BestHub
Sign in
ZhiKe AI
Author

ZhiKe AI

We dissect AI-era technologies, tools, and trends with a hardcore perspective. Focused on large models, agents, MCP, function calling, and hands‑on AI development. No fluff, no hype—only actionable insights, source code, and practical ideas. Get a daily dose of intelligence to simplify tech and make efficiency tangible.

116
Articles
0
Likes
228
Views
0
Comments
Recent Articles

Latest from ZhiKe AI

100 recent articles max
ZhiKe AI
ZhiKe AI
May 17, 2026 · Artificial Intelligence

Harness Engineering: How 8 AI Agents Collaborate to Write Wuxia Novels

The article details Harness Engineering’s deterministic multi‑agent workflow that splits novel writing into seven staged phases, enforced by strict rule files and verification scripts, enabling eight specialized AI agents to collaboratively produce complete wuxia novels with consistent characters, martial arts systems, and quality guarantees.

AI orchestrationMulti-Agent SystemsPrompt Engineering
0 likes · 22 min read
Harness Engineering: How 8 AI Agents Collaborate to Write Wuxia Novels
ZhiKe AI
ZhiKe AI
May 16, 2026 · Industry Insights

Why Compute Is the Lifeline of AI: Anthropic CFO Reveals the Industry’s Harsh Truth

Anthropic’s new credit‑based pricing for Claude, massive multi‑chip compute investments, and the CFO’s warning that buying too little or too much compute is dangerous together illustrate how rising hardware costs and Jevons paradox are driving the AI industry’s ever‑increasing subscription fees.

AI computeAI industryAnthropic
0 likes · 7 min read
Why Compute Is the Lifeline of AI: Anthropic CFO Reveals the Industry’s Harsh Truth
ZhiKe AI
ZhiKe AI
May 15, 2026 · Artificial Intelligence

How to Build Effective Claude Skills: Step‑by‑Step Guide, Limits, and Real Examples

This guide walks you through creating custom Claude skills—from defining a precise problem and naming conventions to crafting detailed descriptions, writing structured instructions, uploading via the UI or API, testing with realistic scenarios, iterating based on usage, and applying best‑practice tips with concrete skill examples.

AIClaudePrompt Engineering
0 likes · 22 min read
How to Build Effective Claude Skills: Step‑by‑Step Guide, Limits, and Real Examples
ZhiKe AI
ZhiKe AI
May 14, 2026 · Fundamentals

Why DDD Is a Cognitive Alignment Tool, Not Just an Architecture

The article explains how Domain‑Driven Design addresses the pitfalls of bloated services, unclear boundaries, and inconsistent terminology by introducing bounded contexts, aggregates, and domain events, and outlines a step‑by‑step adoption process while debunking common misconceptions.

AggregatesDomain EventsDomain-Driven Design
0 likes · 9 min read
Why DDD Is a Cognitive Alignment Tool, Not Just an Architecture
ZhiKe AI
ZhiKe AI
May 13, 2026 · Industry Insights

Leaking Ship, Still Aboard: Ma Huateng’s Candid Take on Tencent’s AI Turnaround

At Tencent's May 13 shareholder meeting, CEO Ma Huateng admitted the company's AI efforts were "leaking," outlined a three‑stage diagnosis, detailed a massive 360 billion‑yuan investment and organizational overhaul, and explained the "parasitic" WeChat strategy while questioning whether the ship can now sail faster.

AI InvestmentAI StrategyCorporate restructuring
0 likes · 9 min read
Leaking Ship, Still Aboard: Ma Huateng’s Candid Take on Tencent’s AI Turnaround
ZhiKe AI
ZhiKe AI
May 13, 2026 · Artificial Intelligence

How Effective Harnesses Keep Long‑Running AI Agents Productive

The article analyzes why AI agents lose progress across discrete context windows, identifies two failure patterns, and presents a dual‑harness solution—an initialization agent and a coding agent—that uses init scripts, progress files, and Git to enable incremental, test‑driven development over hours or days.

AI agentsClaude Agent SDKContext Management
0 likes · 16 min read
How Effective Harnesses Keep Long‑Running AI Agents Productive
ZhiKe AI
ZhiKe AI
May 11, 2026 · Backend Development

Java Rewrites OpenClaw: An Architecture‑Level Translation, Not a Simple Port

A Java team rebuilt the popular Node.js AI‑Agent platform OpenClaw from scratch, replacing AI‑generated “vibe code” with a carefully refactored architecture that leverages Spring AI, JobRunr, and Spring Modulith, and demonstrates how to run the new Java version with just a few commands.

AI agentsArchitecture TranslationJava
0 likes · 16 min read
Java Rewrites OpenClaw: An Architecture‑Level Translation, Not a Simple Port
ZhiKe AI
ZhiKe AI
May 10, 2026 · Fundamentals

What the 800‑Page “Software Engineering” Textbook Really Teaches

The article explains that the classic 800‑page software engineering textbook is not a list of methods to memorize but a decision‑making coordinate system that guides readers through process, requirements, architecture, testing, and evolution, helping them understand why and how to apply each practice in real projects.

Software EngineeringSoftware EvolutionSoftware Process
0 likes · 11 min read
What the 800‑Page “Software Engineering” Textbook Really Teaches
ZhiKe AI
ZhiKe AI
May 9, 2026 · Artificial Intelligence

Why Agent Loops Matter More Than Raw Model Power

The article explains how AI agents that operate in a reasoning‑action‑observation loop outperform single‑shot LLM inference by continuously observing, planning, and correcting errors, illustrated through a ticket‑booking example and detailed analyses of ReAct, Plan‑Execute, OODA, and Steering Loop architectures.

AI agentsLLMOODA
0 likes · 15 min read
Why Agent Loops Matter More Than Raw Model Power