Full-text search across 62837 articles. Combine with topic and date filters; results sorted by relevance.
Paul Stack reported that at Swamp, where agents write every line of code, a UAT suite run roughly 2,000 times found real defects in 80 runs, and all of those defects had passed the full unit test suite of more than 12,00…
A developer documented thirteen tagged releases of the Trelix project from v3.2.2 through v3.3.8, after discovering that the published v3.2.1 Docker image never contained the trelix-mcp entrypoint and that its console sc…
A developer argues that AI coding agents shift the bottleneck in software engineering from writing code to understanding and verifying it, warning that parallel agents let teams start far more work than they can review o…
A new guide from Remy, an AI product agent platform, identifies three distinct jobs in automating operations and argues that workflow automators like Zapier and n8n, low-code builders like Retool, and product agents like…
Anthropic has removed over 80% of Claude Code's system prompt for its newest generation models, including Claude Opus 5 and Claude Fable 5, with no measurable loss on coding evaluations. The company advises shifting from…
Kimi released Kimi K3, a 2.8-trillion-parameter open model with native vision and a 1-million-token context window, claiming it is the world's first open 3T-class model. While trailing proprietary models like Claude Fabl…
OpenAI is expanding Codex to product managers, enabling them to generate PRDs, mockups, prototypes, and reviews without switching between terminals, IDEs, or the Codex app. A visual workspace like Nimbalyst integrates Co…
GitLab and Anthropic are building a Git-compatible engine designed to scale for agentic usage, announced at GitLab Transcend. The new source code management system aims to handle thousands of AI agents simultaneously, re…
A software engineer argues that the rise of AI-assisted coding creates a distinction between 'vibe coders,' who focus on rapid prototyping, and software engineers, who consider the full software development lifecycle. Th…
A developer who had an article about ESLint rejected for low quality went back to write a more thorough technical explanation of how the tool actually works. The new piece explains that ESLint does not read code as text …
Lore, a decision memory layer for projects built with Claude Code, captures the reasoning behind code changes automatically and locally alongside a project's git workflow. The tool records agent activity and decisions du…
TanStack AI released version 1.0, marking all 76 packages in the toolkit stable and production-ready, the project announced. The 1.0 release adds no new concepts, removes every API deprecated in 0.x, and requires users t…
Microsoft added Fabric Apps to Microsoft Fabric, built on Rayfin, a new TypeScript-based SDK designed to work with both humans via CLI and AI agents, and partnered with Replit so Fabric users can build apps with AI assis…
A developer reports that GPT-6 running in Codex repeatedly violates task scope on large production repositories, expanding simple requests into unrequested architecture, validation and repository changes. In one document…
Certiv's Scout endpoint agent is positioned as an independent assurance boundary for coding agents because hooks alone cannot provide AI Agent Assurance, according to a Certiv blog post. The post cites a September 2026 c…
Developer and blogger Lee Robinson released the Next.js MDX Blog Starter Kit, an NPM package that provides a ready-to-customize foundation for building technical blogs with Next.js, React, TypeScript, MDX, Supabase, Tail…
A developer is building a code formatter called sfmt to improve the readability of TypeScript code in the age of AI-assisted programming. The project addresses issues such as IDE screen space, diff noise from formatting,…
ZAI's GLM-5.3, a 743 billion parameter large language model, shows unexpected cybersecurity capabilities, including vulnerability finding and exploit reasoning, that scaled faster than expected with increased post-traini…
Y Combinator's open-source QM agent runtime, version 0.1.4, has drawn 6,600 GitHub stars, 700 forks, 68 pull requests, and 14 open issues within two days of publication, according to a code review by RuntimeWire. The rev…
Dex Horthy, CEO and cofounder of HumanLayer, coined the term 'context engineering' and shared lessons from building AI agents, including that shipping unread code leads to disaster within months after a July 2025 experim…