Full-text search across 61857 articles. Combine with topic and date filters; results sorted by relevance.
AI engineering teams that apply artificial intelligence to collaborative workflows—such as requirements clarification, code review, and coordination—can achieve significant return on investment, according to data from Mc…
Video creator Matthew Berman proposed that AI agents using multimodal LLMs such as Claude 3.7 Sonnet could rebuild complex software like Photoshop by observing its behavior rather than accessing its source code, an appro…
Artie Shevchenko, in his talk at the Craft conference, argued that teams can maintain sustainable human code reviews in the AI era by skipping peer reviews on low-risk PRs and allowing code owners to rely on AI approvals…
Google launched the Gemini Enterprise Agent Platform to help IT leaders build, scale, and govern AI agents. The platform addresses challenges like tool fragmentation, data security, and cost management by providing a uni…
Spec-Driven Development (SDD) has gone mainstream in 2026 as a disciplined counterweight to 'vibe coding,' making precise executable specifications the source of truth while treating code as a generated artifact. The pra…
GitHits launched its public beta 0.9, a CLI and local MCP server that gives coding agents access to open-source code behind project dependencies. The tool indexes open-source code and documentation, allowing agents to se…
GitHub made AI Scan for pull requests generally available, a code scanning feature that complements CodeQL by finding vulnerabilities in pull request changes for languages and frameworks CodeQL does not currently cover, …
Slack launched Code Channels, a feature that brings coding agents and developers into a shared Slack channel, according to Slack general manager Rob Seaman, who discussed the product on a podcast episode. Seaman said mos…
The Ethereum Foundation conducted AI-powered security audits on smart contract code and discovered genuine vulnerabilities that would have been deployed to mainnet. This real-world validation demonstrates that AI agents …
Node.js Technical Steering Committee member Matteo Collina has proposed adding a built-in Virtual File System (VFS) to Node.js core via a new `node:vfs` module, introducing approximately 19,000 lines of code across 100 f…
Anthropic reports that over 80% of code merged into its codebase as of May 2026 was authored by Claude, up from low single digits before Claude Code's preview in February 2025. The company says Claude's success rate on o…
Developer imshaikot released render-visual-skill, an agent skill that lets coding agents generate diagrams, presentation slides, social cards, code snippets, and device mockups as HTML/SVG rendered to PNGs via headless C…
L3 Simulator, an open-source Node.js tool, orchestrates AI coding agents over GitHub issues by labeling issues `ready` to trigger automated planning, coding via Claude Code or Codex, and PR creation, while never merging …
A senior engineer argues that AI coding agents producing up to 12,000 lines of code in a few days have overwhelmed human code review, turning it into a bottleneck that can require splitting a single feature into 20-40 st…
A student developer documented a workflow for building full-stack applications by orchestrating AI coding agents through reusable Claude Code Skills and prompt templates rather than writing code line by line. The account…
A developer argues that while AI coding agents have become good enough since late 2025 that many developers no longer write code by hand, treating that as permission to stop reading the code is a mistake, especially in p…
Anthropic is adding a usage details button and a customization section for Claude Code to its Claude iOS app, giving Pro and Max plan subscribers visibility into their Claude Code allocation and more control over their m…
A four-hour stress test comparing Cursor, Claude Code, and Windsurf found that Cursor remains the most polished AI coding agent for most developers, while Claude Code excels at autonomous debugging in the terminal, and W…
A developer found that asking AI coding assistants to explain code in 'Simple Technical English' improved clarity, and traced the phrase to the ASD-STE100 Simplified Technical English standard, a controlled natural langu…
AI makes software architecture more valuable, not less, because while AI can generate code rapidly, it cannot determine where that code belongs in a system, according to a senior news editor. The bottleneck in software e…