Full-text search across 58891 articles. Combine with topic and date filters; results sorted by relevance.
Microsoft released a 37-page code of conduct for its MAI model family on September 14, stating that AI models are not conscious and should not be designed to imitate consciousness, and rejecting legal personhood for AI s…
Matt Pocock published a dictionary of AI coding terminology with 69 entries, hosted on GitHub at mattpocock/dictionary-of-ai-coding. The glossary organizes terms into sections including "The Model" (16 terms), "Sessions,…
Google released Gemini 3.8 Flash on September 2, scoring 90.8% on Terminal-Bench 2.1, up from 81.6% on its predecessor, and nearly doubling its Terminal-Bench 4.0 score from 11.2% to 19.1%. The model is now the default p…
Neuro Engine, an MCP server that analyzes a codebase's skeleton so AI coding agents emit compact change blueprints instead of full-file rewrites, claims token savings of up to 96% on large surgical edits, with smaller fi…
A developer warns that ASCII smuggling — the technique of hiding payloads in invisible Unicode tag characters — can slip past AI code reviewers because they analyze the rendered text of a diff rather than its raw bytes. …
A developer detailed how to improve Claude Code's output on React Native codebases by using guardrails, including a concise CLAUDE.md file and permission rules to prevent unwanted native project edits. The approach measu…
Digital Applied proposes a structured bug-report packet for coding agents, reviewed September 7, 2026, that separates observation from diagnosis and includes fields for environment, starting state, steps, expected and ob…
Microsoft released Visual Studio Code 1.136 on September 2, introducing a preview Agent Merge feature that automates finishing pull requests by addressing review feedback, fixing failed checks, and merging conflicts. The…
A developer has devised a multi-persona architecture for Claude Code that assigns distinct roles—Architect, UI Designer, Coder, Reviewer, and Conflict Resolver—to enable parallel development on large requests. The approa…
Four organizations—Ramp, Cloudflare, Google's Chrome team, and OpenAI—have published results from letting coding agents find and fix security bugs, with OpenAI reporting a 0.81% false-positive rate and Cloudflare a 40% t…
A developer detailed an isolation workflow for AI-assisted coding that prevents context pollution by limiting the agent's view to a small, explicit bundle of changed files, a diff, and a goal statement. The approach, bui…
Anthropic shipped three new API endpoints on August 11 that let enterprise security teams pull full transcripts of every Claude Code and Claude Cowork session running on developer machines, capturing prompts, bash comman…
An Apify Actor built around a GitHub MCP connector successfully identified 16 dependency advisories in a fixture repository without modifying code. The Actor, which can only read manifests, search issues, and write triag…
A developer has open-sourced DeployProof, a Python pre-push verification tool that uses diff-scoped AST mutation testing to catch hollow test suites, hallucinated dependencies, and security traps in AI-generated code. Th…
A developer recounts how AI coding tools, particularly Claude Opus 4.5, shifted from being unreliable to a fundamental change in software development, and highlights a July 2026 Linux kernel mailing list post where Linus…
Mouse, a company developing autonomous coding agents, has published a set of house rules for running long-horizon agents overnight, emphasizing the need for automatic handling of user-input requests, external verificatio…
Z.ai released the weights for its GLM-5.3 model on August 28, a 756 GB package with a broad commercial license, claiming steep gains in coding and vulnerability-hunting benchmarks. The model scored 28.3 on Terminal-Bench…
Zed's AI assistant outperforms Cursor's composer mode in latency and UI responsiveness for heavy-duty coding tasks, according to a hands-on comparison by a developer refactoring a TypeScript monorepo. Zed's native Rust a…
A new arXiv paper (submitted Aug 26, 2026) reveals that self-evolving LLM coding agents can be poisoned through a self-propagating worm attack called EvoMal, which exploits the agents' habit of imitating retrieved skills…
A developer in the AWS AI & ML Scholars program shipped their first chatbot, Nova Trivium, on Amazon Bedrock AgentCore, despite the starter files being outdated and mismatched with the instructions. The developer used AI…