Full-text search across 63048 articles. Combine with topic and date filters; results sorted by relevance.
Anthropic's Claude Fable 5, released June 9, was placed under U.S. export controls three days later, forcing a global disable until restrictions lifted June 30, with temporary free access extended through July 19. Indepe…
GitHub's open-source Spec Kit turns specifications into executable source-of-truth documents for AI coding agents, enforcing a four-phase loop of constitution, specification, planning, and implementation to prevent agent…
A developer found that providing AI with project context—such as architecture, coding standards, and business requirements—yields better code than crafting elaborate prompts. After testing both approaches, the developer …
Five open-weight AI models have emerged as distinct tools for specific tasks in 2026, with DeepSeek V4 Pro leading in agentic coding and Qwen 3.6 serving as a balanced default. The models, including DeepSeek V4 Flash, of…
Tokdash, a local dashboard for tracking AI token usage and costs across coding tools like Claude Code and Gemini CLI, launched with performance improvements of up to 30x over previous versions. The open-source tool provi…
A developer built Lynkr, an open-source LLM gateway that extends Claude Pro/Max usage by routing different coding tasks to appropriate models across Azure AI Foundry, Amazon Bedrock, and local models. The gateway aims to…
A developer built a four-layer configuration system to enforce coding principles in Claude Code, moving beyond the suggestion-based CLAUDE.md file. The system includes a brain (CLAUDE.md), references, versioned skills, a…
A developer working on the open-source framework Projector encountered a bundle size issue caused by unnecessary code being pulled into the browser. Using ChatGPT 5.5 with Codex, they iterated on solutions for 2-3 hours …
Retool launched a new platform that lets developers build React apps using AI tools like Claude Code, Codex, Replit, or Lovable and deploy them through a governed runtime with automatic authentication, permissions, and d…
A developer debunked the viral AI coding skill Ponytail, which claims to make agents write terse code by following YAGNI principles, finding it to be a 100-line markdown file that barely outperforms a simple "Follow YAGN…
A new OCaml course book for the NPTEL MOOC platform runs code directly in the browser with no installation or server, aiming to eliminate the setup barrier that has long plagued beginners. The book, which covers OCaml an…
Claude Fable 5 leads GPT 5.5 in coding benchmarks, long-horizon tasks, and multi-step reasoning, making it the stronger choice for agentic workflows and production use cases. GPT 5.5 excels in multimodal capabilities, in…
HuggingFace's smolagents framework introduces CodeAgent, a code-writing agent that generates and executes Python in a sandboxed Jupyter kernel environment, replacing traditional tool-calling approaches. The agent uses a …
A developer has outlined a minimum viable test suite for teams working with AI coding agents, arguing that strategic coverage at three key "seams"—API contracts, data layer boundaries, and critical business rules—provide…
AI coding agents amplify ambiguity in human language, confidently generating code based on their own interpretation of vague terms without asking for clarification. It argues that this lack of friction, unlike traditiona…
Docker has introduced an undocumented API for spawning microVMs, which the author reverse-engineered to create the open-source Sandbox Agent SDK. Unlike standard containers, which share the host kernel and are unsuitable…
A system called "Minions," inspired by a Stripe blog post, which uses a markdown-based orchestrator to run multiple AI coding agents in parallel on independent tasks. Each agent operates in an isolated git worktree to av…
BMad Method, an open-source agile framework for AI-driven development, released stable version v6.12 through its npm installer and is previewing v7 in alpha, with a v7 release ETA of October 16, 2026. The v6.12 line is f…
Developer iha2 released superlite, an open-source Claude Code plugin that plans a build, splits it into parallel tasks, routes each task to the cheapest capable agent, and reviews the result without the human approval ga…
Anomaly released OpenCode 2.0 on 12 Oct 2026, a "major overhaul" of its coding agent that introduces three breaking changes to plugins, the server API and the terminal config file. The release adds a single shared backgr…