Full-text search across 31894 articles. Combine with topic and date filters; results sorted by relevance.
A developer created ts-auntie-review, an Agent Skill that reviews TypeScript code with the persona of a Chinese neighborhood auntie, offering technical analysis across six dimensions and a 'Community Harmony Score'. The …
Fastly has released Fastly Fiddle, a web-based tool that compiles and executes VCL on real Fastly edge nodes, enabling developers and coding agents to test VCL code against production infrastructure including geolocation…
The AI coding market is shifting from model competition to the 'harness' layer, the software that routes coding tasks to models, as enterprises push back on price hikes from tools like Cursor. Cursor, which SpaceX agreed…
Xint Research analyzed 28 AI-generated codebases and found that the most common vulnerabilities include injection flaws, broken access control, and cryptographic issues, with AI code being inherently prone to these error…
AceKit, a new installer from Ace Data Cloud, wires external capabilities like image generation, web search, and URL shortening into coding agents such as Claude Code, Codex CLI, and Cursor. The tool installs a skill tool…
Taleeb Shahbaz argues that AI will not replace developers in 2026, despite the rise of 'vibe coding'—a workflow popularized by Andrej Karpathy where developers describe what they want and let AI generate code. Shahbaz ex…
A developer warns that AI-generated prototypes often appear finished but break under real-world conditions, shifting the bottleneck from code generation to verification. The post outlines a process for converting 'vibe-c…
A Java developer published a four-article series on designing Java code for LLM-based agents like Claude Code, arguing that agent-friendly code makes errors immediately visible to the compiler or instantly reproducible i…
Vibe Arcade built every game in its collection using 'vibe coding,' a term coined by OpenAI co-founder Andrej Karpathy that describes generating software by describing desired features in plain language to an AI model. T…
China's National Vulnerability Database warned on Wednesday that Anthropic's AI coding tool Claude Code contains a security backdoor that could transmit sensitive user data without consent. The regulator urged users to u…
Anthropic reported that Alberta's Ministry of Technology and Innovation used Claude Code with Opus and Sonnet models to scan 466 million lines of government code in about 20 hours, flagging vulnerabilities and generating…
Godot Engine formally banned AI-generated code from its open-source project on June 30, citing maintainer burnout and the inability of AI-reliant contributors to fix their own code. The policy prohibits AI-authored code,…
Microsoft's Visual Studio Code version 1.126 introduces a restricted mode for untrusted folders to prevent automatic code execution, allowing developers to browse code safely before deciding to trust the folder. The upda…
Smolagents, a Python library from Hugging Face for building AI agents, prioritizes code-based actions over JSON tool calls, enabling loops, conditionals, and tool composition. However, this design shifts the safety focus…
A developer with 25 years of experience reports that AI coding agents became genuinely productive around late 2025 with models like GPT-5.3 and Claude Sonnet 4.5. The developer's role shifted to designing environments wh…
A new survey from arXiv introduces 'code as agent harness,' a framework positioning code as the operational substrate for AI agent reasoning, action, and environment modeling. The paper organizes agent infrastructure int…
AI-whisper, a new open-source tool, pairs two coding agent CLIs—such as Claude, Codex, or ezio—in a terminal-native workflow where one agent implements code while the other reviews it, autonomously iterating until a deli…
Researchers at Northwestern University and the University of Chicago developed a computational method to measure open codes in qualitative analysis, using LLM-enriched hierarchical clustering and four novel metrics (Cove…
Inithouse, a studio shipping multiple products in parallel, tested seven code quality checkers on vibecoded projects built with Lovable, Cursor, and Bolt. Audit Vibe Coding won for AI-specific audits, CodeRabbit for ongo…
Agent skills—folders of markdown files that instruct AI coding agents—have become one of the most-starred new categories of developer tooling, with repos like Superpowers and a community-built skill based on Andrej Karpa…