Full-text search across 57582 articles. Combine with topic and date filters; results sorted by relevance.
Vibe coding lets non-engineers build working prototypes from natural-language prompts, but moving those applications into production exposes operational complexity that AI does not eliminate, according to a first-person …
Microsoft Research researchers Minseon Kim, Zhengyan Shi and colleagues present FrogNano, a 4B coding agent post-trained exclusively with reinforcement learning on about 1,500 software engineering environments using synt…
A developer guide published by Mariana Souza on Sourcefeed demonstrates how to build a two-subagent refactor pipeline in Claude Code 2.1.263, using a read-only scout and a surgeon subagent behind a /refactor command that…
James Komo released config-drift-checker, an open-source tool that tests Claude Code setups—CLAUDE.md, skills, and hooks—against a pinned baseline on every pull request and canaries new model and Claude Code releases, op…
Developer Harry Philippe Mbouyap has released an open-source project that provides a three-layer safety system for giving Claude Code real autonomy without risking system damage. The approach combines permission settings…
CodeRabbit, an AI code review company, raised $143 million in a Series C round, valuing it at $1.5 billion, and launched Agentic Change Management (ACM) to address the surge in AI-generated code. GitHub processes 275 mil…
Hycu has made backup for Azure DevOps generally available, citing the rise of AI agents that commit code around the clock as a reason why Git repositories now require protection every 30 minutes rather than daily. The co…
Bash, the Unix shell, is the most effective interface for coding LLMs because it grants models access to the entire ecosystem of command-line tools with zero integration cost, according to a technical essay. The author a…
DeepSeek V3 outperformed Claude 3.5 Sonnet in a six-hour coding stress test, achieving 95% logic accuracy versus 92% for Claude, while costing about $0.28 per 1k tokens compared to Claude's $15.00, according to a develop…
A developer argues that memory servers for AI agents, such as those built on the Model Context Protocol (MCP), are designed to store conversational context, not code knowledge. The post highlights that MCP lacks a memory…
A developer used AI to build an Instagram automation bot and found that while the generated code worked, it required significant engineering review to be production-ready. The developer emphasizes that AI accelerates pro…
Developer jystervinou released Claude Code Arcade, a tool that runs animated 80s-style arcade games such as Ms. Pac-Man and Frogger in the Claude Code status line, driven by Claude's activity. The tool, available via a G…
A developer who used Claude Code to build a .NET invoicing library discovered that the AI-generated tests passed while the code was still wrong, failing to catch a rounding bug that would have mispriced common UK invoice…
Developer lennney released Stop That Shit 0.1.0, an open-source guard that blocks coding agents like Codex, Claude Code, OpenCode, and Hermes Agent CLI from performing unrequested defensive work such as generating SHA-25…
Anthropic's Claude Code running Opus 5 in Auto Mode can be tricked into executing attacker-controlled code up to 80 percent of the time by asking it to summarize a malicious website, according to researcher Johann Rehber…
VS Code 1.135, released August 26, introduces the Agent Host Protocol (AHP), external agent sessions, and a new 'Rubber Duck' feature that pairs a second AI model to review the primary agent's work. The AHP runs agents i…
XAI released Grok Build v1.0 on August 7, a terminal coding agent with 8 parallel subagents, isolated git worktrees, plan mode, and headless CI support, powered by Grok 4.6 with a 500K token context window. The release f…
A developer on a small tech team of about three engineers reports that code review has become a tighter bottleneck than code generation since adopting LLM tools like Cursor, with pull requests stacking up and review time…
AI-generated code introduces security risks that developers often overlook, according to a new analysis comparing automated code auditing tools. The report finds that generic large language models prioritize plausibility…
Determinant introduces AAL (Auditable Application Language), a deterministic layer between LLMs and code that contains AI uncertainty within a human-auditable boundary, after which compilation to TypeScript/Node.js proce…