Full-text search across 61889 articles. Combine with topic and date filters; results sorted by relevance.
A developer argues that vibe coding's missing half comes before the build, not after it, proposing an expanded loop — Vibe → Spec → Break the Design → Build → Break the Build → Understand → Stabilize → Perfect — that add…
Patric Fornasier, who quit his job in October 2025, spent eight months solo-building a quantitative trading fund with AI, using Claude Code as his primary tool after testing Cursor, Antigravity, Gemini CLI, and Codex CLI…
A developer survey of MCP (Model Context Protocol) support across Codex, Cursor, Claude Code, Grok, and OpenCode finds only 56% of the scoreboard features are implemented, with partial support for the 2026-07-28 protocol…
Anthropic's Claude opened 388 maintenance pull requests across the company's iOS, Android, desktop, web, CLI and Agent SDK repositories, with 180 merged after automated and human review, according to Boris Cherny, creato…
GitHub's reliability is declining under the strain of AI-generated code, with outages, missing PRs, and a merge-queue bug that silently deleted commits, according to an analysis in The Hangar community. Agentic coding to…
A Microsoft internal study of tens of thousands of engineers found that CLI coding agents such as Claude Code and GitHub Copilot CLI spread primarily through social networks rather than mandates, and adopters merged roug…
A security researcher demonstrated that indirect prompt injection in agentic coding tools like Claude Code can lead to full system compromise. By cloning a seemingly benign GitHub repository, the researcher triggered a r…
Indeed increased AI coding tool adoption from 25% to 97% across its engineering organization by implementing a structured training program called AI Coding Essentials, which reduced coding time by 35-36% for participants…
LLMs are shifting from vibe-coding to specification-based programming, where human input is via specifications that generate code. This approach enables controlled, repeatable software creation, with features and bugs ma…
A developer warns that AI coding tools can accelerate building software but also amplify mistakes when used without a clear plan. The engineer argues that the real bottleneck has shifted from writing code to defining the…
Bryce Rattner Keithley, a talent and recruiting professional with no coding experience, built and shipped a fitness app called Daily Hundred to the App Store using AI tools including Claude, Replit, and Gemini. The app f…
A developer has created Aweskill, a CLI-first Skill package manager designed to be operated autonomously by AI coding agents. The tool enables agents to install, manage, and troubleshoot their own Skills without human in…
This document outlines strict coding guidelines for AI agents and contributors working with Python code, emphasizing full optimization through algorithmic efficiency, parallelization, and minimal technical debt. It manda…
A new arXiv paper (2610.23436v1) proposes PolicyLift, a three-stage framework for improving decision policies from observational data when actions are complex structured objects such as text messages or images. PolicyLif…
E2B, an open-source project for running AI-generated code in secure, isolated cloud sandboxes, was last updated in October 2026 and has 14,000 stars on GitHub. The infrastructure, written primarily in Python and controll…
A developer published a free, self-contained lab demonstrating that AI-generated test suites can reach high code coverage while still passing against deliberately broken code. In the lab, the AI's own suite passes 3/3 ag…
A developer's analysis of roughly 4,300 real coding-agent sessions (Claude Code and Codex, 43 developers, ~350,000 LLM steps) found that the median LLM step re-sends about 119,000 cached prefix tokens while appending onl…
Microsoft unveiled a September 25 Copilot update that consolidates chat, coding, and autonomous agents into a single app organized around three tabs: Home, Code, and Autopilot. The Home tab merges the company's Chat and …
Anders Hejlsberg unveiled a Go-based rewrite of the TypeScript compiler that processes the VS Code codebase (roughly 1.5M lines) in under a second, compared to 12-15 seconds for the old implementation. Hejlsberg said AI …
Salvatore Sanfilippo, creator of Redis, outlines seven qualities tomorrow's programmers need as AI reshapes software development, emphasizing system-level understanding, judgment, and communication over raw coding speed.…