Full-text search across 57190 articles. Combine with topic and date filters; results sorted by relevance.
A developer recounts taking over four web apps generated by Figma Make and developing them with Claude Code, noting that the generated code is a projection of the design with exact-pinned dependencies and no data layer. …
Actualis, a new open-source tool from Digital Foundry, reads coding-agent session logs on a user's machine to report shell commands, credential exposure, refused tool calls, and per-project costs across Claude Code and C…
JetBrains has released Junie Local, an on-device version of its AI coding agent that runs entirely on supported Macs without cloud inference or token charges. The tool uses a JetBrains-tuned, 4-bit quantized Qwen3.6-27B …
Atlassian announced Code Context on August 12, a new capability in its Teamwork Graph that indexes GitHub and Bitbucket repositories and integrates with Jira, Confluence, and 50-plus third-party tools, enabling AI coding…
A developer examined AI-generated code in real GitHub repositories and found recurring structural problems, including silent error handling, untyped parameters, and hardcoded values, regardless of the tools or teams used…
Claude Code, Anthropic's CLI tool, enables AI agents to directly edit files, run commands, and refactor code in the terminal, offering a workflow distinct from IDE plugins like Cursor or Copilot. In a hands-on test, a de…
Claude Code's auto mode became the default on Pro, Max, and Team plans today, but a pseudonymous researcher published a bypass two days early that hid instructions in an image and succeeded in 6 of 10 trials. Anthropic r…
A developer argues that comparing AI coding tools by autocomplete quality is a mistake, as tools like Cursor, Windsurf, Claude Code, GitHub Copilot, Replit Agent, and CodeGeeX operate in different environments. The post …
RemObjects Software, the maker of CodeBot for Delphi, published a guide outlining critical questions businesses should ask when evaluating AI coding tools, covering commercial terms, source code safety, and practical val…
AI code review tools save 20-30% of review time when used correctly, according to a developer who ran AI-assisted reviews on real pull requests for about a year. The developer found that AI reviewers flag style issues an…
Developer Geir Isene reimplemented an X Server in assembly for the Frame project, not to replace X.Org but to understand how the system works. In an era where AI can generate code, the scarce skill is understanding syste…
Anthropic admitted that engineering missteps caused a monthlong decline in Claude Code performance, affecting paying users who reported the tool as less capable and more expensive to use. The company's April 23 postmorte…
Dex Horthy, founder of HumanLayer, has outlined a four-gate software development workflow—Product, Architecture, Program Design, and Vertical Slices—designed to make critical decisions before code is written. The workflo…
Prompt engineering for AI coding requires shifting from vague requests to precise specifications using an 'Anchor and Constraint' framework, according to a developer who tested workflows on Claude 3.5 Sonnet and Cursor. …
Claude Code CLI outperforms Cursor for systemic refactors by autonomously executing shell commands and running tests, while Cursor remains superior for UI work and visual diffs. The author recommends a hybrid workflow us…
Alibaba open-sourced its internal AI code review tool, Open Code Review (OCR), under Apache-2.0 after two years of use, claiming it served tens of thousands of developers and flagged millions of defects. The tool's hybri…
A director of engineering argues that after the cost of producing code collapsed with the introduction of LLMs, about half of traditional engineering management rules rest on broken assumptions. The author warns that cla…
A developer automated their daily morning health check for a Claude Code setup using launchd, consolidating production HTTP probes, hook latency, launchd exit codes, API costs, and git status into a single Markdown file …
Cursor and Windsurf, both built on VS Code, differ fundamentally in their approach to AI-assisted coding: Cursor focuses on high-accuracy codebase indexing and multi-file edits via Composer, while Windsurf emphasizes age…
GitHub announced that Copilot code review now reads custom instructions from the head branch of pull requests, supports additional instruction files (REVIEW.md, GEMINI.md, CLAUDE.md), and allows custom setup steps via a …