Full-text search across 61901 articles. Combine with topic and date filters; results sorted by relevance.
A senior engineering leader argues that AI coding tools like Claude Code can boost code-generation throughput by up to 10x, but human engineers remain the bottleneck because the surrounding engineering system—processes, …
JetBrains has made KotlinLLM, its research prototype for delegating runtime logic to a large language model from Kotlin code, open source and public. The IntelliJ IDEA plugin, announced in July, adds a language feature c…
Chron, an MCP server that logs and audits AI-assisted coding sessions, has surpassed 6,000 downloads. The tool, built by a developer to address compliance gaps such as SOC 2 evidence requirements, records every message, …
Capital One released VulnHunter as an open-source agentic AI code-security tool on July 16, designed to analyze source code from an attacker perspective, map potential exploit paths, and propose targeted remediations. Th…
Alphabet CEO Sundar Pichai said during the Q2 2026 earnings call that Google needs to improve its coding and agentic coding capabilities, and that a larger Gemini 4 base model will be necessary to stay competitive at the…
A staff engineer describes using large language models (LLMs) for writing production code, throwaway code, learning new domains, and last-resort bug fixes, finding them most valuable for non-production code and as a tuto…
Independent developer Pedro Shakour released grok-build-ios on July 18th, an open-source SwiftUI client that lets developers control xAI's Grok Build coding agent from an iPhone. The app communicates with a Mac over xAI'…
A proposal for Language-Agnostic Module rePresentation (LAMP) introduces an intermediate representation that captures software modularity before code generation, aiming to improve modular structure in agentic coding. LAM…
A developer placed a logging proxy between two coding agents and their model to measure token overhead. Claude Code shipped roughly 33,000 tokens of scaffolding before a 22-character prompt, while OpenCode shipped about …
Legacy codebases encode organizational history in formats that AI agents cannot safely interpret, leading to architectural hallucinations when agents apply public-code patterns to enterprise systems. Vibe coding's low no…
A developer released token-saviour, an agent skill that routes coding tasks to the most token-efficient tool based on a benchmark of nine tools, achieving up to 69.6% token reduction on comprehension tasks. The skill cla…
JetBrains tested the viral 'Caveman' prompting style for AI coding assistants and found it reduces token usage by only 8.5%, far less than the claimed 65%. The technique trims conversational padding but has limited impac…
TERN has rolled out a framework called 'deep-understanding' to turn AI coding assistants into mentors rather than code generators. The framework, inspired by prompt mechanics from Anthropic engineers, guides developers t…
AI coding assistants are transforming software development by generating code at unprecedented speed, but this acceleration is creating a security imbalance. Engineers are inadvertently becoming security engineers as eve…
AbyssGuard launches a static analysis tool designed to catch security flaws in AI-generated code, targeting gaps in authentication, payment, and data-flow logic that AI coding assistants miss. The tool offers free scans …
Microsoft faced backlash after VS Code 1.117 silently added 'Co-authored-by: Copilot' to all commit messages by default, even when AI had not generated code. The company reverted the change and apologized, but the incide…
A 2026 survey by Hackceleration found that over 60% of AI-generated prototypes never ship to production, with database configuration, authentication flows, and deployment infrastructure cited as the most common failure p…
Rapid adoption of generative AI in software engineering, arguing that it undermines code quality, developer ownership, and craftsmanship by encouraging the acceptance of "slop" code. The author analyzes GenAI from four p…
Simon Willison built Battle Drones, a browser-based real-time strategy game, entirely through coding agents, accumulating 321 commits without writing any code himself. The project relied on Claude Code's "Ultracode" mode…
Rust off Rails launched as a set of roughly 60 Markdown files that instruct coding agents to build full-stack Rust web apps from a single prescribed stack, with the project's founding rule stating that all code — Rust, S…