AI subscriptions add up faster than you notice. I'm paying $236/month across seven AI tools — and every company I'm giving money to says they're losing money on me. The math only works because of VC subsidies that won't last. When the bill catches up, you'll wish you'd built your own stack. This playlist tracks what AI actually costs, why it's about to cost more, and what happens when you stop renting and start owning your compute. Topics covered: • What you're really paying every month (the subscription audit) • Why "$20/mo" turns into $200/mo (the enshittification cycle) • Self-hosting the AI tools you actually use • Replacing SaaS with a homelab — what works, what doesn't • When AI is genuinely cheaper than humans, and when it isn't If you've ever stared at a credit card statement wondering when "just one more subscription" became $100+/month, this playlist is for you.
Curated by: Codacus (15 videos)
Someone improved 15 different LLMs at coding — all of them — in a single afternoon. They didn't fine-tune anything. They didn't switch models. They changed everything around the model. That's harness engineering — the four layers between your intent and the model's output that actually determine your results. 00:00 Intro 00:14 How We Got Here 01:08 What Is Harness Engineering 01:56 My Personal Setup 02:36 Layer 1: Agent Frameworks 03:43 Layer 2: Tool Harnesses 04:45 Layer 3: Prompt Harnesses 05:55 Layer 4: Inference Engines 06:52 The Convergence 08:15 What To Do Next 🧠 Layer 1: Agent Frameworks How your model plans, acts, and recovers. Comparing OpenAI Agents SDK, Google ADK, Anthropic Agent SDK, LangGraph, CrewAI, and AutoGen. 🔌 Layer 2: Tool Harnesses MCP (Model Context Protocol) — the USB-C of AI. 97M monthly SDK downloads, 10K+ community servers, adopted by every major player. 📄 Layer 3: Prompt Harnesses Beyond system prompts — hierarchical instruction files, DSPy auto-optimization, Microsoft Guidance constrained generation. ⚡ Layer 4: Inference Harnesses vLLM vs SGLang benchmarks, PagedAttention, Ollama, llama.cpp — where and how fast your model runs. The models are converging. The harnesses are diverging. That's where builders win or lose. 📺 More deep dives coming on MCP and agent frameworks — subscribe to catch them.