RouteLLM achieves 90% GPT4o Quality AND 80% CHEAPER
Matthew Berman. Walks through the LMSYS RouteLLM paper and code: a small classifier sits in front of a strong/weak model pair and decides which one to call, hitting roughly 95% of the strong model's quality at a fraction of the cost. The view count is under the usual 100k bar, but for the specific "show me real model routing, not just model comparisons" niche this is the cleanest explanation on YouTube and lines up directly with the article's quality/cost tradeoff section.
AI Expert note
Model names, pricing and capabilities change quickly. Use this for the decision pattern, then verify current model behavior before adopting it.
What you should get from this
Evaluate model-routing tradeoffs between quality, cost and reliability before adding orchestration complexity.
Watch next
Continue through the same learning path with the next curated companion videos.
40 minutesAndrej Karpathy: Software Is Changing (Again)
Evaluate partial-autonomy product ideas where humans keep control over high-risk decisions.
Watch next
18 minutesPydantic is all you need: Jason Liu
Learn why schema-first LLM calls need typed objects, validators, retries and explicit handling for malformed or hallucinated fields.
Watch next
25 minutesPrompting 101 | Code w/ Claude
Watch a vague insurance-claims prompt become a structured, testable prompt with clearer examples, output rules and refusal behavior.
Watch nextRelated videos
18 minutesAWS re:Invent 2025 - Implementing Human-in-the-Loop Controls for Multi-Agent AI Systems (CNS428)
17 minutes12-Factor Agents: Patterns of reliable LLM applications — Dex Horthy, HumanLayer
6 minutesAI Voice Agents: How They Actually Work & Why They Sound So Human
8 minutesAnthropic's Claude Computer Use Is A Game Changer | YC Decoded
Take it further
Hand-picked external courses that go deeper on this topic.
Coursera · Vanderbilt UniversityChatGPT: Excel at Personal Automation with GPTs, AI & Zapier
The clearest path from "I use ChatGPT in a tab" to "my AI handles my inbox while I sleep." Three-course specialization built around Zapier — no Python required. By the end you'll have agents that summarise emails, update spreadsheets, and trigger workflows when conditions are met.
Hugging FaceAI Agents Course
The clearest open-source treatment of agentic systems available. Anchored in the three frameworks engineers actually evaluate (smolagents, LlamaIndex, LangGraph) rather than one vendor's stack. Concludes with a benchmark assignment and public leaderboard — accountability your team can verify.