chrishayuk

0:25:40

why llama-3-8B is 8 billion parameters instead of 7?

0:00:47

3 reasons to choose ZIGLANG over RUST for Programming #zig

0:28:51

getting started with typespec

0:00:43

NVidia Nemotron 340B is the model to use for synthetic data generation

0:11:50

functional programming with nim language

0:28:35

NVIDIA's Nemotron-4's is totally insane for synthetic data generation

0:00:48

Multi-Head Attention vs Group Query Attention in AI Models

0:01:00

Coding a Math Function in ZIG - In 60 Seconds! #ziglang

0:00:56

Langchain vs Llama Index #python #coding #ai #gpt

0:39:51

The future of AI agents is WebAssembly (get started now)

0:00:40

Alan Kay's Vision: The Essence of Object-Oriented Programming

0:22:49

Understanding STaR and how it powers Claude and Gemini/Gemma 2 (and maybe OpenAI Q* or Strawberry)

0:00:56

ai bias in LLM's explained in a small language model built from scratch

0:40:55

superduperdb supercharges your database for AI

0:00:50

how does nim compare to zig, rust or c programming languages

0:00:51

ChatGPT converts my JavaScript REST Service to Python #chatgpt coding

0:29:11

Real-Time Rust: Building WebSockets with Tokio Tungstenite

0:00:51

how RAG solves hallucinations with LLM's #ai #llm #gpt

0:01:00

Rust Actix-Web Server with Docker using ChatGPT in 60 seconds!

0:43:33

Getting Started with ReAct AI agents work using langchain

0:00:57

ChatGPT can't reverse words either #ai #gpt #chatgpt #chatgpt4 #llm #javascript #python #shorts

0:40:12

introduction to wapm (webassembly package manager) tutorial using wasmer, assemblyscript and as-wasi

0:17:35

Is JavaScriptCore (JSC) really the reason bun.js is so fast? Is V8 that slow? Is JSC the fastest?

0:00:49

new 3 pillars of object oriented programming in a world of AI and LLM's