Loading video...

Video Failed to Load

Go Home

I’ve decided to start a new adventure where I’m livecoding an entire NeRF renderer from scratch using open-source and permissively-licensed resources, with ChatGPT as my assistant, (and Google, public research, etc).

jperldev's profile picture

James Perlman

5,197 subscribers

67,661 views • 3 years ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

We built Open Gamma An Open Source Presentation Generator with Composio Tool Router and AI SDK - Generate Presentations in Google Slides instantly - Can research on the topic with web search - Can connect and fetch data from multiple data sources like Hubspot, Slack, Notion and more Completely free and open source link to the code:
1:00

We built Open Gamma An Open Source Presentation Generator with Composio Tool Router and AI SDK - Generate Presentations in Google Slides instantly - Can research on the topic with web search - Can connect and fetch data from multiple data sources like Hubspot, Slack, Notion and more Completely free and open source link to the code:

Karan Vaidya

40,455 views • 7 months ago

I wanted to express my gratitude to everyone who has been a significant part of my journey to this day. It is something that I’ve dreamt about my entire life, and I’m excited to share this new adventure with Canadians.
1:22

I wanted to express my gratitude to everyone who has been a significant part of my journey to this day. It is something that I’ve dreamt about my entire life, and I’m excited to share this new adventure with Canadians.

Joshua Kutryk

12,926 views • 2 years ago

ChatGPT hasn't been my main chatbot for a long time But Google AI Mode is. You basically have everything in one place: - Nano banana for image gen/editing - Gemini 2.5 Flash and Pro - Voice typing - File handling - Deep research And above all, the best web grounding available (better than ChatGPT, Claude, etc.). Google is the new Google.
0:48

ChatGPT hasn't been my main chatbot for a long time But Google AI Mode is. You basically have everything in one place: - Nano banana for image gen/editing - Gemini 2.5 Flash and Pro - Voice typing - File handling - Deep research And above all, the best web grounding available (better than ChatGPT, Claude, etc.). Google is the new Google.

Paul Couvert

71,417 views • 9 months ago

I’m building an assistant from scratch using OpenCode first step is iMessage integration. I could run the OpenCode webapp on my phone, but I want a group text with my wife where we can ask it stuff together Here’s a demo, so cool that I can open the same session in the TUI (filmed by my 8 yr old, be gracious)
2:14

I’m building an assistant from scratch using OpenCode first step is iMessage integration. I could run the OpenCode webapp on my phone, but I want a group text with my wife where we can ask it stuff together Here’s a demo, so cool that I can open the same session in the TUI (filmed by my 8 yr old, be gracious)

James Long

11,433 views • 5 months ago

monthly reminder that there is an ENTIRE GOOGLE DRIVE FANDOM PROJECT with TONS of clips of F1 drivers you can use for edits, resources, tweets, etc. AND ITS FREE AND PUBLIC!!! RTs for publicity are appreciated!! click on the link! more info below ⬇️
0:22

monthly reminder that there is an ENTIRE GOOGLE DRIVE FANDOM PROJECT with TONS of clips of F1 drivers you can use for edits, resources, tweets, etc. AND ITS FREE AND PUBLIC!!! RTs for publicity are appreciated!! click on the link! more info below ⬇️

Doctor Ava P.h.D. M.D. Russioscopular Surgeon

102,391 views • 1 year ago

Introducing `claude-researcher` 📈 A powerful Claude 3 research agent that delivers thorough reports in record time. Just provide an topic, and a chain of AIs with **access to Google** will generate an incredibly comprehensive report for you. And it's open-source!
0:37

Introducing `claude-researcher` 📈 A powerful Claude 3 research agent that delivers thorough reports in record time. Just provide an topic, and a chain of AIs with **access to Google** will generate an incredibly comprehensive report for you. And it's open-source!

Matt Shumer

397,549 views • 2 years ago

New generative UI experiences in the Google Gemini and AI Mode in Search use Gemini 3’s multimodal understanding capabilities to make entire user interfaces for you from scratch — dynamically delivering what you need in a visual and interactive way. Google Research software engineer Yaniv Leviathan shares more about the process of building generative UI (hint: so much fun that the team couldn't stop playing with it) and how he's been using it so far.
1:53

New generative UI experiences in the Google Gemini and AI Mode in Search use Gemini 3’s multimodal understanding capabilities to make entire user interfaces for you from scratch — dynamically delivering what you need in a visual and interactive way. Google Research software engineer Yaniv Leviathan shares more about the process of building generative UI (hint: so much fun that the team couldn't stop playing with it) and how he's been using it so far.

Google

138,435 views • 8 months ago

"Google is the front door to the Internet and worth $2T. ChatGPT is the front door to AI." - Sonya Huang 🐥 from Sequoia Capital "I found it interesting when Sam Altman said that, if you are old, you are using ChatGPT as a Google replacement." "If you are 20-30, you are using it as a life coach." "If you are really young, you are using it as an OS."
1:01

"Google is the front door to the Internet and worth $2T. ChatGPT is the front door to AI." - Sonya Huang 🐥 from Sequoia Capital "I found it interesting when Sam Altman said that, if you are old, you are using ChatGPT as a Google replacement." "If you are 20-30, you are using it as a life coach." "If you are really young, you are using it as an OS."

TBPN

46,318 views • 1 year ago

Today I’m launching Open Interpreter, an open-source Code Interpreter that runs locally. Summarize PDFs, visualize datasets, and control your browser — all from a ChatGPT-like interface in your terminal. ● $ pip install open-interpreter $ interpreter
1:30

Today I’m launching Open Interpreter, an open-source Code Interpreter that runs locally. Summarize PDFs, visualize datasets, and control your browser — all from a ChatGPT-like interface in your terminal. ● $ pip install open-interpreter $ interpreter

killian

2,055,740 views • 2 years ago

Introducing Epic’s version control system: Lore! Built from scratch and open-sourced, we made scalability and performance core tenets from day one. We’re releasing Lore as open source today.All source code, along with documentation of data formats and protocols are released under an MIT license and free to use. Help shape it into something even more powerful, together:
0:52

Introducing Epic’s version control system: Lore! Built from scratch and open-sourced, we made scalability and performance core tenets from day one. We’re releasing Lore as open source today.All source code, along with documentation of data formats and protocols are released under an MIT license and free to use. Help shape it into something even more powerful, together:

Unreal Engine

227,769 views • 1 month ago

Zero to $100K with AI: My Real Journey Begins I'm documenting my journey using AI tools in 12 months - will I succeed or crash and burn? Follow along as I build in public, share all my wins and failures, and show you what really happens when a regular person tries to build an AI business from scratch.
1:19

Zero to $100K with AI: My Real Journey Begins I'm documenting my journey using AI tools in 12 months - will I succeed or crash and burn? Follow along as I build in public, share all my wins and failures, and show you what really happens when a regular person tries to build an AI business from scratch.

Ray Fernando

25,806 views • 1 year ago

2/ Building a Website from Scratch with Wide Research We tasked both agents to build a website on UNESCO sites. Manus conducted deep, multi-source research to build a comprehensive and detailed website. The depth is astounding.
1:32

2/ Building a Website from Scratch with Wide Research We tasked both agents to build a website on UNESCO sites. Manus conducted deep, multi-source research to build a comprehensive and detailed website. The depth is astounding.

Manus

22,187 views • 6 months ago

“I left EME with zero naira and I had to start everything from the scratch as a result” Wizkid
0:48

“I left EME with zero naira and I had to start everything from the scratch as a result” Wizkid

ÌKÀ NATION 🇳🇬

119,134 views • 8 months ago

New course: A2A: The Agent2Agent Protocol, built with Google Cloud Tech and IBM Research, and taught by Holt Skinner, Ivan Nardini, and Sandi Besen. Connecting agents built with different frameworks usually requires extensive custom integration. This short course teaches you A2A, the open protocol standardizing how agents discover each other and communicate. Since IBM’s ACP (Agent Communication Protocol) joined forces with A2A, A2A has emerged as the industry standard. In this course, you'll build a healthcare multi-agent system where agents built with different frameworks, such as Google ADK (Agent Development Kit) and LangGraph, collaborate through A2A. You'll wrap each agent as an A2A server, build A2A clients to connect to them, and orchestrate them into sequential and hierarchical workflows. Skills you'll gain: - Expose agents from different frameworks as A2A servers to make them discoverable and interoperable - Chain A2A agents sequentially using ADK, where one agent's output feeds into the next - Connect A2A agents to external data sources using MCP (Model Context Protocol) - Deploy A2A agents using Agent Stack, IBM's open-source infrastructure Join and learn the protocol standardizing agent collaboration!
3:06

New course: A2A: The Agent2Agent Protocol, built with Google Cloud Tech and IBM Research, and taught by Holt Skinner, Ivan Nardini, and Sandi Besen. Connecting agents built with different frameworks usually requires extensive custom integration. This short course teaches you A2A, the open protocol standardizing how agents discover each other and communicate. Since IBM’s ACP (Agent Communication Protocol) joined forces with A2A, A2A has emerged as the industry standard. In this course, you'll build a healthcare multi-agent system where agents built with different frameworks, such as Google ADK (Agent Development Kit) and LangGraph, collaborate through A2A. You'll wrap each agent as an A2A server, build A2A clients to connect to them, and orchestrate them into sequential and hierarchical workflows. Skills you'll gain: - Expose agents from different frameworks as A2A servers to make them discoverable and interoperable - Chain A2A agents sequentially using ADK, where one agent's output feeds into the next - Connect A2A agents to external data sources using MCP (Model Context Protocol) - Deploy A2A agents using Agent Stack, IBM's open-source infrastructure Join and learn the protocol standardizing agent collaboration!

Andrew Ng

86,175 views • 5 months ago

New course: Build and Train an LLM with JAX, built in partnership with Google and taught by Chris Achard. JAX is the open-source library behind Google's Gemini, Veo, and other advanced models. This short course teaches you to build and train a 20-million parameter language model from scratch using JAX and its ecosystem of tools. You'll implement a complete MiniGPT-style architecture from scratch, train it, and chat with your finished model through a graphical interface. Skills you'll gain: - Learn JAX's core primitives: automatic differentiation, JIT compilation, and vectorized execution - Build a MiniGPT-style LLM using Flax/NNX, implementing embedding and transformer blocks - Load a pretrained MiniGPT model and run inference through a chat interface Come learn this important software layer for building LLMs!
1:54

New course: Build and Train an LLM with JAX, built in partnership with Google and taught by Chris Achard. JAX is the open-source library behind Google's Gemini, Veo, and other advanced models. This short course teaches you to build and train a 20-million parameter language model from scratch using JAX and its ecosystem of tools. You'll implement a complete MiniGPT-style architecture from scratch, train it, and chat with your finished model through a graphical interface. Skills you'll gain: - Learn JAX's core primitives: automatic differentiation, JIT compilation, and vectorized execution - Build a MiniGPT-style LLM using Flax/NNX, implementing embedding and transformer blocks - Load a pretrained MiniGPT model and run inference through a chat interface Come learn this important software layer for building LLMs!

Andrew Ng

192,696 views • 4 months ago

In tonight's news, some diverse individuals decided to start a fight with an entire platoon of U.S. Marines, and it went as expected. 📍 6th St, Austin TX
0:42

In tonight's news, some diverse individuals decided to start a fight with an entire platoon of U.S. Marines, and it went as expected. 📍 6th St, Austin TX

₿en Wehrman

3,239,565 views • 2 months ago

Today, we're launching a new Laracasts series that will show you the essentials building an AI agent from scratch. We start with a basic chat response and gradually introduce new concepts, such as the agent loop, custom tools, and more. 😀 "So You Want To Build An Agent"
9:08

Today, we're launching a new Laracasts series that will show you the essentials building an AI agent from scratch. We start with a basic chat response and gradually introduce new concepts, such as the agent loop, custom tools, and more. 😀 "So You Want To Build An Agent"

Laracasts

16,427 views • 3 months ago

📢 New short course in collaboration with Google: Build and Train an LLM with JAX. In this course, you’ll implement and train a 20M-parameter MiniGPT-style language model from scratch using JAX, the open-source library behind Gemini. You’ll build the model architecture, load and preprocess training data, implement the training loop, save checkpoints, and generate text through a chat interface. Taught by Chris Achard, Developer Relations Engineer on Google’s TPU Software team. Enroll now:
1:54

📢 New short course in collaboration with Google: Build and Train an LLM with JAX. In this course, you’ll implement and train a 20M-parameter MiniGPT-style language model from scratch using JAX, the open-source library behind Gemini. You’ll build the model architecture, load and preprocess training data, implement the training loop, save checkpoints, and generate text through a chat interface. Taught by Chris Achard, Developer Relations Engineer on Google’s TPU Software team. Enroll now:

DeepLearning.AI

46,065 views • 4 months ago