Full-text search across 56294 articles. Combine with topic and date filters; results sorted by relevance.
Meta took Muse Code out of beta on August 31st, adding cross-session messaging, workflows for coordinating teams of subagents, and monthly subscriptions starting at $5, 26 days after its beta launch. The release also put…
David Gomes, a software engineer, published a blog post explaining how Git worktrees and coding agents such as Cursor, Codex, Claude Code, and Pi interact, noting that worktrees are essential for parallelizing AI-assiste…
Harness introduced Agent-Ready Harness Code Repository and AI Code Review, a source code management and review system designed for AI coding agents, featuring agent-specific permissions, MCP and CLI support, and AI Check…
An engineer at Snappfood discusses how AI is transforming code review processes in large engineering teams. The engineer notes that AI-generated code increases pull request sizes and speed, but emphasizes the need for en…
RedMonk's analysis of 15 open source projects found that AI-authored code, identified by machine-readable markers such as 'Co-authored-by: Claude' or agent authorship, is increasing, though the exact percentage of AI-wri…
Nick, a developer using Anthropic's Claude Code, refactored his AI-assisted development workflow by converting prose-based coding standards into deterministic ESLint lint rules, reducing reliance on probabilistic AI for …
AI agents now generate code at ten times human speed, but the cost of verifying and maintaining that code has skyrocketed, leading to compounding technical debt. The industry is shifting from 'vibe coding' to 'agentic en…
AI-generated code is neither inherently good nor bad, but rather acts as a "mirror" that amplifies the skill level of the programmer using it. While skilled developers can use AI to produce better code faster by handling…
Kilo Code, an open-source AI coding agent for VS Code, JetBrains IDEs and the CLI, was last updated in September 2026 and offers access to more than 500 models at the provider's rate with no markup. The TypeScript projec…
A September 15, 2026 arXiv paper demonstrates that poisoned benchmarks can induce self-modifying AI coding agents to write vulnerable code on clean, held-out tasks, with Hyperagents powered by Sonnet 4.5 self-evolving in…
ByteByteGo is hiring a part-time instructor for its live, cohort-based course 'Write Production Grade Code with AI', which teaches software engineers to reliably ship production-grade software using AI coding agents. The…
Boris Cherny, the creator of Anthropic's Claude Code, told Fortune's Brainstorm Tech conference that he has not written a line of code by hand in eight months and now runs thousands of Claude Code agents overnight, with …
GitHub Copilot's widespread adoption is creating two distinct failure modes in software development: junior engineers are delivering code they don't understand, while senior developers are rubber-stamping AI-generated co…
A developer comparison of OpenAI Codex and Anthropic's Claude Code finds both tools priced at $20 and $200 per month but built differently: Codex bundles into ChatGPT with GPT-5 and o3 models, while Claude Code is a term…
Two September 2026 studies found that a coding agent's harness — everything except the model — changes cost far more than task success on strong models with large context windows. The UC Berkeley HarnessTax study, from a…
An analysis of C/C++ source code published by Shape of Code found that the 80-character line-length break-point remains visible in 2026 data, though less dramatic than in 2000, with a new break-point emerging at 120 char…
A developer's June 22, 2026 journal entry reports that Claude Code produced about 95% of the code at his workplace, with gpt-5.5 writing the remaining 5% and the author writing less than 1%. The author vibe-coded a mobil…
Ponytail, a coding skill that makes AI agents write less code, cut code volume by 80-94%, cost by 42-75%, and time by 3-6x in benchmarks published in its GitHub repository, according to the project's own test results. On…
Roo Code outperforms Cline in developer efficiency, cutting approval wait times from 12 minutes to under two minutes per session through auto-approval of read-only operations, according to a three-month comparison by an …
Inplan, an open-source interactive planning editor for AI-assisted software development, introduces Planning-Driven Development (PDD) to help coding agents and humans collaborate on a versioned Markdown spec before code …