S2-E13 · Fine-Tuning, the Tool You Reach For Last (LoRA and QLoRA)
Your assistant is great, but the way it talks keeps slipping. You write the perfect prompt, paste in examples, and it's right about 90% of the time, and that last 10% makes it feel like a toy instead of your product. So you reach for fine-tuning, the most misunderstood tool in AI, and for most of what you're building, the very last thing you should reach for. In this episode you'll learn what fine-tuning actually does (it changes the model's weights, not its desk), the line that saves you weeks ("RAG is for knowledge, fine-tuning is for behavior"), and why force-feeding facts through fine-tuning makes a model hallucinate more, not know more. You'll learn how LoRA and QLoRA make it cheap enough to run on a single free GPU by training a tiny swappable adapter, the decision ladder (prompt, then RAG, then fine-tune), and the honest catches: you need a real dataset, a real eval, and you risk catastrophic forgetting. Episode 13 of Season 2 of How AI Works, a free hands-on course on building with AI. 📺 Full course playlist: • How AI Works · Season 2: Build With AI New episode every week. Subscribe to @HowAIWorksHQ to learn how to build with AI.

Android 17 sucks. So I put Linux on a phone.

Cursor AI Explained: How the $60 Billion AI Code Editor Actually Works

Stop Prompting Claude. Use Karpathy's Method Instead.

S3-E10 · How AI Learned to Think (the Training Algorithm)

Rowan Atkinson's Brilliant Humor Leaves Celebrities in Tears!

Why Google Just Gave Away Gemma 4 for Free

S3-E14 · Don't Get Pwned (Prompt Injection and the Lethal Trifecta)

How To Think SO CLEARLY People Assume You're A Genius

NVIDIA Monopoly is DEAD | OPEN-SOURCE Chips Are HERE!

S2-E12 · Make Your AI Remember You (Agent Memory Explained)

I Made Opus 4.8 and Fable 5 Build the Same App (RAW RESULTS)

S3-E4 · Can You Run a 671B Model? (MoE and Attention Variants)

We're 99.9% sure this pattern is true, but no one can prove it

Planet of the Apes: The Banned Ending They Hide For 60 Years

ML Foundations for AI Engineers (in 34 Minutes)

S3-E12 · How Agents Talk and Remember (MCP, A2A, and Memory)

Gemma 4 12B: The First "Encoder-Free" AI, Explained

Rufus JUST DESTROYED Windows 11 As Millions Watch Microsoft COLLAPSE!

S3-E11 · Thinking on Demand (When More Thinking Helps, and When It Burns Money)

