Full-text search across 56587 articles. Combine with topic and date filters; results sorted by relevance.
A developer with experience across Flutter, backend, and full-stack projects shares practical strategies for debugging AI-generated code, emphasizing that AI lacks project context and often produces syntactically correct…
A developer essay titled '2x, not 10x: coding with LLMs in 2026' topped Hacker News with 349 comments, arguing that realistic productivity gains from AI coding tools are 2x, not 10x, citing Amdahl's Law and a peer-review…
Moonshot AI released Kimi Code CLI, an MIT-licensed terminal coding agent that reads and edits code, runs shell commands, and loops on results, as a ground-up TypeScript rewrite of its predecessor. The single-binary tool…
Zed Industries' Agent Client Protocol (ACP), an open standard for connecting AI coding agents to editors, has been adopted by JetBrains and Amazon's Kiro IDE, with 25+ agents including Claude Code and GitHub Copilot in i…
GitHub COO Kyle Daigle told Observer that AI coding tools are about more than just generating code, emphasizing the broader process of creating software. New data from Exceeds shows Claude Code leading primary tool share…
Redis co-creator Salvatore Sanfilippo (antirez) argues that programmers should focus on controlling the ideas behind software rather than reading every line of code, as AI-generated code makes line-by-line review ineffic…
ASSET Research Group and Sudipta Chattopadhyay published a proof-of-concept attack called Ghostcommit that hides a prompt-injection instruction inside a PNG image, passes AI code review, and later induces a coding agent …
A software engineer reports that using Claude Code for personal projects has degraded their ability to write code manually and understand codebases, while improving their skills in managing and instructing development te…
Amazon Bedrock now offers general availability of OpenAI's GPT-5.5, GPT-5.4, and Codex models, providing developers with managed cloud access to frontier AI capabilities. Xiaomi released MiMo Code, an open-source languag…
Kilo launched Coding Plans, starting with MiniMax, allowing users to purchase token plans directly through their Kilo balance for use across Kilo Code products and the Kilo Gateway. The feature aims to simplify access to…
Nearly half of all production code is now AI-generated, yet 93% of enterprises surveyed suffered a security breach directly from in-house developed apps in 2025, according to a new Checkmarx report. Three-quarters of org…
Frontman, a frontend development tool, has published a workflow-based framework for selecting AI coding agents, arguing that the best tool depends on the specific frontend task rather than a universal ranking. The framew…
The author, a software engineer with nearly two decades of experience, initially opposed AI due to concerns about hallucination, poor quality in generated images and text, and the superficial nature of "vibe coding." How…
Pillar Security found that selecting a model in Unsloth Studio triggered the download and execution of Python code from the model repository, with researcher Ariel Fogel stating "Reading the model's config.json was enoug…
A developer has documented how to configure Claude Code's Stop hook to fire a desktop notification when the AI coding agent finishes responding, distinguishing it from the Notification hook that signals Claude is waiting…
A hospitality management software team traced a failing authentication flow to a single mismatched keyword after LLM coding assistants and multiple developers failed to surface the cause. The team had used AI assistance …
Cursor and Claude Code maintain separate discussion venues, with Cursor hosted on its own forum at forum.cursor.com and Claude Code discussions scattered across the Anthropic Discord and X, according to a guide to AI cod…
A developer's essay introduces 'comprehension debt,' a term coined by Jason Gorman, to describe the gap between what AI-generated code does and what human teams understand about it. The piece argues that as AI agents pro…
New research from Microsoft and academia, published in ACM Queue, finds that AI coding tools' impact is limited because developers spend only 14% of their time writing code, and gains vary widely by task. The study, led …
The European Commission and the AI Board have endorsed the Code of Practice on Transparency of AI-Generated Content as an adequate voluntary tool for complying with the AI Act's transparency obligations under Article 50,…