Amazon Web Services announced the general availability of OpenAI GPT-5.5, GPT-5.4 models, and the Codex coding agent on Amazon Bedrock. The new models are designed for coding, reasoning, and complex p…
JetBrains open-sourced Mellum2, a 12-billion-parameter coding model, on Monday to target the infrastructure layer of agentic AI. The model is designed for tasks where tools like Claude Code fall short…
JetBrains released Mellum2, a 12-billion-parameter Mixture-of-Experts model trained on natural language and code that activates only 2.5 billion parameters per token for efficient inference. The open-…
A developer built Trof, an open-source AI task generator for the self-hosted project management tool Vikunja that requires human approval before any tasks are added or modified. The system uses a two-…
Cursor and Copilot have evolved significantly since 2024, with both tools now supporting agent mode, Model Context Protocol, and persistent project-level instructions. A developer demonstrated that wr…
Kilo Code, an open-source coding agent that began as a VS Code extension, has surpassed 3 million downloads and processed over 40 trillion tokens in its first year. The project's rapid growth exposed …
Zig President Andrew Kelley has banned all AI-assisted code contributions to the open-source programming language, calling them "invariably garbage" and "negative value" that waste reviewer time. The …
Mistral AI has released Codestral, a 22-billion parameter model specialized exclusively for code generation, trained on over 80 programming languages. The model features a fill-in-the-middle mechanism…
A developer calculated their monthly software subscription costs and found they were spending $67.89 per month ($814.68 per year) on essential developer tools, with costs rising to $194.89 per month (…
Anthropic's Claude Opus 4.8 model is now generally available for GitHub Copilot, offering improved code understanding and generation for complex problem-solving and large-codebase navigation. The mode…
GitHub Copilot CLI now supports plugins and a marketplace system that lets developers package reusable agents, skills, hooks, and MCP server integrations as installable packages. Instead of manually c…
Current large language models cannot safely modify real software systems despite impressive code-generation demos, because they rely on pattern matching rather than causal reasoning. The fundamental g…
By May 2026, AI-assisted development has become standard, with GitHub Copilot, Cursor, and Claude emerging as the leading tools for production coding. GitHub Copilot offers the best context awareness …
In 2026, the AI coding assistant market has matured, with GitHub Copilot becoming the safe enterprise choice integrated into VS Code and Visual Studio, while Cursor gained indie developer mindshare th…
GitHub's new GH-600 (Agentic AI Developer) certification, the first vendor credential focused on building and governing AI agents in the software development lifecycle, is currently in beta until May …
JetBrains is positioning its AI coding tools as an independent alternative as competitors like Cursor align with larger tech ecosystems. The company argues that developer tool ownership matters as the…
Major developments in AI development tools as of April and May 2026, highlighting Cursor 3.0's shift to a multi-agent workspace, Anthropic's Claude Code achieving 87.6% on SWE-bench Verified, and Wind…
The article compares three local LLM-based code completion tools—Zed AI, Continue, and Cursor—highlighting their strengths and weaknesses for different workflows. It notes that local models offer priv…
The Amazon Q Developer CLI has been rebranded and replaced by the new Kiro CLI, reflecting a shift from a simple terminal chatbot to a more advanced "agentic IDE" tool. Unlike its predecessor, Kiro CL…
On May 18, GitHub released a general availability feature allowing users to remotely control Copilot CLI sessions from mobile, web, or VS Code by scanning a QR code. The author independently published…