Full-text search across 31918 articles. Combine with topic and date filters; results sorted by relevance.
SpaceX has acquired Anysphere, the maker of the AI coding agent Cursor, to build a proprietary AI coding agent model. The deal signals a shift toward vertical integration in developer tools, with plans to deepen model tr…
Anthropic's Claude Code has evolved from a terminal coding assistant into a layered agentic system with distinct memory, hooks, skills, subagents, plugins, and MCP layers. A new guide details 25 features and strategies f…
Loop engineering is emerging as a new paradigm for working with coding agents, where developers design recursive systems that autonomously prompt agents rather than writing prompts manually. Industry leaders like Peter S…
A year after being an obscure term inside AI labs, the "agent harness" has become a critical decision for AI-coding teams in 2026, yet most teams are making that choice accidentally. A harness—comprising context, restrai…
OpenAI's GPT-5.5 outperformed Anthropic's Opus 4.7 and OpenAI's GPT-5.4 on 56 real coding tasks from two open-source repositories, passing more tests and producing patches that more often survived code review. Opus 4.7 w…
A developer at Blume compared built-in Claude Code usage commands, the community CLI ccusage, the Claude Code Usage Monitor, and Blume's desktop dashboard for tracking usage on Pro and Max plans. The comparison highlight…
Anthropic engineer Thariq Shihipar revealed at the AI Engineer World's Fair that the team removed over 80% of Claude Code's system prompt for Opus 5 and Fable 5—shrinking it from roughly 2,686 words to around 514—with no…
A developer's comparison of GitHub Copilot, OpenAI Codex, and Claude Code as of July 2026 finds all three have shifted to token-based pricing and metered usage. GitHub Copilot offers a free tier and $10 Pro plan, Codex s…
Claude Code v2.1.172 now allows subagents to spawn their own subagents up to 5 levels deep, enabling autonomous multi-agent pipelines. Developer UCJung migrated their uc-taskmanager pipeline to use a nested orchestrator …
Network expert Glenn Fiedler, a leader at Network Next, warns game programmers to fix security bugs in their code after using Anthropic's Claude Code Fable 5 to review his own open-source networking libraries, which foun…
AI coding tools can turn an idea into a working prototype in under half an hour, but shipping a finished experience takes weeks, according to a practical workflow guide based on the creation of GitHits Agent Runner. The …
A developer released cc-context-telemetry, an open-source tool that displays Claude Code's context window percentage, Pro/Max rate-limit usage with reset countdowns, and the current model in the statusline bar. The tool …
Amazon Web Services (AWS) expanded its DevOps Agent with new release management capabilities, including Release Readiness Review and Autonomous Release Testing, now available in preview. The features assess code changes …
A Faros AI study of 22,000 developers across 4,000 teams found that AI coding tools boosted PR counts by 98% but tripled production incidents per PR, with code churn jumping 10x and bugs per developer up 54%. The phenome…
A developer finds that large language models like Claude generate verbose, legacy code patterns that increase token costs, especially output tokens which are 3-5x more expensive than input tokens. The author argues that …
Figma announced code layers and AI plugin tools at Config 2026, enabling teams to clone repositories, convert components into editable code-backed layers, and build custom plugins via text prompts. The updates include na…
A developer released a collection of 100 prompt shortcuts that change how Claude responds, with an interactive version available at clskills.in/prompts. The shortcuts include codes like /ghost to rewrite text to avoid AI…
Developer David P. V. released a stack-agnostic CLI tool called opsx that enforces spec-driven development workflows on top of OpenSpec, supporting agent CLIs including OpenCode, Claude Code, and Codex. The tool separate…
Anthropic researchers found that junior developers using AI assistants scored 50% on a comprehension quiz versus 67% for those working without AI, a gap termed 'cognitive debt.' Studies from METR, MIT Media Lab, and othe…
Researchers from UC Berkeley and other institutions released CommBench, a benchmark of over 100 GPU communication problems, to evaluate whether large language models can generate correct and efficient multi-device commun…