Full-text search across 68174 articles. Combine with topic and date filters; results sorted by relevance.
A developer migrating from Claude Code to OpenCode found that agent rules were loaded but not followed, a state they call 'loaded but not load-bearing.' They propose a two-lane diagnostic model distinguishing rules that …
Moonshot AI's Kimi K3, a 2.8-trillion-parameter open-weight model with a 1-million-token context window, is now available in GitHub Copilot as of August 6, but Business and Enterprise admins must enable it manually. The …
Linux kernel maintainer Greg Kroah-Hartman removed the Moxa Intellio multiport serial driver, deleting 2,148 lines of code, after AI agents began probing the 27-year-old driver and finding issues that would waste maintai…
On the fourth anniversary of a 2022 tweet, Simon Willison used Claude Fable 5 in Claude Code for web to build a complete browser-based 3D game, 'Raccoon Heist', from the original GPT-3 and DALL-E concept. The game is pla…
Microsoft has expanded its Zero Trust for AI strategy with new tools and guidance to secure AI agents and DevSecOps, including an AI-focused Zero Trust Assessment and a new DevSecOps pillar in the Zero Trust Workshop. Th…
The EU AI Act's Article 50 took effect on August 2, requiring businesses to disclose AI interactions, but upcoming Articles 12, 19, 26, and 86 will demand detailed logging and explainability of AI decisions, which most c…
Five teams maintaining the Rust compiler and standard library — compiler, libs, types, rustdoc, and bootstrap — adopted a formal LLM policy for the rust-lang/rust repository that permits using LLMs for assistance but ban…
Context Goblin, an AI code reviewer developed from the 2026 Bitmovin AI Incubator, analyzes pull requests using a repository graph to understand the broader codebase, aiming to reduce the need for human re-review. The to…
A developer has built Mana, a voice AI assistant that runs entirely on a local machine with an 8GB VRAM GPU, achieving 2-3 second response times by using a single 4B model for reasoning, code generation, and explanation …
GitHub published an August 4 engineering guide detailing a workflow for splitting large AI-generated code changes into dependency-ordered stacks of smaller pull requests using the gh-stack CLI extension and an agent skil…
Microsoft Agent Framework reached version 1.0 general availability on April 2, 2026, and at Build 2026 (June 2-3) the Agent Harness and Foundry Hosted Agents reached general availability, providing a supported production…
A Platform Engineering team at an unnamed company built a self-service system using Amazon Bedrock to generate Terraform code dynamically, but later removed it, concluding that AI reasoning should not be used for determi…
A developer's context layer fails when reused because it hard-codes content instead of acting as an interface, argues a new analysis from InfoWorld. The piece, by an unnamed author, proposes a metadata layer that combine…
A developer reports that multi-agent collaboration is hitting an engineering wall as single-agent systems plateau, citing Mano AFK's experience where splitting coding and testing into separate contexts improved review qu…
Anthropic's February 23, 2026 announcement that Claude Code could automate COBOL modernization analysis triggered a 13.2% drop in IBM shares, the biggest one-day decline since October 18, 2000, according to Reuters. IBM'…
A developer building RAG and agent features in Python for a mid-size SaaS product recommends using a chatbot gateway that exposes one chat API behind one key, allowing model changes via a string, while keeping the fallba…
A developer released NoDiff, a TypeScript framework for rich-client apps that treats TSX as browser syntax, built with LLM assistance and designed to live in a monorepo. The framework, published as @nodiffjs/core, provid…
Tencent Cloud released TencentDB Agent Memory, an MIT-licensed memory hub for AI agent teams that converts conversations, documents, and code into four shareable memory assets—Chat Memory, Skill, Wiki, and CodeGraph—usin…
A developer built an AI evaluation framework for a Minecraft mod's combat advisor agent, using another AI as a judge to score the agent's decisions. The framework combines code-based checks for JSON validity, action boun…
A developer discovered that their MCP server tool, create_article, failed to enforce DEV.to's 4-tag limit, unlike the standalone publish_devto.py script, causing inconsistent behavior between the two code paths. The deve…