Full-text search across 57372 articles. Combine with topic and date filters; results sorted by relevance.
DX's Q2 AI Impact Report finds that organizations should measure AI coding tools by their effect on innovation capacity rather than by metrics like 'Developer Horsepower' that estimate human effort replaced. The report a…
A developer who burned through their token budget running Claude Code and Codex found that local inference with open-weight models trades dollar costs for wall-clock and retry costs. Testing Qwen3-Coder-Next on a 64 GB m…
Eyal Estrin, author and Cloud Security Architect at Undisclosed, argues that AI will not replace human developers because the core of software engineering lies in planning, requirements analysis, and design—tasks requiri…
A developer argues that AI-assisted coding is not the same as software engineering, warning that reliance on AI without understanding can hinder true engineering growth. The post emphasizes that engineering involves deci…
Chain-of-thought prompting can dramatically improve AI coding workflows by forcing models to reason before writing code, according to tests run by the author. A direct request for a regex solution succeeded 0% of the tim…
Shopify is launching a new storefront theme with 93% fewer lines of code than its current Horizon theme, driven by the need to make code readable for AI agents like its Shopify Sidekick assistant. Product director Ben Se…
Codeberg, a volunteer-run code hosting community, has voted to ban vibe-coded projects primarily developed by AI agents, citing resource strain, environmental harm, and damage to the Free, Libre and Open Source Software …
Anthropic has added iOS Simulator integration to Claude Code Desktop in public beta, allowing the AI to tap through an iOS app in real time, read the screen, and revise code without requiring macOS Accessibility or Scree…
A developer detailed how Claude Code silently introduced a bug by guessing the event shape for an SQS-triggered Lambda, accessing `event.body` instead of the correct `event.Records[0].body`. The developer then used the I…
AI coding agents are increasingly used to build and maintain the Astro web framework, with its repository containing an AGENTS.md file and commits co-authored by Claude and GitHub Copilot, signaling a shift toward commod…
Booz Allen found that four Chinese large language models (LLMs) commonly used by U.S. developers produced more vulnerable code when prompted with a U.S. government persona, and the vulnerabilities were highly obfuscated,…
Generative AI coding agents are disrupting software engineering collaboration by replacing peer discussions with direct engineer-agent conversations, starving product requirements backlogs, and shifting technical design …
A developer explains why they switched from VS Code to Cursor, arguing that Cursor treats AI as a core part of the development environment rather than an add-on. The developer highlights Cursor's Composer feature for mul…
A new research framework called MOSAIC successfully compromised AI coding agents in 96.59% of 2,525 attempts by exploiting CLI command-composition risk (CCR), a novel attack category that does not rely on prompt injectio…
An engineer who ran ~$10K/month in Claude Code API bills found that 80% of spending went to frontier models for tasks that didn't need them. By implementing task-level model routing—matching model tier to coding phase—th…
Amazon Web Services has introduced AWS Continuum, a new integrated security platform that automates the discovery, enforcement, and remediation of security issues across codebases, dependencies, and applications. The pla…
Marc Olson and Andrew Wheeler introduced a defense mechanism for coding agents like Claude Code, Codex, and Cursor that filters secrets from tool outputs using a post-tool-use hook, replacing detected secrets with "***RE…
A developer's guide details how to integrate Claude Code with NanoBanana MCP for image generation and editing directly from the terminal. The integration exposes two tools—nanobanana_generate_image and nanobanana_edit_im…
A developer argues that the biggest problem with AI coding assistants is not the AI itself but how code is written. By adding metadata like file paths, usage locations, and feature READMEs, developers can provide the con…
Mathematician Terence Tao used an AI coding agent to port his old Java applets to JavaScript, making them functional again after years of obsolescence, and also created new visualization tools for special relativity and …