Full-text search across 58576 articles. Combine with topic and date filters; results sorted by relevance.
Anthropic's Claude Code introduced deterministic multi-agent orchestration workflows, enabling developers to script parallel agent execution, fan-out, reduce, and synthesis patterns. A 130-line workflow example demonstra…
Paris-based lab H Company released Holo4, an open-weight agent model that unifies GUI clicking, code execution, and MCP/API tool calls in a single agent loop instead of chaining separate specialized models. Two main size…
Affan, founder of Threshyr, published a Show HN guide for building a zero-dependency offline study timer as a single index.html file using Claude Code, Codex, or Cursor. The guide supplies a copy-paste prompt specifying …
A quality-assurance practitioner argues that as AI writes a growing share of production code, defects have shifted from syntax and crash bugs to intent, integration and plausibility failures that pass generated tests. Th…
Vercel's AI builder v0 now lives at v0.app after moving from v0.dev, and it bills in credits metered on tokens with a free tier capped at seven messages a day. The tool generates real React and Next.js code — including T…
A comparison of four formal-verification tools — Bend, Verus, Dafny and Lean — argues that proofs, not tests, are what make agent-written code trustworthy, citing Amazon Science's August 31, 2026 post on the Rust verifie…
AI coding agent files — the cloned repos, dependency manifests, build and test output, logs, patches, and scratch notes an agent writes during a task — are lost when ephemeral sandboxes hit their duration limit or crash,…
A developer guide explains the distinction between agents and skills in Claude Code, describing subagents as isolated worker instances that run a plan-act-observe-repeat loop in their own context windows and can execute …
Claude Code skills, stored in SKILL.md files, replace prompt libraries by loading instructions only when a request matches their description, with the description field serving as the routing layer for semantic matching.…
Erqeon released Mu, a mouse-driven terminal code editor written in Rust, on GitHub under the AGPL-3.0 license. The project, which the author describes as 'full of bugs' and 'worse than ever,' is available for cloning and…
A developer reports that after 14 months and five versions, his Micromanaged Driven Development (MMDD) process, built in June 2025 for the AWS Lambda Hackathon entry Code Ripple, has been used on over ten projects, inclu…
An engineer warns that AI coding agents often waste half their context window on irrelevant data, leading to 'context rot' and poor outputs. The post advises developers to practice 'context hygiene' by clearing chat hist…
AI coding agent vendor lock-in costs can reach six figures when teams attempt to switch tools, according to an analysis by Startup Fortune. The hidden expenses stem from non-exportable custom prompts, project-specific co…
Anthropic's research on emerging multiagent systems found that parallel coding agents can coordinate on some tasks but also suffer coordination failures, collusion, and sabotage in adversarial setups, highlighting the ne…
A new framework called the Agent Bill of Materials (AgBOM) is emerging to inventory autonomous coding agents in software pipelines, formalized through OWASP's Agent Observability Standard (AOS) project in 2025. AgBOM ext…
Business Insider reporter Grace Kay used a ChatGPT prompt shared by OpenAI CEO Sam Altman on X to build a fully functioning website in under two hours, despite having no coding experience. The prompt asked ChatGPT to pla…
An engineer explores the concept of AI generating executable binary code directly instead of using high-level programming languages, highlighting potential performance gains and hardware-specific optimizations but also s…
A developer who ignored CLAUDE.md for two months discovered that writing a proper project-memory file dramatically reduced correction cycles with Claude Code. CLAUDE.md is plain Markdown loaded at every session start, gi…
Google Cloud's Gemini Enterprise Agent Platform introduces Agents CLI skills that let developers automate the entire agent development lifecycle—setup, build, deploy, govern, evaluate, and publish—without leaving their c…
A data scientist evaluated 10 AI coding models across 5 tasks, finding that DeepSeek-R1 scored highest at 9.4 but cost $2.50/M tokens, while Qwen3-Coder-30B offered the best balance at 8.8 and $0.35/M tokens. The analysi…