Amazon launched Amazon Bedrock AgentCore Runtime, a service that provides isolated Linux microVMs with persistent workspaces and real shells for hosting coding agents, addressing the security and reso…
Microsoft shut down over 70 of its own GitHub repositories, including those related to Azure and AI coding agents, after hackers planted malware designed to steal credentials when opened in AI coding …
Anthropic published its official guide to building Claude Skills, a system that allows users to create reusable instruction folders for the AI assistant. The guide covers the technical structure of sk…
AI coding agents like Claude Code and OpenAI Codex favor open-source software because it lacks permission barriers, but they still reject projects with high friction, abstraction, or verification cost…
AI Gateway data shows DeepSeek's share of tokens on the platform surged from under 1% to 17% in May, while its share of spend remained near 1%, as the low-cost model entered production use. Anthropic'…
A software developer explains why they refuse to use LLMs for coding, citing enjoyment of the craft, autonomy concerns, and the proliferation of low-quality AI-generated open-source contributions. The…
Developer Joe Pohnelt created an email triage system using Claude Code subagents to automate Gmail management. The system uses six specialized AI agents for security analysis, relationship mapping, co…
Thoughtbot engineers built a Claude Code hook that automatically runs RuboCop against any Ruby files an AI coding agent modifies, then gives the agent a chance to fix violations it can catch. The hook…
A developer rebuilt Cloudflare's AI code review system as a 250-line JavaScript workflow using Claude Code, replacing Cloudflare's infrastructure with a single file that runs locally. The system uses …
A developer published a CLAUDE.md configuration file for Claude Code that enforces two working principles: judge work by correctness rather than ROI, and fix bugs at the architectural root rather than…
A multi-agent refinement loop using three agents iterating over 'What is recursion?' achieved a score increase from 0.92 to 0.98 in five hops, but the process revealed five critical bugs in the Loomcy…
AI adoption has evolved through distinct eras, from the initial LLM period starting with ChatGPT's release in November 2022 to the current agent period beginning in summer 2025, where model performanc…
Pi released a programmatic SDK that allows developers to embed its coding agent directly into their own scripts, eliminating the need for separate extension and system prompt files. The SDK follows th…
Pi, a minimal agent engineering tool, offers a lightweight alternative to Claude Code, which the author compares to Django versus Flask. The author rebuilt their news reader with Pi to explore its cap…
Rising AI costs are forcing businesses to scrutinize spending as price hikes from providers like OpenAI and Microsoft challenge the value proposition of large language models. Companies such as Uber a…
A writer argues that criticism of AI-generated content relies on an idealized, unrealistic standard of human output, pointing out that most human-created code, advertisements, and media are already lo…
A developer has created a guide for running coding agents like Codex CLI, Claude Code, and Cursor entirely on local hardware using Ollama, eliminating the need to send proprietary code to third-party …
Developer Jack Franklin launched ai-review, an open-source tool that lets terminal-based AI coding agents present plans and diffs in a browser for line-by-line review. The tool bridges the gap between…
AI providers are quietly reducing model quality and throttling capacity as demand outpaces infrastructure supply, according to an analysis by a senior director at AMD's AI group. The study of 6,852 Cl…
Clawdcursor, a new open-source desktop control tool, allows AI models to directly interact with computer interfaces through a single MCP entry point, supporting macOS, Windows, and Linux. The tool ope…