Full-text search across 56235 articles. Combine with topic and date filters; results sorted by relevance.
AI-assisted pull requests contain 1.7 times more issues than purely human-written code, according to CodeRabbit's State of AI vs Human Code Generation report analyzing 470 real-world GitHub pull requests. The report foun…
Researchers at Air Security disclosed Plugin4Shell, a zero-click remote code execution vulnerability affecting AI coding agent plugin marketplaces for Claude Code, OpenAI Codex, GitHub Copilot, and Google Gemini CLI, cau…
Developers who rely on AI coding assistants like GitHub Copilot must write clean code because sloppy code trains the LLM to generate even sloppier code, creating a feedback loop that turns repositories into technical deb…
Concept of "AI license laundering," where generative AI coding assistants trained on public code repositories can produce output that closely resembles copyleft-licensed code (such as GPL) without including the required …
Code sandboxes are isolated computing environments that allow developers to run untrusted code, such as code generated by large language models, without risking security breaches or data loss. They are experiencing a sur…
Datadog's new research series testing coding agents' secure code generation found that running models in plan mode versus default mode had no significant security impact across Sonnet 5, Composer 2.5, and GPT 5.5, with a…
Meta and AWS launched coding-agent products a day apart this week, converging on the same parallel-agent architecture. On August 4, AWS released Kiro Crew, an open-source orchestration workspace for its Kiro agentic IDE,…
AI-generated code has turned security debt into a governance problem, according to a CyberScoop analysis. The Veracode 2025 GenAI Code Security report found that AI coding tools produce insecure code nearly half (45%) of…
Fabien (FAB) released a personal agent.md file in March 2026 to improve LLM-assisted code quality after finding that LLM-generated code, while functional, lacked structure and required extensive cleanup. The file, which …
Muse released Muse Code (beta), a terminal coding agent powered by its new Muse Spark 1.2 model, which features async background agents, a replay-exact runtime, and bundled skills for planning and execution. Muse Spark 1…
PicNet's Practical AI in Health series recommends that hospitals build AI-assisted coding suggestion engines rather than fully automated coding systems, citing the high financial stakes of coding errors under Australia's…
A developer won the $25k grand prize in the 2026 Vibejam game competition with a game built almost entirely by Claude Code, an AI coding tool. The game, 'A Game About Capybaras Delivering Food,' was developed in 15 days …
Nebius published a cookbook showing how to run open coding models such as moonshotai/Kimi-K2.7-Code behind Anthropic's Claude Code CLI using nebiusrelay, a local proxy that translates Anthropic Messages API calls into th…
A developer comparison of Anthropic's Claude Code CLI agent and Cursor's IDE found Claude Code faster for complex refactoring (6 minutes versus 15 minutes) and runtime debugging (2 minutes versus 5 minutes), while Cursor…
Thoughtworks' Birgitta Böckeler argues that AI's surge in code production—Meta reported a 106% increase in significant lines of code per human-landed diff in a year, and DX data shows median pull request size up 64%—mean…
Amazon CloudWatch launched Coding Agent Insights on July 20, 2026, providing engineering teams with an AWS-native dashboard to track AI coding tool spend, adoption, and output across Claude Code, GitHub Copilot, and Code…
Adobe has patented a self-correcting AI coding system that trains a large language model by pairing correct and incorrect code responses and fine-tuning on the resulting preference dataset, according to a patent filing t…
Piebald AI has released a repository tracking Claude Code's system prompts across 237 versions since v2.0.14, now covering 515 prompts as of Claude Code v2.1.211 (July 15, 2026). The repository, updated within minutes of…
The AI Now Institute published a proof-of-concept on July 8, 2026, showing that autonomous coding agents like Anthropic Claude Code and OpenAI Codex can be manipulated during security review workflows, turning defensive …
A new analysis argues that when coding agents write software, human reviewers must still read the generated code because the code remains a critical artifact, not an ephemeral by-product. The author explains that the dec…