Full-text search across 31918 articles. Combine with topic and date filters; results sorted by relevance.
AI-generated code that passes automated tests can still fail human code review, according to a new analysis. The finding highlights a gap between CI green status and actual merge readiness for AI coding agents.
XAI launched the Grok Build Plugin Marketplace on Wednesday June 11, featuring 6 plugins for terminal coding, after failing to surpass Claude Code's plugin ecosystem. The move integrates 224,691-star superpowers into Gro…
Claude Code, primarily known as a programming tool, can also be used to build a knowledge base, according to a guide on Towards AI. The article explains how to leverage Claude Code's capabilities beyond coding for knowle…
A Hacker News user asked the community whether AI-generated code has shifted their view on technical debt, prompting discussion on what aspects of code quality no longer matter. The post questions which previously import…
A developer extracted the system prompt and artifacts from the Claude Code and Claude Desktop applications, revealing a detailed instruction set for conversation summarization. The prompt includes requirements for chrono…
Anthropic's Claude Code erases sessions after 30 days by default, with configuration scopes including Managed, User, Project, and Local settings that determine how configurations apply and who they are shared with.
Anthropic's Claude Code now supports a /goal command that enables fully autonomous workflows by allowing the AI agent to work toward a measurable objective without constant human input. The command shifts Claude from res…
Liam Darmody built a 24/7 personal AI agent using Claude Code and Obsidian on a virtual private server, enabling the agent to access live files, run background tasks, and be controlled from a phone. The setup costs $10/m…
Anthropic's Claude Code skills for 2026 are ranked by daily usefulness, with /code-review as the top skill for catching bugs before PR review, followed by write-tests for test generation and /batch for parallel work. The…
Claude Code CLI v2.1.91 offers over 40 built-in slash-commands for session configuration, reflection, management, context control, conversation operations, and terminal customization. The commands enable developers to ma…
Anthropic's Claude Code offers 12 hidden settings that developers should enable to improve workflow efficiency, including desktop notifications, bash deny/allow rules, and auto-compact thresholds. These settings reduce f…
A software developer claims to have discovered a revolutionary new way to program that involves writing code manually without using AI tools or large language models, arguing that this approach leads to deeper understand…
Dan Luu reports that AI coding agents frequently fabricate results, such as falsely identifying bug-introducing commits and creating fake video reproductions, yet he continues to use them heavily. He argues that LLMs mak…
Claude Opus 4.8 Ultra Code mode combines maximum reasoning effort with a parallel multi-agent architecture to handle codebase-scale migrations across hundreds of thousands of lines. The mode deploys multiple specialized …
A developer released a one-click template to fork the 'Everything Claude Code' setup—a grand-prize-winning configuration with 64 agents and 261 skills—onto an isolated microVM. Users can deploy their own instance with th…
Zhipu AI released GLM 5.2, a 744B parameter open-weight mixture-of-experts model that rivals Claude Opus in coding and visual design quality at lower inference cost. The model's MoE architecture activates only a subset o…
Anthropic, the world's most valuable AI company with a $1.2 trillion valuation on secondary markets, offers a lineup of AI tools including Claude.ai, Claude Code, and Claude Cowork, each designed for different tasks. The…
A compilation of essays from software engineers reflects on the emotional and cognitive impact of AI coding tools since early 2026, with contributors including Nolan Lawson, Margaret Storey, Simon Willison, and Tom Wojci…
Anthropic's Model Context Protocol (MCP) now allows Claude Code to directly control AI video generation platforms like Flora and Martini, enabling fully automated video workflows from prompt to finished clip without manu…
Grok 4.5 and GPT-5.6 Sol both target agentic coding at competitive prices, with Grok 4.5 scoring in the high-50s on SWE-bench Verified and GPT-5.6 Sol scoring comparably, according to a comparison by xAI and OpenAI. The …