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.

Trying to understand a codebase? This technique BLEW MY MIND. Reto Meier told me to try uploading a code repo (after flipping all files to txt) and asking Google AI NotebookLM ( to make a podcast from just the code. It did, and it was crazmazing.

Richard Seroter

34,774 subscribers

20,852 views • 1 year ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 Comments

Ozgur Ozer1 year ago

@retomeier @GoogleAI I tried it just giving a link to Cursor and the result is very impressive

InverseAGI1 year ago

@retomeier @GoogleAI Just tried this, so cool!

Raiza Martin1 year ago

@retomeier @GoogleAI oh my

AK Kulkarni1 year ago

@retomeier @GoogleAI @tokumin @simpsoka cool use case!

Daniel Bartley1 year ago

@retomeier @GoogleAI Is the video supposed to be black screen?

Richard Seroter1 year ago

@retomeier @GoogleAI Just audio of the generated "podcast".

Gene Kim1 year ago

@retomeier @GoogleAI 🤯🤯🤯

2024=2023+1 (e/acc)1 year ago

@retomeier @GoogleAI I just upload my resume and wow!!! I am impressed about myself. 😀

Tanel Poder 🇺🇦1 year ago

@retomeier @GoogleAI Next step, rename a binary to .txt and upload - see what are the disassembly/decompilation capabilities of this thing? 😅

Isaiah Stone1 year ago

@retomeier @GoogleAI Curious how it'll do if you just add the link to the repo

Related Videos

Google NotebookLM is absolutely insane, easily the best AI product out there, and it is free to use. The new Mindmap feature makes learning so easy. You can use it to understand your codebase. Just convert your codebase to a single file and try it out.

Google NotebookLM is absolutely insane, easily the best AI product out there, and it is free to use. The new Mindmap feature makes learning so easy. You can use it to understand your codebase. Just convert your codebase to a single file and try it out.

AshutoshShrivastava

240,949 views • 1 year ago

The easiest way to build an MCP Server using Google DeepMind Gemini 2.5 Pro and get started! 1. Use Gitingest to get all the code and docs from the FastMCP repo 2. Download the code into a txt file 3. Go to AI Studio, upload the file, define what kind of MCP Server you want to build 4. Gemini 2.5 Pro builds it for you.

The easiest way to build an MCP Server using Google DeepMind Gemini 2.5 Pro and get started! 1. Use Gitingest to get all the code and docs from the FastMCP repo 2. Download the code into a txt file 3. Go to AI Studio, upload the file, define what kind of MCP Server you want to build 4. Gemini 2.5 Pro builds it for you.

Philipp Schmid

75,968 views • 1 year ago

This is one of the coolest open-source AI agent projects I've seen in a while: 'Understand Anything' It's a plugin for Claude Code, Codex, OpenCode etc. that analyzes your codebase and turns it into a knowledge base that you can interact with. It explains the codebase to you, rather than showing you the structure. It seems like it's designed for code but I opened my Obsidian vault of podcast highlights in Claude Code, then ran /understand. The result is a knowledge graph that I can search of highlights from 888 podcast episodes and 144K lines of markdown text.

This is one of the coolest open-source AI agent projects I've seen in a while: 'Understand Anything' It's a plugin for Claude Code, Codex, OpenCode etc. that analyzes your codebase and turns it into a knowledge base that you can interact with. It explains the codebase to you, rather than showing you the structure. It seems like it's designed for code but I opened my Obsidian vault of podcast highlights in Claude Code, then ran /understand. The result is a knowledge graph that I can search of highlights from 888 podcast episodes and 144K lines of markdown text.

Dan McAteer

154,615 views • 3 days ago

The new Screenshot to Code from Vercel v0 is insane. I just took a screenshot of a pricing table and it was converted into code using AI in seconds! It even outputs the code and allows you to modify any specific parts.

The new Screenshot to Code from Vercel v0 is insane. I just took a screenshot of a pricing table and it was converted into code using AI in seconds! It even outputs the code and allows you to modify any specific parts.

Alvaro Cintas

377,994 views • 2 years ago

Engineering is going to change forever. I just fed GPT-4-32K nearly all of Pinecone's docs, and the results blew my mind! It helped me make architecture decisions, and it then wrote my code for me. The future of AI-assisted development is here, and it's beyond impressive.

Engineering is going to change forever. I just fed GPT-4-32K nearly all of Pinecone's docs, and the results blew my mind! It helped me make architecture decisions, and it then wrote my code for me. The future of AI-assisted development is here, and it's beyond impressive.

Matt Shumer

503,045 views • 3 years ago

I tested a new coding assistant on 34,568 lines of code. (Cursor could not achieve what this tool did.) AI models are improving every day: - Faster inference - Longer context lengths But are AI coding assistants advancing at the same rate? Can they truly understand your entire project? I tested Augment Code on my ai-engineering repo with ~35k lines of code. Augment Code is a powerful AI Assistant built for developers working with large, evolving codebases—needing an assistant that understands the full context of their projects. In the video demo below, I asked it to: - Merge two projects. - Answer a global context question. Here’s what happened: - It understood dependencies across both projects. - It merged them intelligently—without breaking anything. - It even created a README file for the merged project. - It answered my global query instantly, pulling from the full codebase. This is the difference between AI autocomplete and an AI engineer that truly understands your repo. Augment Code is powerful because it indexes your entire repo upfront. This way, it can answer questions instantly, no matter how large your project is. Lastly, Augment Code is fully compatible with VSCode, JetBrains, Vim, Slack, and more. Try them now, I have shared a link in the next tweet! Thanks to Augment Code for showing me their powerful AI coding assistant and working with me on this post.

I tested a new coding assistant on 34,568 lines of code. (Cursor could not achieve what this tool did.) AI models are improving every day: - Faster inference - Longer context lengths But are AI coding assistants advancing at the same rate? Can they truly understand your entire project? I tested Augment Code on my ai-engineering repo with ~35k lines of code. Augment Code is a powerful AI Assistant built for developers working with large, evolving codebases—needing an assistant that understands the full context of their projects. In the video demo below, I asked it to: - Merge two projects. - Answer a global context question. Here’s what happened: - It understood dependencies across both projects. - It merged them intelligently—without breaking anything. - It even created a README file for the merged project. - It answered my global query instantly, pulling from the full codebase. This is the difference between AI autocomplete and an AI engineer that truly understands your repo. Augment Code is powerful because it indexes your entire repo upfront. This way, it can answer questions instantly, no matter how large your project is. Lastly, Augment Code is fully compatible with VSCode, JetBrains, Vim, Slack, and more. Try them now, I have shared a link in the next tweet! Thanks to Augment Code for showing me their powerful AI coding assistant and working with me on this post.

Akshay 🚀

30,799 views • 1 year ago

Inspired by Andrej Karpathy & Farza 🇵🇰🇺🇸, introducing LLMwiki.. fully open source to help build yours. Inputs were tweets, bookmarks, iMessage/WhatsApp, and all my writing. Spent a bunch of time refining the frontend design to make it look great. Even though every single article here was written by AI, it was able to make surprisingly sharp connections. To make yours, just give the repo to Claude Code and it'll guide you!

Inspired by Andrej Karpathy & Farza 🇵🇰🇺🇸, introducing LLMwiki.. fully open source to help build yours. Inputs were tweets, bookmarks, iMessage/WhatsApp, and all my writing. Spent a bunch of time refining the frontend design to make it look great. Even though every single article here was written by AI, it was able to make surprisingly sharp connections. To make yours, just give the repo to Claude Code and it'll guide you!

Nikunj Kothari

32,388 views • 2 months ago

Google Gemini 2.0 realtime AI is insane. Watch me turn it into a live code tutor just by sharing my screen and talking to it. We’re living in future. I’m speechless.

Google Gemini 2.0 realtime AI is insane. Watch me turn it into a live code tutor just by sharing my screen and talking to it. We’re living in future. I’m speechless.

Mckay Wrigley

624,751 views • 1 year ago

For those of you tired of yet another AI-based IDE: Check out Traycer. It's a Visual Studio Code extension (free forever for anyone working on open-source repositories), and it does something different from everyone else. You write a high-level prompt outlining the changes you want to make to your codebase, and the extension generates a plan for you before you touch the code. (It reminds me of GitHub Copilot Workspaces.) You can review the plan, understand exactly the changes the extension will make to your code, and make any modifications. When you are ready, you execute the plan, and Traycer stages all of the changes so you have a new opportunity to review everything. Only then does Traycer apply the changes. This is ideal for large codebases where you'd rather study the changes the AI plans to make before they make it into your code. Look at the video I recorded to see how it works. Thanks to the Traycer team for collaborating with me on this post!

For those of you tired of yet another AI-based IDE: Check out Traycer. It's a Visual Studio Code extension (free forever for anyone working on open-source repositories), and it does something different from everyone else. You write a high-level prompt outlining the changes you want to make to your codebase, and the extension generates a plan for you before you touch the code. (It reminds me of GitHub Copilot Workspaces.) You can review the plan, understand exactly the changes the extension will make to your code, and make any modifications. When you are ready, you execute the plan, and Traycer stages all of the changes so you have a new opportunity to review everything. Only then does Traycer apply the changes. This is ideal for large codebases where you'd rather study the changes the AI plans to make before they make it into your code. Look at the video I recorded to see how it works. Thanks to the Traycer team for collaborating with me on this post!

Santiago

83,805 views • 1 year ago

This is CRAZY. You have to watch the video below. I uploaded all of my weekly newsletters to Google's notebook LM. I clicked a button and it generated a 22 minute audio podcast about all my newsletters. This was completely AI generated. (AI = Artificial Intelligence) It took a couple minutes to read 60+ pages of my newsletters and generate this podcast-style conversation. Absolutely mind blowing.

This is CRAZY. You have to watch the video below. I uploaded all of my weekly newsletters to Google's notebook LM. I clicked a button and it generated a 22 minute audio podcast about all my newsletters. This was completely AI generated. (AI = Artificial Intelligence) It took a couple minutes to read 60+ pages of my newsletters and generate this podcast-style conversation. Absolutely mind blowing.

Lou Stagner (Golf Stat Pro)

80,650 views • 1 year ago

What if writing code was as simple as talking to your device? Watch my GPT-4 voice assistant: - take in a complex coding task - write the code - create a PR on my GitHub repo All I had to do was tell it what to do. This is the future of software.

What if writing code was as simple as talking to your device? Watch my GPT-4 voice assistant: - take in a complex coding task - write the code - create a PR on my GitHub repo All I had to do was tell it what to do. This is the future of software.

Mckay Wrigley

1,347,716 views • 3 years ago

Google Chief Scientist, Jeff Dean "AI now generates 25% of Google's integrated code" Google has already trained a Gemini model on its internal codebase to help developers this doesn’t cover everything, but it improves AI-assisted coding by integrating code into its parameters

Google Chief Scientist, Jeff Dean "AI now generates 25% of Google's integrated code" Google has already trained a Gemini model on its internal codebase to help developers this doesn’t cover everything, but it improves AI-assisted coding by integrating code into its parameters

Haider.

173,475 views • 1 year ago

> downloaded Claude Code > thought it was just another AI chatbot > opened it up > found a chat bar > typed a prompt > nothing happened to my files > realized the difference > browser AI waits for you to bring your files > Claude Code goes into your folder > all 45 PDFs > all the transcripts > all the messy Excel sheets > reads them all > remembers them session after session > you never re-explain your project again > so before your next literature review, do this: > create a folder with all your papers > open it in Claude Code > write a CLAUDEmd with your role, field, and writing style > ask it to screen every PDF using your inclusion/exclusion criteria > let it rename, extract, and summarize while you think > the AI didn't replace your scholarship > it eliminated the 6 hours of grunt work before it starts

> downloaded Claude Code > thought it was just another AI chatbot > opened it up > found a chat bar > typed a prompt > nothing happened to my files > realized the difference > browser AI waits for you to bring your files > Claude Code goes into your folder > all 45 PDFs > all the transcripts > all the messy Excel sheets > reads them all > remembers them session after session > you never re-explain your project again > so before your next literature review, do this: > create a folder with all your papers > open it in Claude Code > write a CLAUDEmd with your role, field, and writing style > ask it to screen every PDF using your inclusion/exclusion criteria > let it rename, extract, and summarize while you think > the AI didn't replace your scholarship > it eliminated the 6 hours of grunt work before it starts

Blum

13,520 views • 1 month ago

I hooked up an iOS shortcut to GPT-4 and GitHub. Here’s how it works: - identifies the repo - identifies the target files - writes the code for me - creates a branch - commits changes Now I can code right on my Apple Watch with nothing but my voice!

I hooked up an iOS shortcut to GPT-4 and GitHub. Here’s how it works: - identifies the repo - identifies the target files - writes the code for me - creates a branch - commits changes Now I can code right on my Apple Watch with nothing but my voice!

Mckay Wrigley

1,283,858 views • 3 years ago

GPT Engineer github: Specify what you want it to build, the AI asks for clarification, and then builds it. GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt.

GPT Engineer github: Specify what you want it to build, the AI asks for clarification, and then builds it. GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt.

AK

349,142 views • 3 years ago

I gave a photo a voice and now it talks better than me Lip sync, emotions, gestures all from one pic Used Gaga AI and it legit blew my mind Try it out for yourself: #GagaAI

I gave a photo a voice and now it talks better than me Lip sync, emotions, gestures all from one pic Used Gaga AI and it legit blew my mind Try it out for yourself: #GagaAI

SARAH

121,915 views • 10 months ago

Just built a Perplexity clone using Gemini 2.0 + Grounding, and the wildest part? Replit ⠕'s Agent wrote ALL the code in 2 hours! Search anything, get sources, ask follow-ups. Google has all the pieces to make AI search incredible. Hope they productize it soon! Demo + code 👇

Just built a Perplexity clone using Gemini 2.0 + Grounding, and the wildest part? Replit ⠕'s Agent wrote ALL the code in 2 hours! Search anything, get sources, ask follow-ups. Google has all the pieces to make AI search incredible. Hope they productize it soon! Demo + code 👇

Ammaar Reshi

533,735 views • 1 year ago

Whoa, I just used Google's Bard AI to recreate a basic timer app for iPhone in under 4 minutes... just from a screenshot! 🤯 Did not give it hints as to what the app did, and it provided all of the code—it made some mistakes but nothing it couldn't fix! Here's the full process

Whoa, I just used Google's Bard AI to recreate a basic timer app for iPhone in under 4 minutes... just from a screenshot! 🤯 Did not give it hints as to what the app did, and it provided all of the code—it made some mistakes but nothing it couldn't fix! Here's the full process

Ammaar Reshi

508,457 views • 2 years ago

Try out Gemini Code: a coding assistant in your terminal powered by Gemini 2.5 Pro. 💜 💜 Release Notes: → It's easy to get started, just run `pip install gemini-code` in a virtual environment, and then run `gemini` to initialize it. It requires your own API key, so don't forget to get one from → I built this because I love Claude Code and wanted a similar experience -- I like that I can just use my own API key and Gemini is generally way cheaper as well. → Found a bug? Feel free to fork the code and fix it (lol)! If you want to try to improve it, please do so - repo is public! → Reminder and a disclaimer that I don't work at Google and this is not an official Google project - just a weekend side hack → It is highly likely you'll get throttled by rate limits - I put as much info as I can in the guide so you know what behavior to expect when that happens. You can also set which default model to use if you want to switch to 1.5 Pro.

Try out Gemini Code: a coding assistant in your terminal powered by Gemini 2.5 Pro. 💜 💜 Release Notes: → It's easy to get started, just run `pip install gemini-code` in a virtual environment, and then run `gemini` to initialize it. It requires your own API key, so don't forget to get one from → I built this because I love Claude Code and wanted a similar experience -- I like that I can just use my own API key and Gemini is generally way cheaper as well. → Found a bug? Feel free to fork the code and fix it (lol)! If you want to try to improve it, please do so - repo is public! → Reminder and a disclaimer that I don't work at Google and this is not an official Google project - just a weekend side hack → It is highly likely you'll get throttled by rate limits - I put as much info as I can in the guide so you know what behavior to expect when that happens. You can also set which default model to use if you want to switch to 1.5 Pro.

Raiza Martin

159,702 views • 1 year ago