Full-text search across 59663 articles. Combine with topic and date filters; results sorted by relevance.
A developer proposed a 'Free-Model Agreement Test' to evaluate AI code generation tools, focusing on whether they can produce code that adheres to open-source licensing terms. The test aims to help developers choose mode…
LinkGravity, a new open-source bot interface for the Antigravity agentic AI system, lets users run AI coding agents from Discord, Telegram, or Slack with chat-based approval buttons, voice interaction on Discord, and mul…
Cognitive Fab released Polycheck, a least-privilege linter for Claude Code agent policies, available as the npm package @cognitive-fab/polycheck. The tool helps developers enforce minimal permissions in AI agent configur…
Capuchin, an AI coding assistant, now offers a bring-your-own-key (BYOK) model that gives developers full control over the entire stack, from models to infrastructure. The feature allows users to integrate their own API …
MacSurf's latest Patreon post, titled 'Retro Computing and AI Assisted Coding,' discusses the intersection of retro computing and AI-assisted coding, though no specific figures or outcomes are provided. The post appears …
GitHub Copilot, Microsoft's AI-powered coding assistant, is used by over 77,000 organizations and 20 million users, with a new study analyzing its production-scale usage. The research, conducted by GitHub and Microsoft, …
Alibaba Group Holding Ltd.'s AI model, Qwen, autonomously coded for 16 consecutive days, with every commit publicly available on GitHub, according to a report by The New Stack. The AI, developed by Alibaba's Qwen team, d…
Michael Hannecke built a sovereign coding agent on macOS, running Pi in an Apple container with zero NPM dependencies on the host system. The setup isolates the agent's runtime, ensuring a clean host environment and enha…
Angular was built for codebases where no one person could review every change, and agent-generated code is that same problem arriving faster, argues developer Brandon Roberts. He makes the case that if you're going to le…
Anthropic has released a new version of its Claude Code developer tool that runs with Opus 4.8 and full permissions, enabling more autonomous coding capabilities. The update allows the AI agent to execute commands and mo…
A developer at iHateReading has launched a free collection of prompts and rules for AI coding tools like Cursor, Codex, and Claude Code. The curated list aims to save developers time by providing reusable prompts for com…
The New Stack reports that single-pass AI code generation is not obsolete, but 'high-reasoning' models represent the next frontier in software development, according to the publication's analysis of current AI coding tre…
A new concept called 'comprehension debt' is emerging as developers increasingly rely on AI coding tools, according to a report by TechRadar. The term describes the growing gap between what code does and what developers …
Linus Torvalds rebuked anti-AI stances in the Linux kernel code review process, arguing that AI-generated code should be evaluated on its merits rather than dismissed outright. In a public exchange, Torvalds stated that …
A developer questions whether AI-assisted coding tools are dulling developer skills, sparking debate about the long-term impact on problem-solving abilities and code quality.
A developer built Codra, an AI code review tool designed to be self-hosted and fully owned by the user. The tool aims to provide privacy and control over code analysis by running locally.
A developer argues that Claude Code setups optimized for autocomplete are insufficient for AI agents, which require different configuration rules. The post highlights the need to adjust tooling and prompts to support aut…
China has issued a security warning about Anthropic's Claude Code, alleging it poses a backdoor risk. The advisory targets the AI coding assistant developed by the US-based company, escalating tensions over AI tool secur…
Y Combinator CEO Garry Tan claims his company ships 37,000 lines of AI-generated code per day, but a developer investigation reveals the claim may be exaggerated or misleading, raising questions about the true impact of …
A developer explores balancing Claude 4.8 and GLM 5.2 in structuring prompts for mid-level coding agents, aiming to optimize performance in automated code generation tasks.