Full-text search across 57471 articles. Combine with topic and date filters; results sorted by relevance.
VibeSolve, an open-source tool, converts plain-English descriptions of optimization problems into Timefold code, leveraging LLMs for rapid prototyping. The tool outperforms direct LLM queries for Timefold code generation…
Traversal CEO Anish Agarwal explains that AI coding agents have made writing code easier but running it safely in production harder, as production failures are increasingly caused by system interactions rather than code …
Norrin launches a new tool that provides inline diff control, file tracking, and accept/reject functionality within Claude Code, enabling Cursor-like control over code agents to streamline code review and reduce PR revie…
Mistral AI is developing Code and Apps features for its web platform Vibe (Le Chat), moving beyond conversation toward a full product platform. The Code section brings coding agents to the browser, while the Apps area al…
Chad and Sami discussed AI code audits on the Giant Robots Podcast, focusing on developer-friendly AI code bases and security concerns. Sami shared insights from a recent audit of an AI-built codebase using Spec Driven D…
A developer on Hacker News expresses unease about using AI coding tools, feeling a loss of control and confidence as LLMs generate code faster than they can review it, despite maintaining architectural oversight. The pos…
Moonshot's Kimi K2.7 Code model is now available on Cloudflare Workers AI, expanding the coding model's reach into developer infrastructure. The model is optimized for long-horizon agentic tasks, a capability increasingl…
Google's Angular team has released a repository of Agent Skills that teach AI coding tools to write modern Angular v20 code instead of outdated patterns. The skills, designed for tools like Gemini CLI, enforce current co…
A new Anthropic study reveals that researchers with typically male names use AI coding agents more than twice as often as those with typically female names, even when controlling for discipline and career level. The gap …
A new open-source coding agent, mini-SWE-agent, achieves up to 74% on the SWE-bench verified benchmark using just 100 lines of Python code. Developed by the Princeton and Stanford team behind SWE-bench, the agent operate…
A developer built `/letsgo`, a master agent orchestrator for Claude Code that coordinates development through a structured 15-step blueprint. The system separates planning and discovery from implementation, refusing to w…
LLMs can theoretically generate millions of correct lines of code, but any important code still requires hand-auditing every line—a process harder than writing it from scratch. This creates a fundamental limit on the spe…
A developer released Agent Launch, a command-line interface that unifies launching local coding agents including Codex, Claude Code, Cursor, Gemini, and OpenCode. The tool provides a single command with consistent option…
CC-Wiki is a tool that converts local Claude Code session histories into a shareable Quartz-based knowledge base, allowing users to package research and learnings into a reusable, arXiv-like format. It is installed via a…
An experiment using Claude Code to create a multi-agent AI workflow for software development, orchestrated through a Java/Spring Boot backend. The author found that the main challenges were not code generation but rather…
QR code generator tool that was built with the assistance of Claude, an AI model. The tool allows users to create QR codes for text, URLs, and WiFi network connections. It is categorized under topics like vibe-coding, to…
A developer outlines a pragmatic framework for auditing AI-generated code, arguing that passing tests alone are insufficient because coding assistants like GitHub Copilot and Claude optimize for the happy path and miss c…
Meta research found that pairing two AI coding agents to review each other's patches improves bug detection more than increasing a single agent's budget, according to a study tied to the company. Meta's internal RADAR re…
Developer adjaecent released Hutch (magit-hutch), a local code-review interface for Emacs that runs LLM-powered reviews on staged changes, un-pushed changes, or diffs between the current and working branch, rendering fin…
A developer built EdgeMate, an offline mock coding-interview tool that runs entirely on a laptop using Ollama-hosted open-source models such as qwen2.5-coder:3b. The system pairs a local LLM with a deterministic subproce…