Best of AI Coding — 2025

  1. 1
    Article
    Avatar of hnHacker News·37w

    Doomscrolling: The Game

    A developer created a browser-based game called 'Doomscrolling' where players navigate through a Doom-inspired world using only scroll gestures. The project evolved from a failed attempt with GPT-4 to a successful implementation with GPT-5, incorporating real-time news headlines from RSS feeds as in-game elements. The development process showcased AI-assisted coding techniques, including creating standalone 'labs' for testing visual elements and using computational rendering instead of pre-made sprites.

  2. 2
    Article
    Avatar of vibecodingVibe Coding·44w

    Supercharging Claude Code

    A comprehensive setup guide for optimizing Claude Code beyond basic installation. Covers essential prerequisites including Claude Pro subscription, enhancement tools like SuperClaude and Claudia, project-specific CLAUDE.md files for context, Model Context Protocols (MCPs) for extended functionality, agents for specialized prompts, and best practices for effective collaboration with the AI assistant. Emphasizes treating Claude Code as a tool requiring proper guidance rather than an autonomous code wizard.

  3. 3
    Article
    Avatar of ergq3auoeReinier·46w

    Claude Code UI

    Claude Code UI provides a desktop and mobile interface for Anthropic's Claude Code CLI tool, enabling developers to manage AI-assisted coding projects and sessions through a graphical interface instead of command-line interactions. The tool works both locally and remotely, offering the same functionality as the CLI with improved accessibility across different platforms.

  4. 4
    Video
    Avatar of fknightForrestKnight·47w

    My Linux Ubuntu Setup for Software Development

    A developer shares their Ubuntu 24.04 setup using Omakub, a development configuration by DHH. The setup includes multiple workspaces, tiling window management, and various AI-powered coding tools like Zed, VS Code with Augment, and Warp terminal. The configuration emphasizes productivity through workspace organization and AI assistance while maintaining traditional development workflows with IntelliJ for Java and multiple browsers for testing.

  5. 5
    Article
    Avatar of collectionsCollections·44w

    Anthropic Introduces Weekly Rate Limits for Claude Code Subscribers

    Anthropic has implemented weekly rate limits for Claude Code subscribers starting August 28, 2025, affecting both Pro and Max tiers. The new structure operates on 5-hour rolling sessions with weekly quotas impacting less than 5% of intensive users. Most users receive 140-280 hours of Sonnet 4 and 15-35 hours of Opus 4 weekly, while Max subscribers can access higher tiers at $100-200/month. The changes have drawn criticism from developers who feel legitimate power users are penalized, though Anthropic cites system reliability and policy violation prevention as reasons for the restrictions.

  6. 6
    Article
    Avatar of aiAI·51w

    Cursor on mobile is coming

    Cursor, the AI-powered code editor, is expanding to mobile platforms. This development would bring AI-assisted coding capabilities to smartphones and tablets, potentially enabling developers to code and edit projects on the go.

  7. 7
    Article
    Avatar of lobstersLobsters·50w

    Cursor YOLO deleted everything in my computer

    A developer experienced a critical bug with Cursor's YOLO mode that resulted in the deletion of all files on their computer during a backend migration from Express.js to Next.js. The AI editor attempted to delete old files, failed initially, then proceeded to delete everything including itself. Data recovery attempts using EaseUS were unsuccessful, though the developer had backups on Google Drive and GitHub.

  8. 8
    Article
    Avatar of codewithandreaCode with Andrea·48w

    Build Flutter Apps FASTER with Claude Code Opus 4

    Claude Code Opus 4 was used to build a voice-activated timer Flutter app from scratch, demonstrating AI-assisted development workflow. The project involved native integrations like speech recognition and permissions, showcasing both strengths and limitations of AI coding tools. Key success factors include writing detailed requirements, using structured planning, actively reviewing generated code, and leveraging the most powerful AI models available. The workflow emphasizes breaking down complex tasks, maintaining context through documentation, and combining AI assistance with manual oversight for production-ready results.

  9. 9
    Video
    Avatar of indentlyIndently·49w

    I'm a huge Zed fan

    A developer shares their experience switching from PyCharm to Zed editor after 2 months of use. They highlight Zed's superior performance on older hardware, smooth user experience, and easy JSON-based configuration. Key features discussed include the new debugger, custom snippets, multi-language support, and integrated AI capabilities. The switch was motivated by PyCharm being overkill for simple development tasks, while Zed provides a lightweight yet feature-rich alternative with excellent customization options.

  10. 10
    Article
    Avatar of theregisterThe Register·40w

    AWS CEO says AI replacing junior staff is 'dumbest idea'

    AWS CEO Matt Garman argues that replacing junior developers with AI is counterproductive, emphasizing that junior staff are cost-effective and naturally adept with AI tools. He warns that eliminating entry-level positions would create a knowledge gap in the future workforce. Garman advocates for using AI as a collaborative tool rather than a replacement, criticizing the metric of measuring AI value by lines of code generated. He recommends focusing education on critical thinking, problem decomposition, and learning skills rather than narrow technical abilities to prepare for rapid technological change.

  11. 11
    Video
    Avatar of t3dotggTheo - t3․gg·27w

    Google just dropped their Cursor killer (FREE Gemini 3 Pro???)

    Google released Anti-gravity, a free AI-powered IDE built on VS Code that integrates Gemini 3 Pro. The editor features an innovative agent manager workflow that operates as a separate window, browser control capabilities through Chrome integration, and automatic asset generation. While the tool shows promise with successful one-shot project creation and unique UX patterns for managing multiple tasks, it suffers from numerous bugs including broken extensions, inconsistent performance, and UI glitches. The editor appears to be based on Windsurf code from Google's recent acquisition, offering generous free usage limits during its preview period.

  12. 12
    Article
    Avatar of ergq3auoeReinier·43w

    Cursor AI Complete Guide (2025): Real Experiences, Pro Tips, MCPs, Rules & Context Engineering

    A comprehensive guide covering Cursor AI, an AI-powered code editor, including setup instructions, advanced features like Model Context Protocols (MCPs), configuration rules, and context engineering techniques. The guide includes real-world experiences and professional tips for maximizing productivity with AI-assisted development, plus a practical example of building an AI SaaS application for automated newsletter generation.

  13. 13
    Video
    Avatar of youtubeYouTube·44w

    Claude Engineer is INSANE... Upgrade Your Claude Code Workflow

    Two free tools can significantly enhance Claude Code workflows: Super Claude, a configuration framework that adds 18 structured commands with development personas and flags for different stages of the software development lifecycle, and a web-based GUI that enables browser access to Claude Code from any device on the same network. Super Claude provides pre-built workflows for frontend, backend, security, and architecture tasks, while the web GUI offers cross-device accessibility for remote coding sessions.

  14. 14
    Video
    Avatar of codetothemoonCode to the Moon·27w

    Zed the IDE (Yes, I tried Cursor & Antigravity)

    A hands-on review of Zed IDE exploring its performance advantages, AI coding capabilities, and unique approach to agentic development. The editor is built in Rust for speed and memory efficiency, supports Vim motions, and implements the Agent Communication Protocol (ACP) for integration with external coding agents like Claude Code and OpenCode. Key features include 120fps rendering, real-time collaboration tools, and flexible AI provider options including local inference with Ollama. The review compares Zed's architecture to Electron-based editors like VS Code and Cursor, noting the performance trade-offs and discussing the $10/month Zed Pro subscription value proposition.

  15. 15
    Article
    Avatar of zedZed·47w

    Why I'm Dialing Back My LLM Usage — Zed's Blog

    A seasoned software engineer with 15 years of experience shares his honest reflection on using LLMs in production code. After initially embracing AI tools with enthusiasm, he encountered significant challenges including poor code quality, cascading bugs, and productivity illusions. He advocates for a more measured approach where developers maintain architectural control and use LLMs only for small, well-scoped tasks like refactoring rather than large features. The key insight is treating LLMs as assistants rather than replacements, emphasizing that senior developers should trust their skills and use AI to leverage existing knowledge rather than offload critical decision-making.

  16. 16
    Article
    Avatar of javarevisitedJavarevisited·43w

    Top 5 Udemy Courses to Learn Claude Code and Claude AI in 2025

    Claude AI and Claude Code are emerging as powerful tools in the AI development stack, created by Anthropic with a focus on safety and natural language understanding. Claude Code enables developers to write production-ready code through conversational prompts and automate workflows with AI agents. The article curates five Udemy courses covering different aspects: from basic Claude Code usage and full-stack AI development to advanced agent building with frameworks like LangChain, CrewAI, and AutoGen. These courses cater to various skill levels and use cases, from beginners learning AI-assisted coding to experienced developers building complex autonomous agents.

  17. 17
    Article
    Avatar of zedZed·41w

    Why LLMs Can't Really Build Software — Zed's Blog

    Large Language Models excel at writing code but struggle with the iterative mental modeling that defines effective software engineering. While LLMs can generate code and update it when given specific problems, they cannot maintain clear mental models of requirements versus implementation, leading to confusion when tests fail or debugging is needed. Current models suffer from context omission, recency bias, and hallucination issues that prevent them from understanding complex software systems. For non-trivial projects, human engineers must remain in control, using LLMs as tools while maintaining responsibility for requirements clarity and code verification.

  18. 18
    Article
    Avatar of communityCommunity Picks·51w

    Claude Code is My Computer

    A developer shares their experience using Claude Code with full system permissions for two months, demonstrating how it transformed their workflow from simple coding assistance to complete system automation. The setup handles everything from content migration and code commits to system configuration and machine setup, saving approximately an hour daily despite potential security risks.

  19. 19
    Article
    Avatar of matkladmatklad·39w

    Vibe Coding Terminal Editor

    A developer shares practical lessons learned from building a VS Code terminal editor extension using Claude AI. Key insights include using a plan.md workflow for structured LLM interactions, treating specs/code/tests as interchangeable formats, and the critical importance of fast, end-to-end testing for AI-assisted development. The author emphasizes that while LLMs excel at code generation, they require proper feedback loops and human oversight in the control plane rather than data plane.

  20. 20
    Article
    Avatar of architectureweeklyArchitecture Weekly·42w

    Requiem for a 10x Engineer Dream

    A developer's critical examination of AI coding tools like Claude Code reveals that promised 10x productivity gains are largely overstated. Despite detailed specifications and careful prompting, the author found that effective use requires such micromanagement that you're essentially programming in Markdown rather than saving time. The tools struggle with autonomous problem-solving, often generating overcomplicated solutions and requiring constant supervision. The experience parallels failed promises of past code generation tools, suggesting that the real challenge in software development isn't specification but discovering what to build while building it.

  21. 21
    Article
    Avatar of medium_jsMedium·44w

    The problem with Claude Code and Cursor: The AI Coding "Death Spiral"

    AI coding assistants like Claude Code and Cursor often create a "death spiral" where fixing one error leads to multiple new problems. This happens because LLMs are pattern-matching machines that confidently generate plausible but incorrect solutions. The author proposes teaching AI assistants better principles by encoding timeless software wisdom (like Rich Hickey's "Simple Made Easy") into specific rules. By creating a simple-mindset.md file with actionable guidelines, developers can transform their AI's behavior from generating complex, intertwined solutions to building simple, maintainable code that actually works.

  22. 22
    Video
    Avatar of t3dotggTheo - t3․gg·46w

    Everyone’s mad at Cursor right now

    Cursor recently changed its pricing model from 500 requests per month for $20 to a credit-based system with $20 of API usage, causing user backlash due to poor communication. Many users experienced unexpected charges when the new pricing kicked in without clear warnings. The change reflects broader industry trends as AI coding tools move away from loss-leader pricing to more sustainable models that reflect actual API costs. While Cursor's value proposition remains strong, the lack of transparency in usage tracking and billing has created uncertainty among users about when they'll hit limits or incur additional charges.

  23. 23
    Video
    Avatar of webdevcodyWeb Dev Cody·51w

    Cursor just got a major update

    Cursor 1.0 introduces several major features including background agents that can perform concurrent code refactoring tasks, bugbot for automated code review in pull requests, memory functionality to learn coding preferences, and enhanced MCP tool integrations. The background agent feature allows developers to delegate smaller tasks while focusing on main work, though it uses expensive premium models. Bugbot automatically reviews pull requests for potential issues, while the memory system learns individual coding preferences per project.

  24. 24
    Article
    Avatar of hnHacker News·42w

    Claude Code Is All You Need

    Demonstrates 'vibe coding' - creating software by chatting with AI models without directly writing code. Shows how Claude AI generated a working SplitWise clone from a single 500-word specification, comparing a successful 900-line PHP implementation against a broken Node.js version with 500MB of dependencies. Highlights the importance of prompt quality and technical constraints when using AI for code generation.

  25. 25
    Article
    Avatar of graphitedevGraphite.dev·44w

    How I got Claude to write code I could actually ship

    Claude Code can generate thousands of lines of code quickly, but large AI-generated PRs are difficult to review safely. The solution is teaching Claude to create stacked pull requests using Graphite's gt CLI, breaking complex features into smaller, focused, reviewable chunks. By adding specific instructions about stacking workflows and requiring Claude to plan its approach before coding, developers can make AI-generated code more manageable and shippable. The GT MCP tool helps align Claude's internal planning with actual PR structure.

See all AI Coding archives