#prefix caching
102 related articles
·4 min
Kun: An Open-Source AI Coding Agent Deeply Optimized for DeepSeek
Kun is an open-source AI coding agent optimized for DeepSeek and domestic users, with nearly 5,000 GitHub stars. Features include requirements drafting, inline diffs, cost visualization, and mobile monitoring. Real-world cache hit rates reached 97%, keeping costs extremely low.
Read more →
·4 min
BingoCode: An Open-Source AI Coding Tool for Offline Deployment — A Claude Code Alternative
BingoCode is an MIT-licensed open-source AI coding tool supporting offline intranet deployment, compatible with DeepSeek, Claude, OpenAI, and Gemini. Pure CLI design, four-step setup, high cache hit rates for lower costs — ideal for security-conscious teams.
Read more →
·6 min
AI's Second Half: The Decisive Battle Shifts from Models to Infrastructure
Model capabilities are converging, making inference cost and scalability the new focus of AI competition. A deep analysis of AI infrastructure's core layers.
Read more →
·4 min
GPT-5.6 Three-Model Benchmark: How Close Are Sol/Terra/Luna to Claude?
Hands-on benchmark of GPT-5.6's three models — Sol, Terra, and Luna — covering frontend, math, and long-horizon agentic tasks. Full scores, category breakdowns, and selection guidance vs. Fable 5 and Opus 4.8.
Read more →
·3 min
GPT-5.6 Three-Model Architecture Explained: Sol/Terra/Luna Pricing and Performance Overview
GPT-5.6 introduces a Sol/Terra/Luna three-model architecture. Terra delivers near-flagship performance at half the price, with new Max and Ultra reasoning tiers.
Read more →
·7 min
Demystifying Claude Code's Harness in 60 Lines of Python: The Core of AI Coding Tool Performance Differences
The same model scores 77% in Claude Code but jumps to 93% in Cursor—the only variable is the Harness. This article dissects how AI coding tools work in 60 lines of Python.
Read more →
·6 min
The Complete Guide to GLM-5.2: Hands-On Review of an Open-Source Long-Context Model
An in-depth hands-on review of Zhipu AI's flagship GLM-5.2: 1M-token context, strong coding, mature agent workflows—at one-fifth the price of top frontier models. Covers website testing, Cursor integration, MCP tooling, and production migration.
Read more →
·5 min
Git Hash Chain Malleability: How Fragile Is the Immutability You Trust?
Are Git hash chains truly immutable? This article dives into Git hash chain malleability, SHA-1 collision risks, and security boundaries, offering practical tips like GPG signing and SHA-256 migration to build a correct Git security trust model.
Read more →
·7 min
Context Warp Drive: A Deep Dive into Deterministic Context Folding for AI Agents
An in-depth look at 'Deterministic Context Folding' from Context Warp Drive: solving AI agent context window management with reproducible, cacheable, debuggable context compression for production-grade agents.
Read more →
·6 min
GPT-5.6 Explained: Three Variants and OpenAI's First Government Review of an AI Model
OpenAI released GPT-5.6 with three variants—Soul, Terra, Luna—and for the first time notified and submitted the model to U.S. government review before full release. A deep dive into the variants, Max/Ultra upgrades, and cybersecurity defenses.
Read more →
·6 min
GPT-5.6 Hits 91.9% on Coding Benchmark: A Guide to Choosing Among Three Tiers and Avoiding Ultra Mode Pitfalls
GPT-5.6 launches Soul/Terra/Luna, with flagship Soul scoring 91.9% on Terminal Bench 2.1. This article breaks down the Ultra vs Max reasoning modes, three-tier pricing, and four hidden pitfalls to guide your technical selection.
Read more →
·4 min
Claude Code /cd Command: The Hidden Trick for Switching Directories Without Losing Context
Learn how Claude Code's /cd command lets you switch working directories without losing conversation context — perfect for microservices, monorepos, and multi-module development.
Read more →
·3 min
Claude Code Caching Explained: A Practical Guide to Saving Money and Speeding Up
A deep dive into Claude Code's Prompt Caching mechanism, covering the three-layer cache structure, invalidation rules, lifecycle management, and best practices to reduce API costs and boost response speed.
Read more →
·6 min
GLM 5.2 Arrives: Industry Upheaval on the Eve of AI Margin Collapse
The rise of Zhipu's GLM 5.2 is accelerating the democratization of LLM capabilities. This article analyzes the commoditization of foundation models, the logic behind margin collapse, and the opportunities and challenges facing application-layer and foundation model firms.
Read more →
·5 min
Claude Drives the sqlite-utils 4.0 Release: The Real Cost and Collaboration Methodology of AI-Assisted Refactoring
Developer Simon Willison used Claude to ship sqlite-utils 4.0: 37 prompts, 34 commits, $149 API cost — revealing coding agents' real capabilities, cross-model review, and agentic engineering best practices.
Read more →
·5 min
Claude Sonnet 5 Integrated with Devin: Enhanced Coding Performance with 30% Lower Quota Consumption
Anthropic's Claude Sonnet 5 launches on Devin Desktop and CLI, delivering frontier-level coding performance while reducing quota consumption by ~30% compared to the previous generation.
Read more →
·7 min
Harness Engineering: Core Methodology and Practical Guide for Enterprise-Level AI Programming
Can AI really replace programmers? This article explains Harness Engineering principles and its three evolutionary stages, revealing real pain points of enterprise AI programming.
Read more →
·6 min
AI Workspace Session and Cache Leaks: A Complete Analysis of Multi-Tenant Isolation Security Risks
AI workspaces face cross-tenant session and cache leak risks that can expose sensitive enterprise data. This article analyzes multi-tenant isolation pitfalls, common architectural flaws, and actionable defenses.
Read more →
·3 min
CodeBurn: The 8.4K-Star Open-Source Tool That Tracks Every Cent of Your AI Coding Spend
CodeBurn is a privacy-first local tool for analyzing AI coding costs. It supports 31 tools including Claude Code, Cursor, and Codex, breaking down spending by model, project, and task to eliminate hidden waste.
Read more →
·3 min
Vibe Coding Guide: Building Web Apps with AI from Zero Experience
Vibe Coding lets non-programmers build web apps using natural language and AI agents. Learn Claude Code, model selection, cost control via cache optimization, and agentic engineering.
Read more →