minimax" Coding plans start at $2… 10x cheaper than Claude Code (yes). You can also invite friends so they can get 10% off and you’ll get 10% API credits. (You can also use it locally if you have the config) And you're ready to build and iterate almost endlessly since the model is both way faster and cheaper than Opus in CC.

Paul Couvert

42,443 次观看 • 6 个月前

You can now fine-tune Llama 3 without writing a single line of code! We are moving at breakneck speed. I recorded a video to show you how to fine-tune any open-source model in a few minutes. I'm using a GPT capable of taking a problem and turning it into a fine-tuned model that will solve it. You don't have to write any code. You only need to explain to a GPT what problem you want to solve and tell it you want to use Llama 3. For example, "fine-tune Llama 3" or "deploy zephyr." It feels magic. The system will recommend a dataset and fine-tune the model for you. I'm using Monster API, a platform that specializes in making fine-tuning and deploying open-source models easy and fast. Their stack is well-optimized to maximize fine-tuning efficiency using techniques like Q-Lora and vLLM. They are behind the GPT. Here is what you need to do: 1. Create an account at 2. Load the GPT with the link below This is as simple as it gets. When you are done, you can click a button to deploy the model and start using it. I have 10,000 free credits for anyone using the code "SANTIAGO" in the dashboard. You can use these credits to access, fine-tune, and deploy these open-source models. You can also keep up with their latest updates, and get free credits and special offers on their Discord server:

You can now fine-tune Llama 3 without writing a single line of code! We are moving at breakneck speed. I recorded a video to show you how to fine-tune any open-source model in a few minutes. I'm using a GPT capable of taking a problem and turning it into a fine-tuned model that will solve it. You don't have to write any code. You only need to explain to a GPT what problem you want to solve and tell it you want to use Llama 3. For example, "fine-tune Llama 3" or "deploy zephyr." It feels magic. The system will recommend a dataset and fine-tune the model for you. I'm using Monster API, a platform that specializes in making fine-tuning and deploying open-source models easy and fast. Their stack is well-optimized to maximize fine-tuning efficiency using techniques like Q-Lora and vLLM. They are behind the GPT. Here is what you need to do: 1. Create an account at 2. Load the GPT with the link below This is as simple as it gets. When you are done, you can click a button to deploy the model and start using it. I have 10,000 free credits for anyone using the code "SANTIAGO" in the dashboard. You can use these credits to access, fine-tune, and deploy these open-source models. You can also keep up with their latest updates, and get free credits and special offers on their Discord server:

Santiago

324,602 次观看 • 2 年前

Building AI agents and tools is getting ridiculously easy! Here is a pretty impressive FREE and Open-Source AI agent builder that runs on your computer. It's a desktop app you can install on Mac or Windows. Link: • Free • 100% no-code: You can type what you want, and the tool will build everything for you. • You can use local models like DeepSeek or Qwen, or connect to cloud models like GPT-4o, Claude, or Gemini with your API key. • You can turn the tools you build into MCP Servers. I recorded a quick video to show you how easy it is to build something from scratch.

Building AI agents and tools is getting ridiculously easy! Here is a pretty impressive FREE and Open-Source AI agent builder that runs on your computer. It's a desktop app you can install on Mac or Windows. Link: • Free • 100% no-code: You can type what you want, and the tool will build everything for you. • You can use local models like DeepSeek or Qwen, or connect to cloud models like GPT-4o, Claude, or Gemini with your API key. • You can turn the tools you build into MCP Servers. I recorded a quick video to show you how easy it is to build something from scratch.

Santiago

56,815 次观看 • 1 年前

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 次观看 • 7 个月前

AI is incredible at writing code. But that's not enough to create software. You need to set up a dev environment, install packages, configure DB, and, if lucky, deploy. It's time to automate all this. Announcing Replit Agent in early access—available today for subscribers:

AI is incredible at writing code. But that's not enough to create software. You need to set up a dev environment, install packages, configure DB, and, if lucky, deploy. It's time to automate all this. Announcing Replit Agent in early access—available today for subscribers:

Amjad Masad

3,336,055 次观看 • 1 年前

How to Create a Stock Dashboard Using TradingView Charts Without Any Coding Skills Even if you're starting from 0programming knowledge, you'll first need to install PyCharm (an IDE for Python programming). It is free for 30 days. TradingView offers a free widget that can be embedded into your custom webpage. Here's how to do it: 1. Configure Your TradingView Chart: - First, set up the TradingView chart exactly how you want it to appear. - Copy the embed code provided by TradingView for their free widget. 2. Use AI Assistance: - Find an AI assistant like ChatGPT. - Explain what kind of dashboard you want to create. For example: I want to create a stock dashboard for AAPL, TSLA, and NVDA. The left side should display stock tickers with columns for price, price change, 5-day change %, and 20-day change %. Each column should be sortable. When I click on a row, the TradingView chart on the right should automatically switch to display the corresponding stock. Please write this in Python using Flask, in a single file. + "EMBED CODE from Tradingview" This approach allows you to build a functional stock dashboard shown in the video. If you want a better-looking UI and more features, just keep communicating with the AI to gradually improve it.

How to Create a Stock Dashboard Using TradingView Charts Without Any Coding Skills Even if you're starting from 0programming knowledge, you'll first need to install PyCharm (an IDE for Python programming). It is free for 30 days. TradingView offers a free widget that can be embedded into your custom webpage. Here's how to do it: 1. Configure Your TradingView Chart: - First, set up the TradingView chart exactly how you want it to appear. - Copy the embed code provided by TradingView for their free widget. 2. Use AI Assistance: - Find an AI assistant like ChatGPT. - Explain what kind of dashboard you want to create. For example: I want to create a stock dashboard for AAPL, TSLA, and NVDA. The left side should display stock tickers with columns for price, price change, 5-day change %, and 20-day change %. Each column should be sortable. When I click on a row, the TradingView chart on the right should automatically switch to display the corresponding stock. Please write this in Python using Flask, in a single file. + "EMBED CODE from Tradingview" This approach allows you to build a functional stock dashboard shown in the video. If you want a better-looking UI and more features, just keep communicating with the AI to gradually improve it.

Will Hu

26,947 次观看 • 1 年前

NVIDIA just dropped free API keys for every top AI model You don't need your own GPU and you don't pay per token. GLM-5.2, MiniMax, Kimi, DeepSeek, OpenAI, all running on NVIDIA's servers, called through a normal API. Link: How to use one: 1. Create a free NVIDIA account. 2. Pick a Free Endpoint model and open its Build tab. You'll see ready-to-copy code with the base URL 3. Hit Generate API Key, copy it and paste that base URL and key into Claude Code, Cursor, or Cline. Bonus: NVIDIA also dropped 237 official skills that install into Claude Code and Codex in one command. Bookmark this.

NVIDIA just dropped free API keys for every top AI model You don't need your own GPU and you don't pay per token. GLM-5.2, MiniMax, Kimi, DeepSeek, OpenAI, all running on NVIDIA's servers, called through a normal API. Link: How to use one: 1. Create a free NVIDIA account. 2. Pick a Free Endpoint model and open its Build tab. You'll see ready-to-copy code with the base URL 3. Hit Generate API Key, copy it and paste that base URL and key into Claude Code, Cursor, or Cline. Bonus: NVIDIA also dropped 237 official skills that install into Claude Code and Codex in one command. Bookmark this.

Yarchi

59,410 次观看 • 13 天前

I vibe-coded an AI agent for making presentations 🤖🖼️ - accessible to everyone and open-source! You can upload both your context files, as well as a style template (a file that captures the style of the presentation you want to create). Then you launch a prompt and watch the agent one-shot your presentation. After the presentation is generated, you can edit the text inline, chat with the agent to add/modify/delete slides, and export to Powerpoint or PDF. Built with Claude Code, powered by Claude Agent SDK + LlamaParse. Hosted on Vercel/Render. To use it, you do need to specify your LlamaCloud API key and Anthropic API key (see below). App: Repo: Sign up to LlamaCloud:

I vibe-coded an AI agent for making presentations 🤖🖼️ - accessible to everyone and open-source! You can upload both your context files, as well as a style template (a file that captures the style of the presentation you want to create). Then you launch a prompt and watch the agent one-shot your presentation. After the presentation is generated, you can edit the text inline, chat with the agent to add/modify/delete slides, and export to Powerpoint or PDF. Built with Claude Code, powered by Claude Agent SDK + LlamaParse. Hosted on Vercel/Render. To use it, you do need to specify your LlamaCloud API key and Anthropic API key (see below). App: Repo: Sign up to LlamaCloud:

Jerry Liu

21,073 次观看 • 5 个月前

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

The Peel

51,632 次观看 • 4 个月前