Distillation: Why Everyone is Getting it Wrong!

From the creator

Thanks to DataForSEO for sponsoring this video — get $5 in free credits (standard is $1): https://l.dataforseo.com/44MSLlT AI Distillation Explained: Why It’s Misunderstood (and What It Means for Open Models) I break down why “distillation” is widely misunderstood in AI and how that confusion could fuel policy moves like banning open Chinese models. Using Moonshot’s rapid K2 → K2.6 → K3 progress and claims that it was “distilled” from top US frontier models, I explain textbook logit distillation (soft labels, dark knowledge, temperature, and the need for access to logits), how this maps to LLMs, and why most APIs don’t expose the probability signals required for real capability transfer. I cover four types of distillation, focusing on sequence-level distillation/output harvesting (e.g., Alpaca/Vicuna, and Anthropic’s report of large-scale fraudulent Claude usage) and why it mostly copies style. I also walk through the modern training pipeline (pre-train, mid-train, SFT, RL), on-policy distillation/RLAIF requirements, compute, and timelines around Fable-5 vs K3. My voice to text App: whryte.com Website: https://engineerprompt.ai/ RAG Beyond Basics Course: https://prompt-s-site.thinkific.com/courses/rag Signup for Newsletter, localgpt: https://tally.so/r/3y9bb0 Let's Connect: 🦾 Discord: https://discord.com/invite/t4eYQRUcXB ☕ Buy me a Coffee: https://ko-fi.com/promptengineering |🔴 Patreon: https://www.patreon.com/PromptEngineering 💼Consulting: https://calendly.com/engineerprompt/consulting-call 📧 Business Contact: engineerprompt@gmail.com Become Member: http://tinyurl.com/y5h28s6h 💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off). Signup for Newsletter, localgpt: https://tally.so/r/3y9bb0 00:00 Distillatio 00:30 Moonshot K3 Timeline 01:30 What Distillation Means 02:41 Soft Labels Explained 05:11 Sponsor Break 06:11 Distilling Language Models 08:15 Four Distillation Types 09:49 Sequence Output Harvesting 11:55 Where Capability Comes From 13:28 On Policy Distillation 15:21 Can K3 Copy Fable 5? 16:37 Wrap Up

Stop watching · start building
Matched to Prompt Engineering

Makers residency 4th edition

Your idea can be anything. At our last workshops, people built plant-based nutrition businesses, a way to measure planetary resilience, crochet headwear and a way to connect lonely people living in the same building. An asset manager went on to raise an additional £25M on their fund within nine months. The fourth workshop is a full day at KOKO with Nick Sarafa, learning to build with Claude Code. Bring the thing you keep meaning to start. We’ll bring the pizza.

◆ Fri 13 Nov 2026 ◆ KOKO, London
Makers residency 4th edition
Live event
Makers residency 4th edition
Fri 13 Nov 2026

More like this

Running one yourself?

List your AI event,
wherever it is.

A meetup, a workshop, a hackathon, a conference. Any city, or online. Tell us about it and it lands in front of people already learning this stuff.