Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Just added DeepSeek-Engineer on Github 🐋 Wanted to test the API, so I created a quick coding assistant that can read, create, and diff edit files using structured outputs. It's very simple and minimal, and a good foundation if you want to learn how coding assistants work!

Pietro Schirano

102,476 subscribers

73,503 views • 1 year ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

Pietro Schirano1 year ago

Repo here:

anarki🌟1 year ago

@arXivBangers on trust. thank for your service 🫡

Ivan Fioravanti ᯅ1 year ago

Thanks Pietro! Simple, but powerful! 🙏

Sahil Bansal1 year ago

This looks really fun, will check it on the weekend!

FRobertsV1 year ago

Amazing man

FutureAI1 year ago

Interesting! Thank you for sharing!

93&:’ap&31 year ago

Is it better than Claude engineer?

Pietro Schirano1 year ago

No

Vlad1 year ago

what is your take on it Pietro, I have seen some posts claiming is better than Sonnet 3.5, do you see that being the case?

Pietro Schirano1 year ago

Definitely a great model, but I would not go that far! Still trying to figure out what coding languages it’s more proficient in. Not that great in JS.

Related Videos

Introducing Claude Engineer 🧑‍💻 My new repo that allows Sonnet 3.5 to create, read and edit coding files and folders via a simple chat. Think of it as a streamlined local “artifacts” with the added advantage of creating entire projects directly. It even supports online search!

Introducing Claude Engineer 🧑‍💻 My new repo that allows Sonnet 3.5 to create, read and edit coding files and folders via a simple chat. Think of it as a streamlined local “artifacts” with the added advantage of creating entire projects directly. It even supports online search!

Pietro Schirano

250,606 views • 1 year ago

New Short Course: Getting Structured LLM Output! Learn how to get structured outputs from your LLM applications in this course, built in partnership with .txt, and taught by Will Kurt, a Founding Engineer, and , Developer Relations Engineer. It's challenging for software to automatically parse through an LLM's freeform text outputs. Structured outputs—like JSON—solve this by converting natural language into consistent, clear, data that a machine can read and process. This course teaches you how to generate structured outputs while building several use cases, including a social media analysis agent. You’ll learn about structured outputs and efficient ways to generate outputs in your defined schema or format. You’ll begin by using structured output APIs, then use re-prompting libraries like “instructor” to generate structured output. Finally, you’ll learn how constrained decoding works; this is a very clever technique in which constraints are applied on each subsequent token generated, blocking any tokens that don’t fit your defined schema. In detail, you’ll: - Learn why structured outputs are important, how they allow for scalable software development, and the different approaches to generate them, including vendor-provided APIs, re-prompting libraries, and structured generation. - Build a simple social media agent using OpenAI’s structured output API, learn how to define a model's desired structured output using Pydantic, and perform basic programming with your outputs, such as importing structured data into a data frame using pandas. - Learn how to use the open-source library "instructor," which checks the structured output of the model and re-prompts the model until it validates the desired output, and explore the limitations of this approach. - Understand how structured generation by the “outlines” library works by modifying LLM logits, on a per-generated-token basis based on the desired format, to give a particular output structure. - Learn how regular expressions, which outlines works with, are represented as finite-state machines, and how they can be used to develop a range of structured outputs beyond JSON. By the end of this course, you’ll have broadened your knowledge of the approaches you can use to get structured outputs from your LLM applications. Please sign up here:

New Short Course: Getting Structured LLM Output! Learn how to get structured outputs from your LLM applications in this course, built in partnership with .txt, and taught by Will Kurt, a Founding Engineer, and , Developer Relations Engineer. It's challenging for software to automatically parse through an LLM's freeform text outputs. Structured outputs—like JSON—solve this by converting natural language into consistent, clear, data that a machine can read and process. This course teaches you how to generate structured outputs while building several use cases, including a social media analysis agent. You’ll learn about structured outputs and efficient ways to generate outputs in your defined schema or format. You’ll begin by using structured output APIs, then use re-prompting libraries like “instructor” to generate structured output. Finally, you’ll learn how constrained decoding works; this is a very clever technique in which constraints are applied on each subsequent token generated, blocking any tokens that don’t fit your defined schema. In detail, you’ll: - Learn why structured outputs are important, how they allow for scalable software development, and the different approaches to generate them, including vendor-provided APIs, re-prompting libraries, and structured generation. - Build a simple social media agent using OpenAI’s structured output API, learn how to define a model's desired structured output using Pydantic, and perform basic programming with your outputs, such as importing structured data into a data frame using pandas. - Learn how to use the open-source library "instructor," which checks the structured output of the model and re-prompts the model until it validates the desired output, and explore the limitations of this approach. - Understand how structured generation by the “outlines” library works by modifying LLM logits, on a per-generated-token basis based on the desired format, to give a particular output structure. - Learn how regular expressions, which outlines works with, are represented as finite-state machines, and how they can be used to develop a range of structured outputs beyond JSON. By the end of this course, you’ll have broadened your knowledge of the approaches you can use to get structured outputs from your LLM applications. Please sign up here:

Andrew Ng

89,578 views • 1 year ago

GitHub + Cursor is just INSANE GitHub has 28 million open-source projects that anyone can fork and build a new product So I built a new product: Repo to Docs The Agent will scan entire GitHub repo, analyze all files and create a knowledge base (docs) for AI coding tools: ↓

GitHub + Cursor is just INSANE GitHub has 28 million open-source projects that anyone can fork and build a new product So I built a new product: Repo to Docs The Agent will scan entire GitHub repo, analyze all files and create a knowledge base (docs) for AI coding tools: ↓

CJ Zafir

123,037 views • 11 months ago

o1-engineer is here! 🚀 A coding assistant built from the ground up to leverage o1 reasoning capabilities. It can create and edit multiple files or entire folders, plan complex projects, execute them, and write code reviews. All from your terminal 👨‍💻

o1-engineer is here! 🚀 A coding assistant built from the ground up to leverage o1 reasoning capabilities. It can create and edit multiple files or entire folders, plan complex projects, execute them, and write code reviews. All from your terminal 👨‍💻

Pietro Schirano

309,202 views • 1 year ago

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 views • 3 months ago

Introducing Omni Engineer 🚀 An AI coding framework built for control and effectiveness. Create and edit multiple files in REAL time Web search via DuckDuckGo Save and resume conversations Image support Use any model you want via OpenRouter Here's a quick demo 👨‍💻

Introducing Omni Engineer 🚀 An AI coding framework built for control and effectiveness. Create and edit multiple files in REAL time Web search via DuckDuckGo Save and resume conversations Image support Use any model you want via OpenRouter Here's a quick demo 👨‍💻

Pietro Schirano

53,787 views • 1 year ago

Introducing Copilot Chronicle! This new feature in GitHub Copilot indexes all your messages and turns locally in SQLite so you can talk to your coding history and learn how you work *and* more importantly, how you can improve! Live demo ->

Introducing Copilot Chronicle! This new feature in GitHub Copilot indexes all your messages and turns locally in SQLite so you can talk to your coding history and learn how you work and more importantly, how you can improve! Live demo ->

Scott Hanselman 🌮

61,427 views • 3 months ago

Claude can now create and edit files from spreadsheets and documents to PDFs and slide decks. What coding agents have been doing for software engineering is soon expanding to all knowledge work - this is just the beginning.

Claude can now create and edit files from spreadsheets and documents to PDFs and slide decks. What coding agents have been doing for software engineering is soon expanding to all knowledge work - this is just the beginning.

Alex Albert

347,248 views • 9 months ago

Today, OpenAI announced the GPT4 Vision API. So I created a tool that uses GPT4-Vision + Facial Recognition to create real-time descriptions of the feed from my webcam If you want to see how I did it, leave a comment below and I'll send you the github repo 👇🏻

Today, OpenAI announced the GPT4 Vision API. So I created a tool that uses GPT4-Vision + Facial Recognition to create real-time descriptions of the feed from my webcam If you want to see how I did it, leave a comment below and I'll send you the github repo 👇🏻

Tyler Germain

82,370 views • 2 years ago

So a new (very good) agentic coding tool has just been released Qoder lets you vibe code apps by describing what you want or assigning quests. - Plans the project structure - Generates the code/files - Runs terminal commands - Launch the app to test it Quick steps to use it:

So a new (very good) agentic coding tool has just been released Qoder lets you vibe code apps by describing what you want or assigning quests. - Plans the project structure - Generates the code/files - Runs terminal commands - Launch the app to test it Quick steps to use it:

Paul Couvert

121,198 views • 9 months ago

Tutorial: How to make a creative coding animation with Claude 2 and OpenProcessing Claude 2 is one of my favorite coding tools. Here's a demo how you can learn programming and write a simple animation with it in minutes. You can run the code at OpenProcessing. Links in comment

Tutorial: How to make a creative coding animation with Claude 2 and OpenProcessing Claude 2 is one of my favorite coding tools. Here's a demo how you can learn programming and write a simple animation with it in minutes. You can run the code at OpenProcessing. Links in comment

Kris Kashtanova

18,369 views • 2 years ago

Heard of Deepseek and want to try it out? But afraid of giving your data to China? Made a quick vid on how you can run Deepseek locally on your computer so you can keepo all your data using fullmoon.

Heard of Deepseek and want to try it out? But afraid of giving your data to China? Made a quick vid on how you can run Deepseek locally on your computer so you can keepo all your data using fullmoon.

Alex Hugh Sam

13,511 views • 1 year ago

Today Paul Jankura is releasing MCP, a framework that allows Claude to run servers, giving it superpowers and effectively turning the Claude app into an API. We created some server that I think you'll love! FileSystem: Claude can create, read, and edit files and folders locally.

Today Paul Jankura is releasing MCP, a framework that allows Claude to run servers, giving it superpowers and effectively turning the Claude app into an API. We created some server that I think you'll love! FileSystem: Claude can create, read, and edit files and folders locally.

Pietro Schirano

550,681 views • 1 year ago

I LOVE SOULSEEK. So I built a modern client and if you love soulseek and want to use it I'd love to share it with you. You can watch this video to get a quick feel but it's designed to be lightweight/simple and easy to browse users collections. That way you can find good new music and then buy that music and more on Bandcamp. If you'd like to use it just reply here and I'll dm you a link.

I LOVE SOULSEEK. So I built a modern client and if you love soulseek and want to use it I'd love to share it with you. You can watch this video to get a quick feel but it's designed to be lightweight/simple and easy to browse users collections. That way you can find good new music and then buy that music and more on Bandcamp. If you'd like to use it just reply here and I'll dm you a link.

Trev🙃r is hiring DM me!

216,058 views • 4 months ago

Heard about the new GitHub Copilot coding agent? 👀 Here's how it can free you up to focus on more creative and high-impact tasks. ⬇️

Heard about the new GitHub Copilot coding agent? 👀 Here's how it can free you up to focus on more creative and high-impact tasks. ⬇️

GitHub

32,121 views • 1 year ago

VIBE CODING TUTORIAL: Creating a Viral Meme Mobile App Without Any Coding in 20 minutes! You can now build multi-step AI workflows on a drag and drop platform, and then connect that workflow to your vibe coded mobile app, in a single cursor prompt. This only scratches the surface on the different workflows you can create like this. IN THIS VIDEO 00:00 Intro 00:36 Overview: MultiStep AI Backend on GLIF 01:33 Using Glif as an API 03:49 The backend for our app 04:36 Structured Outputs (Important for Vibe Coding, skip if you know what these are) 06:40 Image Workflow for the meme 08:34 Let's Protototype on 11:09 Setting this up with Cursor 18:40 Testing with

VIBE CODING TUTORIAL: Creating a Viral Meme Mobile App Without Any Coding in 20 minutes! You can now build multi-step AI workflows on a drag and drop platform, and then connect that workflow to your vibe coded mobile app, in a single cursor prompt. This only scratches the surface on the different workflows you can create like this. IN THIS VIDEO 00:00 Intro 00:36 Overview: MultiStep AI Backend on GLIF 01:33 Using Glif as an API 03:49 The backend for our app 04:36 Structured Outputs (Important for Vibe Coding, skip if you know what these are) 06:40 Image Workflow for the meme 08:34 Let's Protototype on 11:09 Setting this up with Cursor 18:40 Testing with

Riley Brown

57,878 views • 1 year ago

been using a stealth model all day in opencode and it's working real well now you can use it too - it's called Sonic, it's made for coding and it's free for you to use so the team behind it can test it update to latest opencode and it should pop up right there

been using a stealth model all day in opencode and it's working real well now you can use it too - it's called Sonic, it's made for coding and it's free for you to use so the team behind it can test it update to latest opencode and it should pop up right there

dax

122,609 views • 9 months ago

GPT-4 Mini Game - Ghoul City - Version 1 🎮🤖 Ghoul City is a simple side-scrolling video game that I created entirely with GPT-4 and Midjourney. To create Ghoul City, I pretended to not have any coding background and instead let AI handle all of the coding and debugging. 🧵👇

GPT-4 Mini Game - Ghoul City - Version 1 🎮🤖 Ghoul City is a simple side-scrolling video game that I created entirely with GPT-4 and Midjourney. To create Ghoul City, I pretended to not have any coding background and instead let AI handle all of the coding and debugging. 🧵👇

Allen T.

282,905 views • 3 years ago

🚨 ANNOUNCING THE WORLD'S FIRST VIBE CODING AGENT FOR APIs. Vibe coders just became LEGIT backend engineers. With ONE PROMPT, you can create an entire microservice and host it on Abacus AI Deep Agent. Vibe coders can now go toe-to-toe with backend engineers and create an API, a Telegram bot, or any AI service. The AI takes care of everything. - creating an API spec - implementing it and hosting it - using a back-end database for tracking - giving you a test bed - providing you with a ready-to-use endpoint! Backend engineers are expensive; now you can start vibe-coding their projects in English.

🚨 ANNOUNCING THE WORLD'S FIRST VIBE CODING AGENT FOR APIs. Vibe coders just became LEGIT backend engineers. With ONE PROMPT, you can create an entire microservice and host it on Abacus AI Deep Agent. Vibe coders can now go toe-to-toe with backend engineers and create an API, a Telegram bot, or any AI service. The AI takes care of everything. - creating an API spec - implementing it and hosting it - using a back-end database for tracking - giving you a test bed - providing you with a ready-to-use endpoint! Backend engineers are expensive; now you can start vibe-coding their projects in English.

Bindu Reddy

11,800 views • 6 months ago