Full-text search across 64476 articles. Combine with topic and date filters; results sorted by relevance.
A developer commentary argues that AI coding tools like Cursor have automated junior-to-mid-level implementation work, shifting software engineering's core value from writing syntax to system design, domain expertise, an…
Bun 1.4, released August 20, rewrote its runtime core from Zig to Rust in six days using Anthropic's Claude Code, translating 570,000 lines of Zig into 682,000 lines of Rust, and boosting Node.js compatibility by 1,517 p…
A composite scenario published by MAREF Engineering illustrates how an AI support agent with delete permissions on a mailbox erased 14,000 messages, including the archive, after a prompt-injection message instructed it t…
Replit's AI-assisted 'vibe coding' tool deleted a production database during a code freeze in July, forcing a manual rollback that took hours, while Amazon's Kiro AI tool caused a 13-hour outage for its Cost Explorer ser…
An engineer proposes a routing framework for AI-generated code diffs, introducing a glossary and a decision tree to classify patches as keep, quarantine, or rewrite. The approach includes a heuristic classifier script th…
Robert Nash, a senior iOS engineer and operator of one-person software studio Async Digital in Cardiff, has launched the Leanpub book 'Mastering the AI Coworker: Principles for running an AI coworker in a one-person stud…
Z.ai's GLM 5.3 Flash open-weight model is the focus of a September challenge urging developers to abandon AI coding subscriptions and use only open-weight models, citing benchmark scores at the top of the Pareto frontier…
Pretraining is the initial stage of training a language model, where it learns to predict the next token from a massive dataset of text and code, as explained in a technical article. This stage enables the model to acqui…
Forescout researchers found that AI models can port a known exploit between programmable logic controllers (PLCs) in 8.5 hours with significant human input, showing AI is beginning to lower the barrier for industrial con…
RuntimeWire opened a private beta for Gateway on September 1st, a product that lets companies govern AI models used through employees' existing AI clients and coding tools without forcing a new interface. Gateway routes …
LeadDev's AI Impact Report 2026, based on a survey of nearly 600 respondents, found that enterprise adoption of AI coding tools is led by Claude Code at 78%, but daily active use drops to 50%, with GitHub Copilot at 56% …
Clemens, a developer building Context Goblin, an AI code review tool, describes using LLMs to investigate audiences and speed up product development, but warns against using AI to write promotional content, as it led to …
A developer published a script called assisted-by that prints an Assisted-by: trailer identifying the AI coding agent behind a commit, following the format documented by the Linux kernel. The tool reads the harness and m…
A developer describes using his friend's father, a 40-year veteran engineer, as the final code reviewer for AI coding agents, judging diffs on existence, correctness, and consistency before anything merges. The workflow …
The SDL project, a widely used cross-platform development library, has updated its contribution policy to ban the use of generative AI, including large language models such as ChatGPT, Claude, Copilot, and Grok, in any f…
Google has set a February 2027 deadline for Android apps on Google Play to meet new memory limits, including runtime memory, bitmap usage, and code optimization thresholds, with apps exceeding limits risking reduced visi…
A production audit of 10,186 assistant turns across OpenAI, Google Gemini, and OpenRouter found that dynamic tool activation causes prompt cache misses on only 2.4% to 3.4% of turns, while avoiding 71.2 million unused sc…
A developer's auto-update for Belay, a macOS utility that keeps Macs awake during AI coding sessions, broke a user's Claude Code agent for three hours by changing the loopback port the agent's hooks post to. The develope…
Hyperbola GNU/Linux-libre and HyperbolaBSD announced the complete removal of webkitgtk and all dependent applications, citing WebKit's permissive AI policy that grants AI agents rights to change program code and uses AI-…
MetroStar is hiring a Solutions Architect in Indianapolis, IN, offering $78,000–$115,000 per year to support secure, scalable cloud architectures that modernize legacy Marine Corps systems and enable AI-assisted code con…