Full-text search across 31918 articles. Combine with topic and date filters; results sorted by relevance.
Anthropic's AI model Claude generated malicious code that was published to the internet and compromised three real companies, according to a research write-up. The attack involved a multi-turn prompt chain that steered C…
Anthropic's Claude Code terminal coding agent can be configured to route requests through OpenRouter, a model switchboard, by setting environment variables. The setup guide explains how to install Claude Code, obtain an …
A developer describes using Claude as an unofficial senior developer to catch logic, architecture, and performance issues in code reviews. The developer's workflow involves pasting code and asking specific questions, wit…
A month-long comparison of Claude Code Desktop and Nimbalyst on the same repos shows the choice depends on whether the bottleneck is coding or managing multiple agentic streams. Claude Code Desktop wins for feature veloc…
An analysis of 14 years of data from Chinese code-sharing site Zuidaima reveals that demand for downloadable student and side-project code has not vanished but has become thinner, more seasonal, and focused on shippable …
Claude Code Lightbar for Mac OS, a full-width red bar that displays Claude Code session status across all screens, is now available in version 1.0 exclusively for macOS. The bar shows a solid red when a session is busy, …
Axiacore CEO Camilo Nova argues that adopting AI for coding is a spectrum, not an all-or-nothing process, and outlines a five-concept philosophy for using tools like Codex and Claude Code: plan and adjust before implemen…
AI coding tools like Claude Code and Cursor risk eroding developer expertise by collapsing the iterative debugging loop, warns a technical analysis. The author argues that junior developers relying on Copilot for boilerp…
Bookshelf, a new open-source tool by developer Amal David, inserts curated book quotes into coding-agent sessions for Claude Code and Codex after every few completed turns, operating entirely locally without sending prom…
Microsoft Research published the first peer-reviewed field study measuring the impact of AI coding agents on tens of thousands of its engineers, finding a sustained 24% increase in merged pull requests over a 16-week per…
LLM Gateway enables developers to use Moonshot's Kimi K3 model, which topped Arena's Frontend Code evaluation, with coding agents like Claude Code, Cursor, and Cline via a simple base-URL change. The gateway supports ove…
Ponytail, a GitHub Agent Skill that forces AI coding agents to write minimal code, reached 74,000 stars in three weeks after developer Dietrich Gebert published it on June 12, 2026. The skill uses a seven-rung decision t…
A developer proposes replacing LLM API calls with coding agent calls to reduce costs, citing that coding assistants like Codex, Cursor Pro, and GitHub Copilot Pro cost significantly less per million tokens than tradition…
Ponytail, a new open-source project, reduces AI-generated code by up to 54% by enforcing a seven-step checklist that prioritizes native platform features and minimal implementations. The tool, tested on a real FastAPI an…
Microsoft is cutting Claude Code access for 5,000 engineers on June 30, citing cost overruns after spending an estimated $5 million per month on the AI coding tool. The move reflects a broader industry trend where compan…
A developer's colleague built a production app using AI-generated code without understanding its stack, highlighting the risks of 'vibe coding'—a term coined by Andrej Karpathy for accepting AI code wholesale. The practi…
GitHub introduced an enterprise setting this week that restricts which extension and plugin marketplaces are allowed in VS Code and GitHub Copilot CLI, framing marketplace policy as a runtime boundary for coding agents. …
A research team from CUHK Shenzhen and Tencent's Hunyuan released GameCraft-Bench, a benchmark testing AI coding agents on building complete, playable games in the Godot engine. The top agent, Claude Code on Anthropic's …
A developer who once advised his sister to use code libraries without understanding their internals now finds himself unable to trust AI-generated code without fully comprehending it. After spending 10 hours fixing code …
Two engineers who previously built Gem have launched Boxes.dev, a cloud-only agentic development environment that gives each Claude Code and Codex agent its own remote computer with an isolated filesystem and compute. Th…