Full-text search across 61942 articles. Combine with topic and date filters; results sorted by relevance.
A developer who writes commercial copy for a living has shipped Cencurity, an open-source security gateway that proxies traffic between AI coding agents and LLM providers to mask sensitive data and inspect generated code…
A developer debugging a stalled Claude Code session in VS Code traced the issue to a queue of streaming events rather than a lost connection. The session appeared finished to the notification hook but still executing to …
AI-generated code accelerates prototyping but does not replace the judgment needed for production-grade software, according to an analysis. The article argues that computer science education remains valuable because it b…
A developer found that AI coding assistants like Cursor frequently generate code with hardcoded secrets, such as live Stripe API keys, because the models are trained on example code that inlines credentials. The develope…
Databricks is adding an agentic code conversion capability to its Lakebridge toolkit, using AI subagents to analyze, convert, and validate legacy SQL code at scale for migration to its lakehouse. The new tool, currently …
Xanadu's quantum compiler Catalyst, built for the PennyLane library, accidentally became an LLVM compiler for JAX when users fed it pure JAX NumPy code without quantum instructions, bypassing XLA to lower JAX representat…
A developer built a free QR Menu Builder SaaS using Laravel 12, React, Inertia.js, and Tailwind CSS to help restaurant owners manage menus online and generate QR codes. The project focused on a simple, modular database d…
Microsoft's in-house MAI-Code-1-Flash model, post-trained within GitHub Copilot's harness, achieves approximately 10% higher code accept rate than GPT 5.4 Mini and Claude Haiku 4.5 in VS Code, with 6% and 11% higher day-…
Software developers have abandoned traditional engineering norms and now rely heavily on large language models (LLMs) to write code, debug errors, and scaffold entire systems without fully understanding the generated out…
Atlas, a free local-first tool for Windows, maps a repository into a persistent dependency graph and evidence store that coding agents like Claude Code, Cursor, and Codex can query via MCP for cited, ranked file lookups …
Grok 4.5 successfully generated SWI Prolog and Lean 4 code to solve a chess puzzle: placing five white queens and three black queens on a 5×5 board so that no queen of one color attacks a queen of another color. The Prol…
Dreamer, a new open-source tool, mines coding-agent session history to identify recurring corrections and proposes updates to context files like AGENTS.md or CLAUDE.md, requiring user approval before applying changes. It…
Anthropic expanded Claude Cowork, its general-knowledge-work agent, from desktop to web and mobile in beta for Max subscribers, introducing a Dispatch feature that maintains a persistent thread and routes tasks to Claude…
Anthropic secretly embedded a tracker in its Claude Code tool to monitor users in China, using 'prompt steganography' to hide code that flagged timezone, proxy, and potential connections to Chinese AI labs. The company r…
Tadashi Shigeoka, CTO of a fully remote company, reflects on how AI tools like Claude and Claude Code have transformed developer experience (DevEx), reducing coding costs and shifting bottlenecks from writing code to oth…
Simon Willison reported that instructing Claude Code to delegate coding tasks to lower-power subagents using its own judgment significantly improved efficiency and reduced token usage. The approach, inspired by tips from…
Andrej Karpathy's AI coding rules, The Batch's 'loop engineering' issue, and Claude Code lead Boris Cherny's flat org structure signal that the unit of AI work has shifted from prompts to self-correcting loops. This shif…
A developer created UnVibe, an open-source learning platform that helps developers understand AI-generated code rather than just generating it. The platform guides users through studying production-style AI code, then re…
A developer released code-atlas-py, a deterministic code intelligence tool that builds a full call graph, dependency graph, and symbol index of any Python project in about 0.2 seconds. The tool scores every function for …
A developer on Hacker News is questioning the effectiveness of Spec Driven Development (SDD) with LLM coding agents, citing issues with code style and hygiene despite using tools like OpenSpec. The developer seeks advice…