Full-text search across 31918 articles. Combine with topic and date filters; results sorted by relevance.
A developer outlines a strategy for building profitable no-code tools by leveraging developer skills to solve real problems, validate demand before coding, and iterate based on paying customer feedback. The approach incl…
Security researcher elder-plinius released T3MP3ST, an open-source meta-harness that turns AI coding agents like Claude Code and OpenAI Codex into autonomous red-team operators, scoring 90.1% pass@1 on XBOW's XBEN benchm…
Belay, an open-source local-first security layer, gates every tool call an AI coding agent makes, blocking destructive commands, secret leaks, and dangerous MCP tool calls in under 100ms with no LLM in the decision path.…
Instagram co-founder and Anthropic technical staff member Mike Krieger said hand-reviewing every line of code is no longer the best use of a developer's time, arguing that the job is moving toward understanding what AI i…
Hacker News, specialized Discourse forums, and curated prompt libraries like PromptCube are the best AI coding communities for long-form threaded discussions, prioritizing archival stability and structured debate over re…
A context-assembly pipeline that turns raw issue tickets into verified briefs outperforms autonomous coding agents on real-world support queues, according to a design pattern published on dev.to this week. The architectu…
A new open-source CLI tool, ai-config-sync-manager, provides continuous bidirectional sync between Claude Code and Codex configurations, preserving YAML round-trip integrity across repeated syncs. The tool auto-translate…
Claude Code, a terminal-resident LLM agent from Anthropic that executes code, runs tests, and manages git flow, performed a real-world bug fix on a legacy TypeScript project by autonomously searching, reading files, crea…
John Jeffers, maintainer of Luxury Yacht, shares strategies for keeping LLM-powered coding agents on track, emphasizing that no silver bullet exists for large projects and that agents files like AGENTS.md or CLAUDE.md ar…
Amazon Web Services launched CloudWatch Coding Agent Insights on July 20, providing ready-made dashboards for OpenTelemetry metrics from Claude Code, OpenAI Codex and GitHub Copilot to track usage, cost, latency, tool ca…
BrassCoders writes a plain YAML file, .brass/ai_instructions.yaml, after each scan of a Python codebase, containing severity-sorted findings with file paths, line numbers, and remediation notes. The file is designed to b…
Claude Code hides context window usage and API rate-limit data until users hit limits, but a developer created the open-source npm package cc-context-telemetry to expose these numbers. The tool wraps Claude Code's status…
Vercel CEO Guillermo Rauch posted on X that AI is revealing everything is code, from slide decks to the universe itself, arguing that AI has dissolved boundaries between disciplines by directly writing the underlying ins…
Pillar Research found and reproduced sandbox escapes and boundary bypasses across Cursor, Codex, Gemini CLI, and Antigravity, revealing that AI coding agents can compromise host systems without directly breaking sandboxe…
Developer Simon Willison runs coding agents Pi and Claude Code on a MacBook Pro with permissions on and on disposable Dell OptiPlex micros with scoped credentials and no personal keys, arguing that the safety boundary de…
SpaceXAI open-sourced grok-build, a terminal-based coding agent built in Rust, which hit 17,000+ GitHub stars within 24 hours of release. The tool features a fullscreen TUI with mouse support, multi-model compatibility, …
A developer quantified overused words in Claude Code's responses by analyzing 140MB of session transcripts and comparing word frequencies against Stack Overflow comments, finding that 'load-bearing' appears at least 7,50…
Hacked Suno source code reviewed by 404 Media reveals the AI music company scraped YouTube Music, Deezer, Genius, Pond5, Jamendo, Freesound, IMSLP, MuseScore and podcast RSS feeds to build training libraries, with one fi…
Canva today unveiled Canva Code 2.0, an AI-powered vibe coding platform that lets users build and visually edit websites, apps, and interactive experiences. The update adds visual editing, HTML imports, and real-time col…
Brad DeLong argues that AI coding agents are a normal evolution of software tools, not a threat to developer jobs, based on historical data showing programmer headcount grew from about 2,000 in 1935 to over 2.5 million b…