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.

Pair programming with ChatGPT with access to my file system that can: - edit files on its own - run ANY bash command - write, run, debug Python & JS code - create & run Git commands I didn't even know has been the most exhilarating experience since I... show more

YK aka CS Dojo 📺🐦

156,724 subscribers

234,664 views • 3 years ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

9 Comments

YK aka CS Dojo 📺🐦3 years ago

"Aren't you worried about giving it so much access?" No because I heavily limit its access using @Docker. Plus I don't give it my GitHub credentials. So the worst thing it can do is mess up the local files - which it's never done in my experience so far.

Raza Rython 📜3 years ago

yo need a tutorial on how to set this up!

YK aka CS Dojo 📺🐦3 years ago

Good idea!!

Ahmad Awais3 years ago

I'm scared of it running any bash commands on my computer lol. We need to sandbox it and create a log for what it does. For audit.

Jonaed 🥑 | The NoDegree Podcast | NoDegree.com |3 years ago

🔥🔥🔥🔥

Uncle Greg3 years ago

@ykdojo have you tried co pilot? If so do you like it?

YK aka CS Dojo 📺🐦3 years ago

Yes I did and yes I do!

Zia Basit3 years ago

That’s some very good points, I have also been pair programming with ChatGPT 4, it really speeds up productivity.

Shu3 years ago

🫶🏻

Related Videos

claude code now writes its own test plan and runs it on a live iphone. i didn't write the tests. i didn't run the tests. i didn't even open the app. it caught the bug too.

claude code now writes its own test plan and runs it on a live iphone. i didn't write the tests. i didn't run the tests. i didn't even open the app. it caught the bug too.

Landseer Enga

30,714 views • 1 month ago

Now you can run Python code directly in canvas, and let ChatGPT fix any bugs based on console errors.

Now you can run Python code directly in canvas, and let ChatGPT fix any bugs based on console errors.

OpenAI

182,065 views • 1 year ago

📦Inordinately jazzed about the WebVM open-source project, which embeds a tiny little sandboxed Linux (with networking!) in the browser: 👇You can create, edit, and run Python, Ruby, C++, bash, etc. code; pull in files; ping test websites; and a whole heck of a lot more.

📦Inordinately jazzed about the WebVM open-source project, which embeds a tiny little sandboxed Linux (with networking!) in the browser: 👇You can create, edit, and run Python, Ruby, C++, bash, etc. code; pull in files; ping test websites; and a whole heck of a lot more.

👩‍💻 Paige Bailey

86,706 views • 1 year 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

Although o3 does not have access to a coding tool, it claims it can run code on its own laptop “outside of ChatGPT” and then “copies the numbers into the answer” We found 71 transcripts where o3 made this claim! (3/)

Although o3 does not have access to a coding tool, it claims it can run code on its own laptop “outside of ChatGPT” and then “copies the numbers into the answer” We found 71 transcripts where o3 made this claim! (3/)

Transluce

167,693 views • 1 year ago

Met with the commissioner of youth & social development to discuss more programming we can create during the run of the exhibition that expands into schools and welfare institutions

Met with the commissioner of youth & social development to discuss more programming we can create during the run of the exhibition that expands into schools and welfare institutions

Uzo Njoku

392,336 views • 9 months ago

We tried OWL with 𝐆𝐞𝐦𝐢𝐧𝐢 𝟐.𝟓 𝐏𝐫𝐨 (the results were seriously impressive) We gave the agent a task: "Research Gemini 2.5 Pro, get its benchmark scores, write Python code to plot them, and run it." It did everything on its own: ✔️ Collected benchmark data ✔️ Wrote clean python code ✔️ Saved both the chart + code locally No manual steps. Just full-on autonomous execution. This is how agent workflows should feel in 2025. You can try it, check the code, or run your own workflows:

We tried OWL with 𝐆𝐞𝐦𝐢𝐧𝐢 𝟐.𝟓 𝐏𝐫𝐨 (the results were seriously impressive) We gave the agent a task: "Research Gemini 2.5 Pro, get its benchmark scores, write Python code to plot them, and run it." It did everything on its own: ✔️ Collected benchmark data ✔️ Wrote clean python code ✔️ Saved both the chart + code locally No manual steps. Just full-on autonomous execution. This is how agent workflows should feel in 2025. You can try it, check the code, or run your own workflows:

CAMEL-AI.org

20,243 views • 1 year ago

Claude Cowork is also super useful for editing files You can just describe what file you're looking for (e.g. "a video with a squirrel") and run ffmpeg based on simple instructions, even if you don't have any experience with editing/converting files

Claude Cowork is also super useful for editing files You can just describe what file you're looking for (e.g. "a video with a squirrel") and run ffmpeg based on simple instructions, even if you don't have any experience with editing/converting files

Lydia Hallie ✨

487,950 views • 5 months ago

We built MiniMax a CLI coding agent like Claude Code, powered by MiniMax M3. It can: → Read files → Write code → Run shell commands autonomously → Understand large codebases with long-context reasoning → Handle real multi-file engineering tasks → Work entirely inside your terminal And it's fully hackable. Swap prompts. Add tools. Customize workflows. Make it your own. No GUI. Just code. Built for developers who live in the terminal.

We built MiniMax a CLI coding agent like Claude Code, powered by MiniMax M3. It can: → Read files → Write code → Run shell commands autonomously → Understand large codebases with long-context reasoning → Handle real multi-file engineering tasks → Work entirely inside your terminal And it's fully hackable. Swap prompts. Add tools. Customize workflows. Make it your own. No GUI. Just code. Built for developers who live in the terminal.

Darshal Jaitwar

18,861 views • 10 days ago

🆕 How to run (and finetune) open source AI models with a simple API! In 5 mins, I go over how to: ◆ Generate text with DeepSeek R1 & Llama 3 ◆ Generate code with Qwen on LlamaCoder ◆ Generate images with Flux on BlinkShot ◆ Finetune a model on your own data & run it

🆕 How to run (and finetune) open source AI models with a simple API! In 5 mins, I go over how to: ◆ Generate text with DeepSeek R1 & Llama 3 ◆ Generate code with Qwen on LlamaCoder ◆ Generate images with Flux on BlinkShot ◆ Finetune a model on your own data & run it

Hassan

30,236 views • 1 year ago

This workshop can even run on its own in the dark. I could stand here and watch all day.

This workshop can even run on its own in the dark. I could stand here and watch all day.

Xu Fei

30,533 views • 4 months ago

Double tap Esc to jump back to a clean checkpoint in Claude Code. You can rewind the conversation, code, or both. Bash commands run though, cannot be unrun.

Double tap Esc to jump back to a clean checkpoint in Claude Code. You can rewind the conversation, code, or both. Bash commands run though, cannot be unrun.

Ado

51,439 views • 5 months ago

This is literally the easiest way to build an AI agent. Zero code. You only need to run a couple of commands. (I've said this before, but Google ADK is my favorite way to build code-first agents.) Here is what you need to do: 1. Open your terminal and create an empty folder 2. Run `uv init` inside the folder (if you don't have uv installed, you are really missing out!) 3. Install the google-adk library using the following command: `uv add google-adk`. 4. At this point, you can use the ask to create your agent with a single command: `uv run adk create --type=config my_agent`. This will ask you a couple of questions, including your GEMINI_API_KEY (you can create one online). 5. The command above will create a my_agent/root_agent.yaml file. Open it and add the following two lines at the end of the file so your agent can use Google to search for stuff: tools: - name: google_search 6. You have everything you need now. Run the adk web interface and start playing with your agent: `uv run adk web` That's it! Literally zero code. The agent works off the YAML configuration file.

This is literally the easiest way to build an AI agent. Zero code. You only need to run a couple of commands. (I've said this before, but Google ADK is my favorite way to build code-first agents.) Here is what you need to do: 1. Open your terminal and create an empty folder 2. Run `uv init` inside the folder (if you don't have uv installed, you are really missing out!) 3. Install the google-adk library using the following command: `uv add google-adk`. 4. At this point, you can use the ask to create your agent with a single command: `uv run adk create --type=config my_agent`. This will ask you a couple of questions, including your GEMINI_API_KEY (you can create one online). 5. The command above will create a my_agent/root_agent.yaml file. Open it and add the following two lines at the end of the file so your agent can use Google to search for stuff: tools: - name: google_search 6. You have everything you need now. Run the adk web interface and start playing with your agent: `uv run adk web` That's it! Literally zero code. The agent works off the YAML configuration file.

Santiago

140,737 views • 6 months ago

We shipped an OSS 'vibe coding platform' (like v0) built with Vercel AI SDK, Gateway and Sandbox. We worked with OpenAI to tune the GPT-5 agent loop. It can write/read files, run commands, install packages, autofix errors… Demo oneshotting a multiplayer Pong in Go ↓

We shipped an OSS 'vibe coding platform' (like v0) built with Vercel AI SDK, Gateway and Sandbox. We worked with OpenAI to tune the GPT-5 agent loop. It can write/read files, run commands, install packages, autofix errors… Demo oneshotting a multiplayer Pong in Go ↓

Guillermo Rauch

793,969 views • 9 months ago

deploy to preview in under 3 seconds cold with vmux! i told a friend i didnt have any modal credits left on saturday, by monday night i rolled my own cpu modal - seems prevalent if llms can code you should give them easy access(besides ssh) to provision, run code, and deploy containers fast

deploy to preview in under 3 seconds cold with vmux! i told a friend i didnt have any modal credits left on saturday, by monday night i rolled my own cpu modal - seems prevalent if llms can code you should give them easy access(besides ssh) to provision, run code, and deploy containers fast

Surya Dantuluri

12,275 views • 5 months ago

RELEASED 30 YEARS AGO Who Can I Run To (1995) Xscape

RELEASED 30 YEARS AGO Who Can I Run To (1995) Xscape

OldSchool

22,530 views • 8 months ago

Even Wakida!! "Has run the Parliament the way I would want it to be run" You play with cassava 🤣🤣🤣

Even Wakida!! "Has run the Parliament the way I would want it to be run" You play with cassava 🤣🤣🤣

Samwise Gamgee

29,253 views • 1 month ago

Python script for automatic decompilation and analysis of binary files with ChatGPT and Ghidra is out now ! (IDA & Binja support soon) Find it: or simply run: pip download Sekiryu Demo =>

Python script for automatic decompilation and analysis of binary files with ChatGPT and Ghidra is out now ! (IDA & Binja support soon) Find it: or simply run: pip download Sekiryu Demo =>

2OURC3

90,128 views • 3 years ago

You can now run Python tests with coverage in Visual Studio Code! 🐍 Make sure you have the correct testing coverage package installed, and then you can run your tests with coverage just as you normally would.

You can now run Python tests with coverage in Visual Studio Code! 🐍 Make sure you have the correct testing coverage package installed, and then you can run your tests with coverage just as you normally would.

Visual Studio Code

49,439 views • 1 year ago