📔 Change logs

2026-06

• Published: Extra: Model Distillation — pouring big-model behavior into smaller models
• Published: 13: AI Native Product Design — making probabilistic systems feel reliable
• Published: 12: LLM Engineering — KV cache, inference cost, and deployment systems
• Published: 11: Agents — from chatbots to task-execution systems
• Published: 10: Tool Use — from saying things to doing things
• Published: “Understanding LLMs from First Principles” 06: Scaling Laws and Emergence, 07: Inference and Generation, 08: The Nature of Hallucination, and 09: RAG
• Updated: gave the “Understanding LLMs from First Principles” series a full polish pass — tightened mechanism accuracy and technical details, standardized and completed section illustrations, and added series entrance cards to the home page

2026-05

• Published: 01: The First Principle of LLMs: Token Prediction
• Updated: 01: The First Principle of LLMs: Token Prediction — added 5 section illustrations
• Published: 02: Token and Embedding: How Language Becomes Numbers
• Updated: 02: Token and Embedding: How Language Becomes Numbers — added 5 section illustrations
• Published: 03: Transformer and Attention: How Models “See” Context
• Updated: 03: Transformer and Attention: How Models “See” Context — added 5 explanatory diagrams
• Published: 04: Language as Compression of the World: Why Prediction Can Become Intelligence
• Updated: 04: Language as Compression of the World: Why Prediction Can Become Intelligence — added 5 explanatory diagrams
• Published: 05: Pretraining, Fine-tuning, and Alignment: From Continuation Machine to Assistant — bundled with 6 explanatory diagrams
• Published: The Math Behind LLM Pricing 01: How Inference Actually Works
• Published: The Math Behind LLM Pricing 02: Writing Inference as Equations — bundled with an interactive T_compute / T_memory simulator
• Published: The Math Behind LLM Pricing 03: From Inference Latency to Inference Cost
• Published: The Math Behind LLM Pricing 04: Cracking Open the KV Cache
• Updated: The Math Behind LLM Pricing 03: From Inference Latency to Inference Cost — added a Cost / Token interactive simulator
• Published: The Math Behind LLM Pricing 05: From One GPU to a Cluster — Parallelism and Interconnect
• Updated: 👋 Hello, World! — added a “Recently Published” section listing the latest posts

2026-01

• Published: Vibe Coding

2025-12

• Published: Intent Recognition

2025-06

• Site upgraded to Nextra-4
• Updated: User Value
• Published: Case Study: Yuque’s Consumer Product Line

2024-04

• Updated: User Value
• Updated: 🔗 RAG Intro

2024-03

• Published: RAG (Retrieval-Augmented Generation) Practice Sharing
• Published: Annotation Reply

2024-02

• i18n Support
• Published: Softwaer as a Service
• Published: User Value
• Published: The 7 Question of Product Design
• Structure Adjusted
• Updated site’s domain: https://insights.kaho.io 
• Published: Dictionary
• Published: Japan Journey Gallery

2024-01

• Site Up! 👋 Hello, world!
• Published: 🇯🇵 Japan Journey