Full-text search across 61567 articles. Combine with topic and date filters; results sorted by relevance.
Developer atomic14 released 'Open Vibe Coded Elite – Harmless', a playable remake of the classic game Elite, built with Claude and other AI models. The project, hosted at harmless.atomic14.com, invites users to submit is…
Airbnb CEO Brian Chesky said AI now writes 60% of the company's new code and has cut concept-to-launch time by as much as 60%, helping Airbnb post $3.6 billion in second-quarter revenue. Chesky told CNBC that 'the winner…
Hoang, a Technical SEO Specialist, has joined DEV Community to share his journey of using AI-assisted development, or 'vibe coding,' to build custom web applications and utility tools. He aims to connect with experienced…
Anthropic reported a service disruption affecting Claude Code on the web and related services, with updates available via email and SMS subscriptions.
Google launched Gemini 3.7 Flash, its most intelligent workhorse model for coding and agents, three weeks after Gemini 3.6 Flash. The model scored 43.6% on FrontierCode 1.1 Main (up from 34.4%), 65.3% on DeepSWE v1.1 (up…
Developer Daniel K. released Structured Steering.app, a macOS UI that monitors coding agent threads for implicit assumptions and surfaces them as editable toggles, dropdowns, and sliders in a popup, compatible with ChatG…
Anthropic's Claude Code is experiencing an outage, with users reporting API Error 529 Overloaded, a server-side issue that is usually temporary. The error message advises users to try again shortly and to check https://s…
A developer building BitFun, an open-source remote coding agent, identified a critical failure mode where permission prompts in a desktop UI can deadlock remote jobs. The fix involves modeling permission requests as dura…
Cognition, maker of the AI coding agent Devin, is in talks to raise a new funding round at a $40 billion valuation, according to Bloomberg, just three months after raising $1 billion at a $26 billion valuation. The compa…
Forbes Councils member Ishraq Khan argues that while AI first demonstrated its value in coding, logistics presents a larger opportunity, predicting the next wave will encompass all forms of movement, not just freight. Kh…
Anthropic has made Claude Code auto mode the default for Pro and Team users, citing a study with over 1,000 paid testers where humans caught dangerous commands only 13.6% of the time, while auto mode blocked 89% of those…
Piotr Migdał released an e-ink dashboard plugin for TRMNL X that displays Claude Code and Codex usage, including rate limits, API-equivalent cost per day per agent, and top projects, pushed from a Mac every 10 minutes. T…
A developer built auto-claude, a bash loop that runs Claude Code unattended overnight on a queue of small, well-defined tasks, using verification commands to decide pass or fail. The tool isolates each task in a git work…
A Hacker News user asked for solutions to reduce verbosity in Anthropic's Claude Opus model when used with Claude Code, noting that asking for a TL;DR improves readability but may hide important information. The post, su…
A Hacker News user asks why businesses continue running legacy code despite AI making re-implementation easier, citing Fandango's 15+ year-old ticketing site as buggy and costly. The user argues that rebuilding would rec…
Aaronontheweb, developer of the autonomous AI assistant Netclaw, revealed that ShellSyntaxTree (SST), a parser for bash and PowerShell commands, has been in production for months despite the author rarely reviewing its c…
Ai2rules-harness, a new open-source tool, lets developers govern coding agents with a single command by installing a gate that denies tool calls based on destination path and taint state, not command shape. The tool, whi…
A comparison of four coding harnesses—opencode, pi, jcode, and reasonix—running Deepseek V4 Flash 0731 found significant differences in RAM usage and problem-solving capability, with only two harnesses successfully findi…
1Password confirmed that AI-generated security patches cannot be deployed without expert human code review, establishing human oversight as mandatory for automated vulnerability remediation. The finding limits autonomous…
Vibe coding efforts to clone existing applications often fail because developers replicate only a partial view of the app's behavior, missing implementation details and edge cases, according to a LinkedIn discussion feat…