Full-text search across 56896 articles. Combine with topic and date filters; results sorted by relevance.
A developer released crt, a local code review tool for reviewing AI-generated code, via a Show HN post on Hacker News. crt shows all files changed since a given commit along with their diffs, lets users approve files and…
Mandiant reported that an attacker hijacked an active AI coding-assistant session at an unnamed software-as-a-service provider and spread the Shai-Hulud worm across roughly 100 internal code repositories, stealing reposi…
Pyor released /pyor:review, a Claude Code plugin and cross-agent skill that opens working changes as a local pre-PR review in the Pyor desktop app before a PR exists. The tool runs a panel of fresh sub-agents with no con…
A developer documented a silent configuration failure in VS Code's MCP support: while Cursor, Windsurf and Claude Desktop expect servers under a top-level `mcpServers` key, VS Code reads a `servers` key, so configs copie…
Anthropic's CI job volume increased 25x over six months as Claude now authors 80% of the code its engineers ship, forcing the company to redesign its test impact analysis service after three quick fixes lasted 70 days, 2…
Atlassian plc announced a set of upcoming Jira features to run and govern AI coding agents at scale, including Code Context built on its Teamwork Graph, Agent Space Settings and Agent Context Controls, AutoDev, a merge-r…
A solo developer warns that relying on Claude 3.5 for 'vibe coding' created a black-box codebase, leading him to abandon AI-generated code and return to manual coding after six months. He advises developers to enforce ma…
Logitech launched the MX Keypad, a nine-key LCD control surface for developers managing AI coding agents, priced at Rs 15,999 in India and available in the US and UK. The device, shipping Tuesday, integrates with GitHub …
CodeMetrics.CLI, a new .NET global tool for C# projects, measures code complexity and maintainability directly from source syntax without restoring or compiling, offering metrics such as cyclomatic and cognitive complexi…
A 10-year iOS developer built their first personal app, AffirmCount, without writing a single line of code, relying entirely on AI vibe-coding. The developer, who could not verify AI-generated SwiftUI code, chose to veri…
A developer reports that using AI coding agents like Claude Code and Cursor has dramatically accelerated their workflow, shifting from syntax-level debugging to describing the intended user experience and letting the age…
As of August 2026, software engineering has shifted from writing code to managing agentic processes, according to a practitioner's experiments. The key is creating constraints—guardrails, linters, tests, and architectura…
A survey suggests that AI coding tools like Claude Code are creating a dopamine-driven feedback loop that leads to a new type of burnout among developers, characterized by cognitive fragmentation, the illusion of progres…
NAEOS (Nusantara Engineering & Architecture Operating System), an open-source declarative engineering platform for AI coding agents, has been released on GitHub, enabling developers to specify software systems once and g…
A developer argues that pricing coding agents per token misrepresents their true cost, citing 2026 research showing a single agentic-coding task consumes 1–3.5 million tokens, with 76% being reads, and can burn up to 100…
Engelbart, a free open-source Claude Code plugin for managing goals and TODOs, is now available in early beta for macOS or Linux with Node 18+ and Claude Code 2.1.175+. The tool, created by a team focused on cognitive sc…
A developer discovered uncommitted code in their open-source repository that had been written by an AI coding session running in parallel. The change added a feature to query DOM elements across cross-origin iframes, and…
The ZIM team, led by Dr. Abstract, developed the ZIM Master Prompt to address AI code hallucinations in the ZIM JavaScript canvas framework. The prompt, available at zimjs.com/prompt, uses two AI-optimized reference URLs…
Developer Manan introduced CXGRD, a CLI tool that computes blast radius via deterministic dependency graph traversal, contrasting it with AI agent-based code review tools that rely on probabilistic pattern matching. CXGR…
AI labs like OpenAI and Anthropic are increasingly seeking diverse, real-world datasets, making obsolete code a potential source of passive income through licensing, according to a report on Pangea.ai. Platforms such as …