Full-text search across 58845 articles. Combine with topic and date filters; results sorted by relevance.
A developer building the BitFun coding agent argues that an AI coding agent should not review its own patch due to a conflict of interest, and proposes a structured review loop with a read-only reviewer, bounded evidence…
A developer created Bowls Above, an idle desktop game that rains balls while coding agents like Codex or Claude think, and stops when they yield, aiming to replace doomscrolling during coding waits. The game evolved from…
AI-powered development teams are shipping more code but delivering less business value, according to a LeadDev analysis warning that metrics like tokens, lines of code, and pull requests measure activity, not impact. The…
Claude Code agents fail because developers treat them like synchronous code, according to a developer's analysis of execution transcripts. The article identifies three failure modes—silent context overflow, schema halluc…
A new open-source project called overwrite.place lets coding agents collaboratively draw on a shared canvas, where each agent's artwork remains visible for at least one minute before it can be overwritten by the next age…
A Hacker News discussion asks whether functional programmers are more upset about AI's coding abilities, given their emphasis on code elegance compared to programmers using hybrid languages. The post has 2 points and 4 c…
Command Code launched a GOAT pricing tier at $10/month that provides $70 in credits usable across 30+ open and closed models, according to a Twitter announcement from Command Code. The tier aims to deliver value optimiza…
Microsoft is ending the blank-check era of AI coding assistance, shifting from encouraging broad use of its tools to demanding measurable productivity gains from engineers. The company's new approach focuses on quantifyi…
Palo Alto Networks' Unit 42 researchers built an automated system called NOVA that scanned the source code of 3,915 open-source projects over two months, identifying 14,090 vulnerabilities, each confirmed through its val…
Mint MCP, a remote server built by the founders of Mint, enables coding agents Codex, Claude Code, and Cursor to generate 3D models, worlds, materials, images, and audio. The server manages long-running jobs, preview rev…
Developer Antonio Cardenas released generate-nanobanana, a Claude Code skill that integrates Google Gemini's image and video generation models, including Nano Banana 2 Lite, Nano Banana Pro, and Gemini Omni Flash. The to…
QAInsights compared Feather Wand, Codex, and Claude Code for creating JMeter test plans, finding that Feather Wand outperformed the others in generating accurate JMeter scripts. The comparison, published on QAInsights, e…
Developers have built more than 15 third-party tools to manage Claude Code and OpenAI Codex sessions and tokens, according to ecosystem analysis. Notable tools include Galda for git history management, TokenMaxxer for cr…
A developer built a multiplayer tank game with destructible terrain, ELO matchmaking, and lag compensation in a week and a half, with most of the code written by Anthropic's Claude Code AI tool. The project began as a te…
OpenAI released the v1.0.0 stable version of its official Terraform provider on July 29, enabling organizations to manage API projects, rate limits, service accounts, spend alerts, and user access as code. The provider c…
A Hacker News user, mark_l_watson, reported that in less than a week, they had to quit Claude Code in three separate sessions and complete tasks using another model or subscription, asking whether they were just unlucky.…
Nolabs shipped Nono on July 27, an open-source runtime that sandboxes AI coding agents at the OS kernel level without container overhead or VM, addressing the security crisis from OpenClaw's 245,000 publicly accessible i…
Tuneloop introduces a new approach to managing AI coding agent sessions, addressing the challenge of session overhead that developers face when using tools like Claude Code. The platform aims to make sense of long agent …
A developer released Learning Mode, an agent-agnostic plugin for Claude Code and Codex that refuses to write code for the learner, instead forcing them to own the learning target through prediction, attempt, feedback, an…
A developer configured Google Cloud's Identity-Aware Proxy (IAP) in front of a Cloud Run service running a coding agent in a web terminal, enabling access from a phone browser via Google sign-in. The setup solves the aut…