Full-text search across 61544 articles. Combine with topic and date filters; results sorted by relevance.
Claude Code's status line can be configured to run a Ruby script, as demonstrated by developer Lucian Ghinda, who shared a setup using a `statusLine` command in `settings.json` to display context window usage, git branch…
Toronto-based AI startup Blueprint has raised $1.4 million CAD in funding, backed by Andreessen Horowitz (a16z), to develop a platform that enables users to turn text prompts into hardware prototypes, described as 'Lovab…
A developer used Anthropic's Claude Code with Opus 4.8 over a four-hour session to reverse-engineer the SPL3 raster language and run HP's real codec in a Linux container, enabling macOS to natively print to the HP Laser …
Cronloop, a new service that schedules AI agents built on Claude Code or Codex, launched on Hacker News, allowing users to run agents on intervals from every five minutes to once a week with persistent memory and integra…
A new arXiv paper (2608.14711v1) reveals that AI coding agent benchmarks misapply the pass@k estimator, inflating reported scores by 0.85-0.97 in absolute terms (0.96-0.98 reported vs. 0.00-0.12 corrected). The authors p…
Microsoft's VS Code 1.133, released August 12, introduces the Agent Host Protocol (AHP), an open specification that runs AI agent sessions in a standalone process, persists them across window closures, and enables multip…
Watermark Scanner, a free browser-based tool, lets users paste text or code to detect and decode hidden characters, including zero-width marks and AI-generated watermarks, with options to scan files and copy cleaned text…
A new arXiv study (2608.13568v1) finds that semantic retrieval via the Language Server Protocol (LSP) is not more token-efficient than lexical grep for coding agents, with token costs increasing by +6% to +118% on symbol…
Developers are building specialized agent tools for desktop automation and code tasks, including Velorn (AI video editing with agent control), Premiss (AI crypto trading bot builder), and agent-desktop (UI state reliabil…
Claude Code 2.1.232 introduces significant changes including forked subagents inheriting full conversation and prompt cache by default, interactive non-teammate spawns moving to the background, and Windows permission byp…
DeepSeek released a new coding harness designed to improve developer workflows, while xAI's Grok model has advanced closer to frontier performance, and Writer introduced a new model aimed at cost-conscious AI developers,…
A developer has released LiquidGlassSkill, a Claude Code plugin that implements realistic glassmorphism with actual refraction instead of the standard blur-plus-overlay effect. The technique uses a displacement map and S…
A developer spent three years building software without shipping a single product, then spent four months interviewing veterinary clinics to validate demand, only to find most had already solved their problems. After los…
An engineer discovered that a simple prompt to rename a root directory caused an AI coding agent's session to become unresponsive. The rename succeeded, but the IDE and agent session still pointed to the old path, orphan…
A first-year engineering physics student built WorkThoseKeys, a typing trainer with 31 sub-levels and per-bigram error tracking, using the AI app builder Lovable instead of hand-coding. The tool separates keyboard layout…
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…