Full-text search across 31918 articles. Combine with topic and date filters; results sorted by relevance.
A developer built SafeDevTools, a collection of browser-based developer utilities, using only a local LLM (Gemma 4:12B) running on a MacBook M4 Pro with Ollama and VS Code. The project demonstrated that a well-written Co…
Researchers at an undisclosed institution analyzed Gemma-2-2b's internal circuits and found that the LLM detects vulnerable code by relying on safety detectors that recognize safe coding patterns, rather than directly id…
Stewie Reflect launches a tool that generates owner's manuals for code repositories, linking claims to evidence in the code. The service, currently in private beta, offers a free preview and charges a one-time $19 fee fo…
GLM 5.2, an open-weight coding model from Z.AI, outperformed Claude Opus in four real-world coding tasks including a codebase audit, UI redesign, and autonomous bug hunting, costing only $3.36 for 6 million tokens. The m…
In 2026, the barrier to building a website has shifted from coding to deployment, as AI tools now generate code easily but non-technical users struggle to get pages live. A Chrome extension called HTML Deployer aims to b…
TanStack AI reached Beta on June 9, 2026, introducing Code Mode, middleware, and host-side MCP. Code Mode lets the model write and execute TypeScript programs in a sandbox, reducing round trips, while middleware adds cac…
A developer argues that current coding agents fail due to excessive tooling, which pollutes context and causes errors. They propose a solution called eeva, a harness that uses a single Elixir Eval tool, reducing noise an…
Agent Rigor, a new open-source framework, provides a structured multi-layer progressive disclosure system to prevent AI coding agents from entering 'doom loops' and other failure modes. The framework enforces empirical d…
Researchers from Renmin University of China and Microsoft Research introduced Arbor, a persistent hypothesis tree that helps AI coding agents remember and refine learnings over long research sessions. In tests, Arbor del…
Anthropic launched live Artifacts for Claude Code, enabling users to generate shareable web pages from coding sessions. The beta feature, available for Claude Team and Enterprise organizations, creates interactive output…
Kkt, a new tool named after the Karush-Kuhn-Tucker conditions, applies constrained optimization to coding-agent workflows by forcing agents to identify explicit constraints before implementation. The tool aims to reduce …
Microsoft's MAI-Code-1-Flash, a small coding model, is now available on additional GitHub Copilot surfaces including Copilot CLI, GitHub Copilot app, Copilot Chat, Visual Studio, GitHub Mobile, JetBrains IDEs, Eclipse, a…
A developer built Agent Island, a macOS tool that monitors Claude Code and Codex CLI sessions by reading local transcript files to detect when an agentic coding session is working, stalled, or waiting for user input. The…
Anthropic has updated its Claude Design assistant with deeper integration into its coding agent Claude Code, allowing designs to be handed off for programming and enabling direct design creation from the terminal. The up…
BrainGrid, an AI-powered planning platform, aims to solve the 'babysitting tax' of agentic coding by providing structured planning and deep codebase analysis. The platform transforms high-level ideas into detailed, code-…
JetBrains open-sourced Mellum2, a 12B Mixture-of-Experts coding model under Apache 2.0, designed for air-gapped and compliance-locked environments where external API calls are prohibited. The model uses a MoE architectur…
SpaceX will acquire AI coding startup Cursor for $60 billion, aiming to gain a competitive edge against Anthropic and OpenAI. The deal, announced in a regulatory filing, will make Cursor a wholly owned subsidiary of Spac…
Researchers introduced Dialogue SWE-Bench, a benchmark for evaluating AI coding agents through dialogue with users, revealing that coding proficiency does not guarantee strong dialogue skills. The study proposes a schema…
Ziwen Xu, founder of AI startup Hyperecho, is attempting to use Anthropic's Claude AI to 'vibe code' a version of Grand Theft Auto VI before its official November release, posting daily updates on X and sharing code on G…
3code, a new coding agent designed for efficiency, is now available for free use even without a subscription. The tool, which integrates with multiple open-weight model providers like Nvidia and DeepInfra, claims to redu…