Full-text search across 31918 articles. Combine with topic and date filters; results sorted by relevance.
AI-written code can be shipped to production only after rigorous human review and automated testing, according to industry best practices. While AI models can accelerate development by 20% to 50%, risks include hallucina…
Ben Greene, founder of Tessi, told an audience that software engineers must adopt startup mindsets to survive the rise of coding agents, which are already enabling companies to retask employees to train agents and then l…
Anthropic's Claude Code now supports auto mode, /goal, and /routines features that enable AI agents to run scheduled tasks without human supervision. The tools allow developers to set persistent objectives and automated …
Anthropic engineer Daisy Holman presented three principles—See, Act, Correct—for transforming code agents from prototypes into production tools, arguing that out-of-the-box agents lack the context of Slack threads, desig…
A llama.cpp maintainer argues that AI coding is a permanent paradigm shift and a 'human amplifier' rather than a replacement, urging developers to understand its strengths and weaknesses, guide AI step by step, and note …
Spec-Driven Development (SDD) has emerged as a disciplined alternative to vibe coding for AI-assisted software development, with tools like GitHub Spec Kit and Kiro implementing the approach. Proponents argue that AI age…
Business owners using AI tools must decide whether to build custom solutions or buy existing SaaS. A two-criteria framework—whether a good-enough solution exists and whether the capability differentiates the business—hel…
Independent testing of Claude Code's effort levels shows that max mode often provides little to no improvement in output quality over default or high settings for most coding tasks, while significantly increasing token c…
Claude Code and Codex both use OS-level process sandboxing to prevent AI models from executing harmful shell commands, relying on Linux primitives like bubblewrap for filesystem isolation and seccomp for syscall filterin…
In a post-AI development world, developers remain responsible for code they commit, even if generated by AI, according to an Ask HN discussion. The original poster notes that their commits still carry their name and they…
The GNU Compiler Collection (GCC) has adopted a policy rejecting substantial code contributions generated by or derived from large language models (LLMs), including code from tools like ChatGPT, Gemini, or GitHub Copilot…
A new field report from OpenAI reveals that coding agents, primarily Codex and Claude Code, enabled small teams to modernize critical scientific software in genomics and other fields across eight projects, accelerating d…
A developer with over a decade of experience building software by hand and three years using AI to build almost everything reports that AI writes working code on the first try more often than most engineers, but the real…
Loop engineering — designing the cycle that runs a coding agent automatically — is the shift from hand-prompting every turn to building a system that finds work, runs the agent, checks results, and decides the next move,…
A study of tens of thousands of engineers at Microsoft over its early-2026 rollout found that adopters of Anthropic's Claude Code and GitHub's Copilot CLI merged roughly 24% more pull requests than they would have otherw…
A developer warns that AI coding tools fail to understand the human context behind legacy code, such as desperate comments left by developers under pressure. The AI's focus on syntax and efficiency can lead to catastroph…
Snitch, an open-source deterministic prose claim verifier for AI coding agents, has been released. It monitors transcripts from tools like Cursor and Claude Code to flag false claims made by AI agents, such as assertions…
A developer built shiibar-cc, a macOS menu bar app that monitors Claude Code sessions in iTerm2 and alerts users when input is needed. The app uses Claude Code's hooks to report session events locally, displaying glyphs …
A developer introduces a structured approach to capturing project knowledge using Claude Code, organizing business rules, tacit knowledge, and code patterns into a hierarchy of files: project-level knowledge, module-leve…
A developer shares a workflow for learning to code by building projects with AI coding agents like Claude Code, OpenCode, and Codex, arguing that software engineering remains a valuable skill even as AI advances toward o…