Tagged articles
AI-assisted coding
64 articles · Page 1 of 1
Independent evaluator METR's 11-week audit of Anthropic found its model capability improvement speed doubled, with ~80% attributed to AI, but redacted internal data and narrow verification channels leave the true extent of AI-driven acceleration uncertain.
AI-assisted codingAI4AIAnthropic
0 likes · 8 min read

This article details a systematic refactoring of a chat assistant Android app, applying SRP, DIP, OCP, layered architecture, and naming conventions to eliminate god classes and tight coupling, while uncovering a JNI symbol mismatch bug that only appears at runtime, and sharing insights on AI-assisted coding limitations.
AI-assisted codingAndroid developmentJNI
0 likes · 18 min read


21CTONov 8, 2026 · Industry Insights
Cisco President Jeetu Patel gave 27-year-old former founder Padmanabhan Krishnamurthy unlimited AI tokens and a two-person team to rewrite 98% of the company's legacy code within 24 months, exemplifying a broader trend of hiring Gen Z talent for their AI-native mindset to challenge industry veterans.
AI tokensAI-assisted codingCisco
0 likes · 8 min read

This guide walks Java developers through the correct sequence for adopting GPT-6.1 Sol via Codex: first confirm model availability in ChatGPT Work or Codex clients, then select a subscription tier matching actual usage, and finally grant scoped, auditable project access with Git-backed guardrails and PR-style review loops.
AI-assisted codingCodexGPT-6.1 Sol
0 likes · 7 min read

This article analyzes Stack Overflow and Anthropic data to compare Python, TypeScript, and other languages for AI-assisted development, then guides language selection by use case — web, data, enterprise, mobile, games, systems — emphasizing project-driven learning over language debates.
AI-assisted codingAnthropic researchPython
0 likes · 10 min read

This article analyzes why ReAct is the dominant paradigm for industrial Code Agents, contrasting it with CoT, Plan-and-Execute, Multi-Agent, ReWOO, and LLMCompiler through a Pinduoduo interview case study, explaining how ReAct's think-act-observe loop with tool use and environmental feedback suits code debugging and exploration tasks while other paradigms serve as optional enhancements.
AI-assisted codingCode AgentLLMCompiler
0 likes · 25 min read

The author warns that relying on AI to learn new specifications and write code erodes the debugging intuition and mental models that only come from reading source code and struggling through problems, turning engineers into mere requirement providers.
AI-assisted codingFeat frameworkMCP specification
0 likes · 7 min read

Claude engineering lead Felix Rieseberg argues developers waste AI potential by manually shuttling tasks between prompts instead of designing closed-loop workflows where agents access full context, tools, and validation loops to independently complete complex engineering tasks.
AI agentsAI-assisted codingClaude
0 likes · 14 min read

Addy Osmani advises simplifying Claude Code prompts by stating goals and acceptance criteria, using cloud sessions for long tasks, auditing prompt bloat, and leveraging Projects for workflow management, as newer models like Opus 5.5 need less hand-holding.
AI-assisted codingAddy OsmaniClaude Code
0 likes · 8 min read


JavaGuideOct 29, 2026 · Artificial Intelligence
JetBrains has open-sourced ThinkRail, a lightweight IDE that wraps the Pi coding agent with a graphical workspace featuring git worktree isolation, Monaco editor, turn-by-turn code review, and spec-driven development via markdown documents, enabling developers to manage AI-assisted coding tasks more efficiently.
AI-assisted codingGit WorktreeJetBrains
0 likes · 12 min read

Alibaba Taotian's Tarot Pixel cuts design-to-code costs below 2 yuan by combining context engineering — exporting structured visual data from MasterGo — with a feedback loop that verifies generated code via screenshot diffs and render-tree comparisons, while a denoising pipeline reduces layer depth from 8–12 to 3–5 and a layout audit with 12 anti-patterns prevents overfitting.
AI-assisted codingAlibaba TaotianCost Optimization
0 likes · 5 min read

Anthropic's internal employment report reveals junior tech hires dropped from 27% to 9% as AI handles basic coding tasks, creating a paradox where companies demand judgment skills that entry-level work once built. The analysis includes productivity metrics, hiring shifts, and practical strategies for newcomers to develop expertise despite shrinking entry points.
AI employment impactAI-assisted codingAnthropic
0 likes · 15 min read


21CTOOct 14, 2026 · Backend Development
Linus Torvalds employed Claude Code to create an 8-patch series that removes a page-cache contention bottleneck for tiny concurrent reads, boosting 8-thread throughput from ~10M to ~32M reads/sec on a laptop, but the patches delay memory reuse via RCU grace periods and still have regressions, leaving them unmerged as of October 2024.
AI-assisted codingClaude CodeConcurrency
0 likes · 9 min read

The article analyzes GPT-6 Astra's impact on software development, arguing it shifts AI programming from generating code snippets to executing complete tasks, and outlines practical implications for Java teams including legacy system understanding, change verification, and documentation consistency, while advocating for structured task boundaries and empirical evaluation before adoption.
AI programmingAI-assisted codingGPT-6 Astra
0 likes · 6 min read

This article uses the ESC framework to analyze how AI-assisted coding shifts developer value from implementation speed to problem definition, system design, and verification, illustrating with an alert governance example and a 90-day plan to transition from code writer to system owner.
90-day transformationAI-assisted codingESC framework
0 likes · 17 min read

A comprehensive guide to 100 must-have IntelliJ IDEA plugins across 10 categories for IDEA 2026.2, featuring AI-assisted development tools, code quality plugins, efficiency boosters, framework integrations, database tools, UI themes, version control enhancements, testing utilities, DevOps plugins, and practical utilities, with detailed comparisons, IDE 2026.2 native feature replacements, installation best practices, and 2026 plugin market trends.
AI-assisted codingDeveloper ProductivityIDE configuration
0 likes · 34 min read

The article argues that creators of foundational software like Linux, Python, Redis, Nginx, and SQLite are true geniuses due to their exceptional abstraction skills and system-level boundary control, illustrated by real-world cases where their minimal, convergent designs outperform modern complex solutions, and warns that over-reliance on AI tools erodes deep system understanding essential for solving hard production issues.
AI-assisted codingLinuxPython
0 likes · 14 min read

This article identifies six categories of AI-generated PHP code that introduce critical security vulnerabilities—SQL injection, unsafe file uploads, weak type comparisons, payment logic flaws, dangerous function usage, and hardcoded secrets—and provides a practical checklist and prompt template to enforce production-grade safety before deployment.
AI-assisted codingPHPSQL injection
0 likes · 9 min read

The author tests Qwen 3.8 27B by generating a data-analysis tool in five minutes and a 12306-like booking page that looks real but lacks backend integration, while noting Cerebras acceleration hits 1950 tok/s but requires foreign payment.
12306AI-assisted codingCerebras
0 likes · 10 min read

This analysis of GPT-6 Astra explains its strength in chaining reasoning, coding, browsing, and documentation into continuous workflows, advises using its long context with clear goals and constraints, and recommends reserving it for complex multi-step tasks like cross-file refactoring rather than simple code generation.
AI-assisted codingDeveloper ProductivityGPT-6 Astra
0 likes · 3 min read

This guide covers Codex CLI installation, key slash commands (/init, /status, /permissions, /model, /review), automation flags (-C, -m, --add-dir, codex exec), and best practices for iterative AI-assisted coding with clear boundaries and verification loops.
AI-assisted codingCLI automationCodex CLI
0 likes · 6 min read

This article organizes 14 Claude Code commands into five practical development workflows—project context setup, session context management, execution mode selection, code review, and failure recovery—explaining when to use each command, common misuses, and why understanding workflows matters more than memorizing commands.
AI-assisted codingClaude CodeDebugging
0 likes · 17 min read


TonyBaiSep 13, 2026 · Backend Development
OpenAI's Habitat storage system evolved from a Python library to a distributed platform handling 70M requests/second for 1B users, with engineers detailing scaling challenges, asyncio tuning, connection pool fixes, and a 2-engineer Rust rewrite using Codex and GPT-5.5 that boosted CPU efficiency 6x and memory efficiency 15x.
AI-assisted codingCodexConnection Pooling
0 likes · 26 min read

The article evaluates GPT-6 Astra's shift from conversational AI to end-to-end task execution, highlighting its large context window and multi-step capabilities while emphasizing that precise task specification, constraints, and human verification remain essential for reliable results.
AI-assisted codingGPT-6 AstraModel Evaluation
0 likes · 4 min read

OpenAI Codex lead Tibo argues that developers shouldn't manage dozens of AI agents manually; instead, future systems should orchestrate tasks, maintain context, and only interrupt humans for high-risk decisions, turning programmers from supervisors into strategic deciders.
AI agentsAI-assisted codingCodex
0 likes · 11 min read

The article explores the growing gap between AI's rapid code generation and developers' slow comprehension, detailing the risks of unread AI code and introducing the /understand tool that creates interactive, line-anchored explanations to help engineers truly own AI-generated changes.
AI-assisted codingAI-generated codecode comprehension
0 likes · 12 min read

Anthropic's Dynamic Workflows for Claude Code let developers write JavaScript orchestration scripts that schedule dozens to hundreds of sub-agents in parallel, keeping intermediate results in script variables instead of context, enabling reproducible, observable, and reusable large-scale coding tasks like Bun's 750k-line Rust migration.
AI-assisted codingAgent OrchestrationBun
0 likes · 8 min read

Uncle Bob proposes a 5-agent Gauntlet pipeline (Specifier, Coder, Cleaner, Hardener, QA) with context isolation, externalized rules, recalibrated thresholds, and human oversight of architecture boundaries, enabling small-step iterations where agents prove correctness via mutation testing and CRAP metrics while humans govern module dependencies and review evidence packages.
AI-assisted codingCRAP metricGauntlet pipeline
0 likes · 8 min read

As AI accelerates code generation, delivery teams face a growing explanation gap: code runs but the reasoning behind changes is lost, making structured change documentation essential for traceability, review, and safe handover.
AI-assisted codingDevSecOpsNIST SSDF
0 likes · 14 min read


TonyBaiAug 14, 2026 · Artificial Intelligence
The article analyzes Google’s blog post that argues AI shifts software‑engineering bottlenecks from code generation to code review, and explains why Go’s readability‑first design, strong static typing, comprehensive toolchain, and long‑term compatibility make it especially suited for AI‑assisted programming, while also summarizing the heated Hacker News debate.
AI-assisted codingGoToolchain
0 likes · 18 min read

This article traces Claude Code agent interactions to reveal how natural language queries are converted into search commands via agentic tool-driven loops, highlighting the impact of tool configuration and LLM reasoning quality on code location accuracy.
AI-assisted codingAgentic LoopClaude Code
0 likes · 5 min read


TonyBaiAug 1, 2026 · R&D Management
As AI tools increasingly generate code, engineers must still decide when to write a design document, how detailed it should be, and what essential sections to include—project scope, requirements, technical solution, risk, and collaboration trace—to ensure sound decisions and effective reviews.
AI-assisted codingDesign Documentarchitecture documentation
0 likes · 18 min read

The article critiques the five fatal flaws of the emerging Vibe Coding paradigm, explains the Specification‑Driven Development (SDD) methodology—including its principles, three‑phase workflow, tool ecosystem, and integration with AI agents—and promotes the first Chinese book that details this approach.
AI-assisted codingAgent IntegrationSDD workflow
0 likes · 12 min read

The article analyzes how AI programming tools disrupt CRUD developers, predicts reduced demand for pure execution roles, and outlines three career directions: becoming AI-enhanced engineers, deepening business domain expertise, and advancing toward system architecture, arguing that value shifts from coding speed to problem-solving with AI.
AI programmingAI-assisted codingCRUD developers
0 likes · 7 min read

This article details how the usb-driver-dev Skill for OpenCode reduces HarmonyOS USB-HID peripheral driver adaptation from 2-3 weeks to 1-2 days by combining knowledge injection, template reuse, and automated compile-fix loops, demonstrated through a 10-step workflow for a drawing tablet.
AI-assisted codingDriver DevelopmentHDF Framework
0 likes · 15 min read

The article argues that mastering Spec‑Driven Development, especially when collaborating with AI, solves most programming problems, improves code‑generation accuracy, and makes the overall development workflow smoother than chasing countless AI‑generated code tweaks.
AI-assisted codingSpec-Driven DevelopmentVibe Coding
0 likes · 8 min read

Anthropic’s Q2 2026 internal review shows Claude Code boosting daily merged code lines eight‑fold, yet this surge uncovers new bottlenecks in verification, responsibility tracing, and collaboration, prompting a systematic redesign of engineering processes.
AI-assisted codingClaude Codeagent workflow
0 likes · 14 min read

The article analyses the rise of Vibe Coding, its hidden entropy costs for teams, and proposes Spec‑Driven Development (SDD) as a deterministic, context‑engineered alternative, detailing its philosophy, lifecycle, tooling ecosystem, practical adoption steps, and metrics for measuring engineering productivity.
AI-assisted codingSpec-Driven DevelopmentVibe Coding
0 likes · 32 min read

The author documents a 7.5-hour experiment using AI-assisted coding with Tencent's Kuikly cross-platform framework to build a multimodal AI chat app for Android, iOS, and HarmonyOS, detailing component selection, custom module creation, debugging via logcat, and iterative UI polishing, demonstrating how AI + Kuikly eliminates cross-platform duplication and boilerplate.
AI-assisted codingCodeBuddyCross-platform Development
0 likes · 19 min read

In just 7.5 hours, the author used AI‑assisted Kuikly to generate a fully functional multimodal chat application for Android, iOS and HarmonyOS—producing about 3,500 lines of code from 28 conversational rounds, supporting text, images, markdown rendering, SSE streaming, and local session management without writing a single line manually.
AI-assisted codingKotlin MultiplatformKuikly
0 likes · 16 min read

This article explains why Vibe Coding reaches its limits for large projects, introduces Spec‑Driven Development with OpenSpec, walks through installing the tool, using its opsx commands, creating specification documents, applying code generation, and archiving the results in a Spring Boot 3.5.0 application.
AI-assisted codingOpenSpecOpsx commands
0 likes · 12 min read

OpenSpec adds a specification layer to existing codebases, offering a pure, brownfield‑friendly, tool‑agnostic approach where specs act as contracts, changes become first‑class citizens, and incremental Delta Specs replace full‑spec rewrites, with detailed workflows, design insights, limitations, and a side‑by‑side comparison to Spec‑Kit.
AI-assisted codingBrownfieldDelta Spec
0 likes · 17 min read


21CTOJun 16, 2026 · Industry Insights
The article analyzes how AI‑assisted “Vibe Coders” focus on rapid prototype creation while software engineers prioritize full‑lifecycle responsibilities, proposing a new “safe‑merge time” metric to evaluate code quality, discussing responsibility boundaries, context awareness, appropriate use cases, and the impact on junior developers.
AI-assisted codingcode reviewdevelopment workflow
0 likes · 12 min read

This article walks through a real‑world project where Claude Code is used to initialize a CLAUDE.md contract, integrate a Milvus database SDK, generate table schemas, clear AI context, manage Git worktrees, and automate unit testing and bug fixing, demonstrating significant efficiency gains.
AI-assisted codingClaude CodeGit Worktree
0 likes · 8 min read

The article details Minsheng Bank's exploration of Spec‑Driven Development (SDD) using the CodeAgent tool within a private‑domain Cloud IDE, outlining the challenges of AI‑assisted coding in banking, the multi‑level specification framework, practical outcomes, limitations, and future enhancements.
AI-assisted codingBanking softwareCodeAgent
0 likes · 16 min read

OpenSpec introduces a Spec‑Driven Development workflow that aligns requirements, design, and implementation before any code is written, using structured proposals, delta specs, and AI‑generated tasks to drive backend feature creation, iteration, and archiving through concise CLI commands.
AI-assisted codingBackendCLI
0 likes · 12 min read


UbuntuApr 15, 2026 · Industry Insights
After months of heated debate, the Linux kernel maintainers released a three‑rule policy that permits AI‑assisted code contributions while insisting that human developers sign off, label the AI origin, and bear full responsibility for any bugs, security flaws, or licensing issues that arise.
AI PolicyAI-assisted codingLinux
0 likes · 13 min read

JetBrains AIR is a new AI‑native IDE that embeds artificial intelligence as the default workflow, offering macOS installation, project opening, AI‑driven task definition, execution, review, parallel task handling, and advanced MCP server integration, all while keeping developers in control of code changes.
AI IDEAI-assisted codingIDE tutorial
0 likes · 7 min read

The article details a practitioner’s method of using Claude Code and spec‑driven development to plan, prototype, and deploy modular serverless stacks on AWS, highlighting the benefits of early specification, AI‑assisted coding, context‑window limits, and iterative testing for reliable software engineering.
AI-assisted codingAWSClaude Code
0 likes · 16 min read


XikeMar 20, 2026 · Fundamentals
This guide walks you through Cursor AI’s advanced configuration—covering core features, custom Rules, the Model Context Protocol (MCP), user‑defined Commands, and switchable Modes—while showing practical Spring Boot and refactoring cases and quantifying efficiency gains.
AI-assisted codingConfigurationCursor AI
0 likes · 10 min read


ArchitectFeb 24, 2026 · Artificial Intelligence
Boris Tane, former founder of Baselime and Cloudflare Workers observability lead, shares a disciplined eight‑step workflow that lets architects harness Claude Code while preventing costly system‑breaking AI‑generated code, by making every AI contribution explicit, reviewed, and anchored to documented architectural decisions.
AI-assisted codingClaude Codecode review
0 likes · 18 min read

Anthony Fu, a Vue core team member, released the antfu/skills GitHub repository—a curated collection of AI agent skills split into opinionated personal presets and up‑to‑date official documentation, enabling shared, on‑demand prompts for Vue, Nuxt, Vite, and related tools.
AI-assisted codingGit submodulesNuxt
0 likes · 5 min read

The author reflects on code taste in the AI era, sharing three core principles from 'Code Complete 2' and 'Hackers & Painters': code form should mirror the problem, programmers should think before expressing in a language, and interfaces have both programmatic and semantic parts.
AI-assisted codingClean CodeCode Complete
0 likes · 5 min read

A junior developer shares the full lifecycle of creating "Gege Check-in," a HarmonyOS habit-tracking app that won Huawei's 2025 developer incentive, detailing architecture, AI-assisted coding, DevEco Studio workflows, calendar component integration, privacy-first local storage, and the monthly active user targets required to claim the reward.
AI-assisted codingArkTSDevEco Studio
0 likes · 9 min read

CodeGenie, HarmonyOS's AI coding assistant, now generates compilable ArkTS UI code from screenshots in ~2 minutes using a parse-then-generate architecture with VLM element detection and LLM agents, achieving 85%+ parsing accuracy, near 100% preview rate, and 40% adoption across food, travel, shopping, news, and education apps.
AI-assisted codingArkTSCodeGenie
0 likes · 14 min read

This article walks through VibeCoding’s immersive AI‑driven workflow, showing how to craft detailed prompts, use ByteDance’s Trae IDE to iteratively generate and refine a two‑page HTML/CSS/JS resume web page, add PDF export, dynamic sections, and achieve a polished final product.
AI-assisted codingFrontend DevelopmentResume generator
0 likes · 15 min read

The article explains that AI acts as an amplifier for software engineers, showing that solid coding fundamentals and precise prompts dramatically boost AI‑generated output, illustrated with prompt comparisons, tooling tactics, and a real‑world PostgreSQL optimization case, while emphasizing disciplined practices to avoid low‑quality code.
AI-assisted codingLLM ToolsPython
0 likes · 17 min read

The guide shows how Cursor IDE’s Project Rules let AI automatically generate reusable code for adding new data sources, cutting development time from days to hours, with near‑100% success across two validation methods, and suggests broader rule design could boost productivity even further.
AI-assisted codingCursor IDEautomation
0 likes · 5 min read

This article shares a practical experience of integrating the Cursor AI code assistant into a front‑end development workflow, outlining expectations, the shift from planning to execution, current pain points, a collaborative feedback loop, and concrete scenario applications such as status analysis, change planning, and impact evaluation.
AI-assisted codingCursor AIFrontend Development
0 likes · 13 min read

The author shares practical experiences and reflections on using AI tools like Cursor and Claude 3.7 to develop a web application, highlighting the growing importance of demand analysis, workflow integration, and the nuanced impact of AI on software engineering jobs.
AI-assisted codingClaude 3.7Cursor
0 likes · 5 min read


ByteFEMar 12, 2025 · Frontend Development
This comprehensive technical guide explores how to leverage AI-powered coding assistants like Cursor to efficiently generate high-quality unit tests for modern frontend applications, detailing essential frameworks, structural patterns, and practical optimization techniques.
AI-assisted codingCursorReact Testing
0 likes · 26 min read

The article explains why unit tests shorten the development‑validation cycle, introduce the concept of atomic correctness to reduce debugging scope, and shows practical ways—especially with AI assistance and tools like Vitest—to eliminate the cold‑start friction of writing tests.
AI-assisted codingGoTypeScript
0 likes · 10 min read

This article walks through a real‑world Pandas solution that calculates each merchant's total orders and first‑order counts to reveal which merchants are most popular among new customers, using AI‑assisted code generation and step‑by‑step explanation.
AI-assisted codingPandasPython
0 likes · 6 min read

This article explores how generative AI (AIGC) is reshaping front‑end engineering by shifting paradigms from imperative to declarative, then to an AIGC‑driven workflow, and offers practical examples, tool comparisons, and strategic advice for the next‑generation front‑end developer.
AI-assisted codingAIGCdeclarative programming
0 likes · 18 min read
