#code drift
413 related articles
·4 min
LibTV Hands-On: A Full Breakdown of How an AI Agent Produces an Animated Short in One Day
Hands-on test of LibTV's AI Agent: from script and storyboarding to video compositing, one person completes an animated short in a day. Full breakdown of the Skill library, node workflow, and Story Board features.
Read more →
·4 min
AI Agent Development in Practice: A Complete Path from Zero to Production
A systematic guide to AI Agent development covering core modules, framework selection, tool calling, data preparation, and production deployment to help developers build production-ready Agent applications.
Read more →
·4 min
IntelliJ IDEA Efficiency Configuration Guide: Lessons from Seven Years of Java Development
A senior Java developer shares 7 years of IntelliJ IDEA configuration tips: JVM tuning, AI-assisted coding, Testcontainers testing, debugging tricks, and Spring toolchain setup.
Read more →
·5 min
Complete Breakdown of Core Competencies for AI Agent Engineers: From Demo to Production-Grade Systems
Deep breakdown of 4 core AI Agent engineer competencies: business decomposition, multi-Agent architecture, quantitative evaluation, and engineering delivery—bridging the gap from Demo to production.
Read more →
·3 min
Simplified Technical English (STE): A Cross-Disciplinary Approach to Optimizing LLM Prompts
Explore how ASD-STE100 Simplified Technical English from aviation can be applied to LLM prompt engineering. STE's disambiguation principles—controlled vocabulary, short sentences, active voice—can improve LLM output accuracy and consistency.
Read more →
·2 min
How Users Gradually Learn to Trust Gemini: The Shift from Full Supervision to Selective Delegation
Exploring how users evolve trust in Gemini and generative AI—from verifying everything to selective delegation, analyzing trust patterns, key factors, and the trust drift trap.
Read more →
·3 min
API Mock vs. Sandbox in Agent Testing: A Detailed Layered Strategy Guide
API Mock is fast but misses bugs; Sandbox is realistic but costly. This article analyzes their core differences and provides a layered testing strategy for building reliable Agent test systems.
Read more →
·3 min
Opus 5 Hands-On: Powerful but Slow — Inference Speed Becomes the New AI Battleground
An AI practitioner tests Opus 5: powerful capabilities but painfully slow inference. Deep analysis of how LLM competition is shifting from intelligence to inference speed.
Read more →
·3 min
How GitHub Established Reliable Ownership for 14,000 Repositories in 45 Days
GitHub had over 14,000 internal repos with less than half having clear ownership. In 45 days, they verified ownership for every active repo through activity filtering, validation, and archiving.
Read more →
·3 min
When Should You Use Machine Learning? A Pragmatic Decision Guide for Data Scientists
Not every data science problem needs ML. This guide offers a decision framework across four dimensions — rule complexity, data quality, prediction needs, and interpretability — to avoid over-engineering.
Read more →
·4 min
From Solo Analyst to Team Data Platform: A Practical Guide to Leveling Up Your Tech Stack
How should a data scientist upgrade their tech stack when transitioning from IC to team lead? A phased roadmap covering Git, dbt, Snowflake, modern data stack, and generative AI.
Read more →
·3 min
GLM 5.2 Hands-On: An Open-Source, Low-Cost Model That Rivals Opus
In-depth hands-on review of GLM 5.2: a 753B-parameter open-source model with a 1M-token context, rivaling Opus 4.8 at about one-tenth the price. Full setup guide for Claude Code and Cursor.
Read more →
·3 min
ProductPai Weekly Roundup: 5 New AI Products Worth Watching
Based on the ProductPai discovery community's weekly rankings, we round up the top five new AI products—from the family AI picture book platform Tonghui and AI imaging studio Zopia to the layout tool Kami and macOS app Frosted.
Read more →
·3 min
GPT-5.6 Requires Government Approval: AI Regulation Enters Deep Waters
OpenAI's GPT-5.6 requires case-by-case government approval, and Claude Mythos was pulled after breaching classified systems. A full breakdown of frontier AI hitting the national security red line.
Read more →
·3 min
GPT-5.6 Requires Government Approval: AI Regulation Enters Uncharted Waters
OpenAI released GPT-5.6 but it requires case-by-case government approval, while Claude Mythos was pulled after breaching classified systems. A full breakdown of AI capabilities hitting national security red lines.
Read more →
·3 min
ProductPai Weekly Roundup: 5 Noteworthy New AI Products
A roundup of the top five AI products from ProductPai's weekly rankings: from the family AI picture-book platform TongHui and AI imaging studio Zopia, to the document layout tool Kami and macOS efficiency app Frosted.
Read more →
·4 min
Mass-Producing AI Short Dramas in Practice: Building a Continuous Production Workflow with Skills
The hardest part of AI short dramas isn't generating a pretty shot, but keeping characters, scenes, and style consistent. This article uses a real American campus drama test to detail how to build reusable workflows with Skills, plus three pitfall-avoidance tips.
Read more →
·3 min
The Claude Code Covert Marking Controversy: How AI Coding Tools Are Reshaping Enterprise Security Boundaries
Claude Code was revealed to steganographically mark system prompts under specific conditions, triggering a developer trust crisis. This article analyzes the steganography, Anthropic's tightening China access, and how AI coding tools became a core enterprise security issue.
Read more →
·3 min
Claude Code for Absolute Beginners: A Step-by-Step Guide (Install + Connect an LLM + Hands-On Practice)
How do complete beginners get started with Claude Code? This guide covers VS Code setup, two ways to connect an LLM in China, four core usage modes, and building your first practical tool without writing a single line of code.
Read more →
·2 min
Claude Code + Skills in Action: Auto-Generate Production-Ready Test Cases in 10 Minutes
A developer shares a test case automation solution built on Claude Code + Skills: encapsulating requirement splitting, test point extraction, and case generation into independent Skills. The full workflow takes under 10 minutes.
Read more →