LLM
8 articles
Prompt Caching (Part 4): AWS Documents 4,096 — I Measured 1,024
AWS gives Claude Sonnet 4.5 a 4,096-token minimum cacheable prefix. Bisecting on Bedrock put the real threshold at 1,024. Three control models matched their docs; only this row was off.
Prompt Caching (Part 1): What Is Actually Cached
Prompt caching saves the server's prefill compute, not the cost of re-sending tokens. Where the KV cache comes from, why a prefix must match token for token, and why caching can cost more.
Prompt Caching (Part 2): Five Vendors, Three Clouds, One Bill
AWS documents a 4,096-token minimum for Sonnet 4.5 on Bedrock; I measured 1,024. Multipliers, TTL tiers and cross-region behaviour for five vendors — measured kept apart from documented.
Prompt Caching (Part 3): It Is On and Not Hitting — Now What
Cache invalidation almost never errors: inference succeeds, the logs are clean, only the bill grows. Four culprits by frequency, plus a cross-vendor hit-rate self-check you can run today.
How Do I Explain "Agent" to My Wife?
From 'the Lark bot can't do math' to 'raising your own AI lobster' — an AI-agent explainer for normal humans. Thirteen burning questions covering LLMs, tokens, Tools, MCP, RAG, Skills, Memory, Multi-Agent systems, and 2026 model prices. The AI isn't dumb — it just hasn't been raised properly yet.
How AI Coding Agents Actually Work: A Source Code Deep Dive
We traced the source code of Amazon Q CLI and Claude Code to understand how AI coding agents really work under the hood.
How to Build a RAG System with LangChain and Elasticsearch
A hands-on guide to building Retrieval Augmented Generation — from vector embeddings to context-enhanced LLM answers.
How to Build an AI Video Course Generator with Python
Turn PowerPoint slides into narrated video courses using LLMs, text-to-speech, and FFmpeg — fully automated, with the pipeline costs measured.