cursor

The author shares a development workflow combining Claude Design with local AI agents (such as Cursor, Codex), and open-sourced the baoyu-design tool, allowing developers to run Claude Design locally for UI design without relying on the web version.

compound-engineering-plugin is an AI coding plugin that avoids technical debt by allocating 80% of resources to planning and review, and 20% to execution. It includes 37 skills and 51 agents, supporting three major platforms: Claude Code, Codex, and Cursor.

Cursor AI introduces Design Mode, allowing users to update their UI by pointing, drawing, or talking.

This article introduces the importance of backing up AI work history and promotes DataMoat, a local encrypted backup tool that helps users save interaction records and work processes with AI tools (such as Claude Code, Codex, Cursor).

Detailed walkthrough of Cursor's approach to training Composer 2: using Kimi 2.5 as the base, learning code knowledge through large-scale intermediate training, then large-scale RL to teach the model to write correct code in real environments, and using self-summarization to handle long contexts.

Awesome Rebuttal is an open-source project designed for papers in AI, NLP, robotics, and other fields. It helps authors analyze reviewer comments, plan supplementary experiments, and generate well-reasoned responses. It supports embedding into Cursor or Claude Code.

General README Skill is a skill pack designed for AI coding assistants like Claude Code, Copilot, and Cursor. It automatically scans projects and generates professional README files, supporting multiple tones, languages, and badge styles.

Cursor now allows users to publish canvases—apps like dashboards and internal tools—and share them via URL.

Ashby Engineering shares that over half of their production code is now AI-generated since August 2025 with no increase in customer issues or code quality regressions. The post outlines their philosophy that AI eliminates mechanical coding tasks while engineer judgment and empathy become more valuable.

Artificial Analysis launched a coding agent index that tests harness and model combinations separately, highlighting that benchmark tasks differ from real production needs. The article argues that teams should evaluate agent configurations on their own codebases and workflows rather than relying solely on standardized benchmarks.

Cursor introduces Debug Mode, which lets the AI agent instrument code, collect runtime logs, and fix bugs based on actual evidence instead of guessing, improving accuracy and handling hard-to-reproduce issues.

Uber is limiting employee token spending to $1,500 per month per AI coding tool, revealing real-world pricing and value assessment for AI assistance in software engineering.

The article criticizes the lack of transparency in AI token usage and pricing, arguing that providers like Claude and Cursor intentionally keep consumption vague to obscure costs and encourage upgrades.

Uber is capping employee spending on AI coding tools like Cursor and Claude Code at $1,500 per month per tool to manage costs, as reported by Bloomberg's Natalie Lung.

This article delves into the technical details such as asynchronous and sparse methods used in Cursor training Composer 2 model, and provides a comprehensive analysis of the RL infrastructure.

Cursor can now read documents attached in Slack threads, supporting formats like .txt, .log, .json, .zip, .pdf, and .docx.

Uber has implemented a monthly $1,500 cap per employee on AI coding tools like Claude Code and Cursor after exceeding its annual AI budget in just four months, highlighting growing AI cost concerns and ROI questions across the tech industry.

A developer shares a workflow using Cursor's Opus 4.8 Max Thinking model with subagent harness, and introduces a GitHub repository with installable skill files for AI coding agents, including a 'running-bug-review-board' skill that performs live QA testing.

A developer shares their workflow using Cursor's subagent harness with Opus 4.8 Max Thinking for long context understanding and implementing large features in Swift, emphasizing hands-on planning and phased acceptance testing.

Cursor introduces new Teams pricing with increased usage limits, a Premium seat for power users, and better spend controls.