Shane | LLM Implementation

@UCf12NnZycD7LB8prrgdTOyg - 2.2K subscribers

Hi, I'm Shane. I build and teach LLM, RAG, and AI agent systems with practical demos and notebooks. Try Jupiter (AI job search app): jupiterpath.dev Discord: discord.gg/KpnJQbgpjt Sponsorships & business: [email protected]

Home Videos Live Playlists

Fix Bad RAG Queries Without Re-Indexing

Fix Bad RAG Queries Without Re-Indexing Shane | LLM Implementation

54 views - 3 days ago

Why Your PDF Breaks RAG (And How to Fix It)

Why Your PDF Breaks RAG (And How to Fix It) Shane | LLM Implementation

149 views - 1 week ago

Build a RAG System in 50 Lines of Python

Build a RAG System in 50 Lines of Python Shane | LLM Implementation

161 views - 1 week ago

I Built an AI Agent to Find AI Jobs (Face Reveal)

I Built an AI Agent to Find AI Jobs (Face Reveal) Shane | LLM Implementation

154 views - 3 weeks ago

Fine-Tune EmbeddingGemma: 5% to 77% RAG Accuracy (Free Colab)

Fine-Tune EmbeddingGemma: 5% to 77% RAG Accuracy (Free Colab) Shane | LLM Implementation

277 views - 4 weeks ago

Train a Reasoning Model for $1.23 (Reinforcement Learning)

Train a Reasoning Model for $1.23 (Reinforcement Learning) Shane | LLM Implementation

247 views - 1 month ago

Stop Using RLHF: How to Align & Control LLMs (DPO Guide)

Stop Using RLHF: How to Align & Control LLMs (DPO Guide) Shane | LLM Implementation

344 views - 3 months ago

Fine-tune a 30B Model for $0.62 (Prompt Distillation with Tinker)

Fine-tune a 30B Model for $0.62 (Prompt Distillation with Tinker) Shane | LLM Implementation

17.5K views - 3 months ago

Local RAG in 1.3s: LangGraph + Ollama (Free, No API Keys)

Local RAG in 1.3s: LangGraph + Ollama (Free, No API Keys) Shane | LLM Implementation

938 views - 4 months ago

Fix Bad OCR: Fine-Tune DeepSeek-V2 on Your Own Data (Unsloth)

Fix Bad OCR: Fine-Tune DeepSeek-V2 on Your Own Data (Unsloth) Shane | LLM Implementation

1.8K views - 4 months ago

Stop Building Brittle Agents: Production Patterns for LangGraph

Stop Building Brittle Agents: Production Patterns for LangGraph Shane | LLM Implementation

297 views - 4 months ago

Local AI Agent with LangGraph + Ollama (Full Tutorial, Qwen3)

Local AI Agent with LangGraph + Ollama (Full Tutorial, Qwen3) Shane | LLM Implementation

8.1K views - 4 months ago

The Ultimate Local RAG Stack: EmbeddingGemma + SQLite-vec + Ollama

The Ultimate Local RAG Stack: EmbeddingGemma + SQLite-vec + Ollama Shane | LLM Implementation

3.2K views - 6 months ago

Building an AI Judge: The Most Powerful (and Dangerous) Way to Evaluate LLMs

Building an AI Judge: The Most Powerful (and Dangerous) Way to Evaluate LLMs Shane | LLM Implementation

236 views - 6 months ago

How to Test AI Models: The 2 Methods That Actually Work

How to Test AI Models: The 2 Methods That Actually Work Shane | LLM Implementation

645 views - 6 months ago

The $7,000 AI Mistake That Changed How I Evaluate Every Model

The $7,000 AI Mistake That Changed How I Evaluate Every Model Shane | LLM Implementation

166 views - 6 months ago

Temperature vs Top-P: Stop Random AI Replies (Complete Guide)

Temperature vs Top-P: Stop Random AI Replies (Complete Guide) Shane | LLM Implementation

1.2K views - 6 months ago

Fine-Tune OpenAI's gpt-oss-20b on a FREE GPU: Complete Unsloth Tutorial

Fine-Tune OpenAI's gpt-oss-20b on a FREE GPU: Complete Unsloth Tutorial Shane | LLM Implementation

2K views - 6 months ago

Why New AI Models Feel "Lobotomized" - The Hidden Alignment Process

Why New AI Models Feel "Lobotomized" - The Hidden Alignment Process Shane | LLM Implementation

133 views - 7 months ago

How 120B+ Parameter Models Run on One GPU (The MoE Secret)

How 120B+ Parameter Models Run on One GPU (The MoE Secret) Shane | LLM Implementation

1.7K views - 7 months ago

Your AI Is ~8× More Expensive in Some Languages — Here's Why

Your AI Is ~8× More Expensive in Some Languages — Here's Why Shane | LLM Implementation

109 views - 7 months ago

The AI Startup Trap: Why 99% of GPT Wrappers Fail (and the Playbook to Beat the Odds)

The AI Startup Trap: Why 99% of GPT Wrappers Fail (and the Playbook to Beat the Odds) Shane | LLM Implementation

149 views - 7 months ago

Build with Top AI Models for FREE: The New Rules of AI Engineering

Build with Top AI Models for FREE: The New Rules of AI Engineering Shane | LLM Implementation

171 views - 7 months ago

The Real Reason AI Exploded: From Language Models to Foundation Models

The Real Reason AI Exploded: From Language Models to Foundation Models Shane | LLM Implementation

176 views - 7 months ago

Run a 235B Parameter AI Model FOR FREE! (Qwen3 + Cline & Kilo Code Demo)

Run a 235B Parameter AI Model FOR FREE! (Qwen3 + Cline & Kilo Code Demo) Shane | LLM Implementation

986 views - 7 months ago

Kimi K2 + SuperClaude: The Ultimate AI Stack (Tutorial)

Kimi K2 + SuperClaude: The Ultimate AI Stack (Tutorial) Shane | LLM Implementation

542 views - 7 months ago

Context Engineering: The Ultimate Guide to 10x Your AI Coding Workflow

Context Engineering: The Ultimate Guide to 10x Your AI Coding Workflow Shane | LLM Implementation

575 views - 8 months ago

Google Gemini CLI vs. Anthropic Claude Code: The Ultimate AI Coding Agent Showdown

Google Gemini CLI vs. Anthropic Claude Code: The Ultimate AI Coding Agent Showdown Shane | LLM Implementation

1.1K views - 8 months ago

Gemini & LangGraph: How to Build & Debug a Full-Stack Research AI Agent (Tutorial)

Gemini & LangGraph: How to Build & Debug a Full-Stack Research AI Agent (Tutorial) Shane | LLM Implementation

1.8K views - 9 months ago

Mastering LLM Agent Frameworks: LangGraph, AG2, CrewAI, Semantic Kernel for AI Development

Mastering LLM Agent Frameworks: LangGraph, AG2, CrewAI, Semantic Kernel for AI Development Shane | LLM Implementation

606 views - 9 months ago

Fine-Tune Qwen3 14B 2x Faster with Unsloth: Step-by-Step Colab Guide

Fine-Tune Qwen3 14B 2x Faster with Unsloth: Step-by-Step Colab Guide Shane | LLM Implementation

1.2K views - 10 months ago

Ultimate Guide: Deploy Google ADK Agents to Vertex AI & Cloud Run (Step-by-Step Tutorial)

Ultimate Guide: Deploy Google ADK Agents to Vertex AI & Cloud Run (Step-by-Step Tutorial) Shane | LLM Implementation

6.3K views - 10 months ago

Advanced Google ADK Tutorial: Build Multi-Agent AI Workflows with LiteLLM

Advanced Google ADK Tutorial: Build Multi-Agent AI Workflows with LiteLLM Shane | LLM Implementation

1.1K views - 10 months ago

GPT-4.1 API Tutorial: Explore OpenAI's NEW Models (Mini, Nano, 1M Tokens!)

GPT-4.1 API Tutorial: Explore OpenAI's NEW Models (Mini, Nano, 1M Tokens!) Shane | LLM Implementation

277 views - 11 months ago

Google ADK Quickstart: Build a Gemini AI Agent with Python Step-by-Step

Google ADK Quickstart: Build a Gemini AI Agent with Python Step-by-Step Shane | LLM Implementation

1.2K views - 11 months ago

Master MCP: Build a Python Weather Server for LLMs (Tutorial)

Master MCP: Build a Python Weather Server for LLMs (Tutorial) Shane | LLM Implementation

774 views - 11 months ago

Budget-Friendly Llama 3 Fine-tuning with Unsloth: Humanize AI Prompts on Google Colab T4 GPU

Budget-Friendly Llama 3 Fine-tuning with Unsloth: Humanize AI Prompts on Google Colab T4 GPU Shane | LLM Implementation

471 views - 11 months ago

How to Cut Video Editing Time by 65% with Gemini 2.5 Pro API Tutorial

How to Cut Video Editing Time by 65% with Gemini 2.5 Pro API Tutorial Shane | LLM Implementation

510 views - 11 months ago

Gemini 2.5 Pro Hands-On: AI Studio Demo & Python API Tutorial (Handling Rate Limits)

Gemini 2.5 Pro Hands-On: AI Studio Demo & Python API Tutorial (Handling Rate Limits) Shane | LLM Implementation

263 views - 11 months ago

Practical Gemini Fine-Tuning: Step-by-Step Guide with Vertex AI & Google Cloud

Practical Gemini Fine-Tuning: Step-by-Step Guide with Vertex AI & Google Cloud Shane | LLM Implementation

2.3K views - 11 months ago