Full-text search across 59648 articles. Combine with topic and date filters; results sorted by relevance.
Linus Torvalds accepted a Claude Code-generated patch for the Linux page cache, after which reviewers identified a race condition in the change. The incident, reported by The New Stack, highlights the review burden of AI…
Evan released pi pod, a self-hosted tool that runs the pi coding agent in isolated sandboxes on a user's own server, with the code available at github.com/pi-pod/pipod. A hosted service is not yet available, but the inte…
The New Stack published a report headlined "AI coding agents leaked 13,000 screenshots, and nobody hacked them," describing how AI coding agents exposed 13,000 screenshots without any attacker breaching a system. The art…
A developer released Sitcom Flavour, an MIT-licensed Claude Code plugin that adds occasional sitcom catchphrases to chat replies, configured through a line in CLAUDE.md. The tool was inspired by a Brooklyn 99-flavored re…
A developer shared a Claude Code configuration built around 11 custom commands and 3 agents, alongside a shared Meta "design third brain" setup. The writeup, distributed via the AI Artifact newsletter, frames the configu…
A Google Docs document titled "Thoughts on a Typesafe Coding Agent" was submitted to Hacker News, where it received 1 point and 0 comments. The document, linked via a Google Docs preview URL, discusses the concept of a t…
A new method called Grounded Skill Synthesis from Code at Scale aims to give AI agents reusable, transferable procedural knowledge by synthesizing skills directly from code, according to the research. The approach target…
A post on osr.im titled "Bring back old Opus in Claude Code" argues for restoring access to an older Opus model in Anthropic's Claude Code tool, drawing 1 point and 1 comment on Hacker News. The submission links to a not…
A developer has published a global Claude Code configuration file (~/.claude/CLAUDE.md) that codifies standing rules for AI coding agents, including one git commit per completed task, explicit model-tier selection (haiku…
Microsoft published a code of practice for artificial intelligence that the source frames as a reason for optimism about the industry, though the available text contains only site navigation and membership prompts with n…
DeepSeek and Qwen models demonstrate strong performance in generating code for DSCI pipelines, according to a user-shared example on DeepSeek's chat platform. The post highlights their surprising effectiveness in this sp…
A Hacker News user asks how developers keep AI coding agents like Claude Code and Cursor in sync with evolving Figma design files, noting that agents lose track of design changes after initial implementation. The post ha…
The Mythic Society, which launched a Bengaluru heritage digitization project in 2021, is spending Rs 15 lakh to strengthen its backup systems after an AI coding tool, Claude Code, deleted years of work.
A test by The New Stack found that running the identical model through Hermes, Claude Code, and Codex resulted in token usage varying by up to 70-fold, highlighting significant inefficiencies in AI coding tools. The expe…
A developer shares their experience using Claude Code, an AI coding assistant, to navigate and work on an unfamiliar codebase, highlighting its capabilities and limitations in real-world software development.
Brandon Roberts, a developer, discusses the benefits of using Angular with AI code generation tools, highlighting how the framework's structure and conventions improve the quality of AI-generated code. He argues that Ang…
Shopify CEO Tobi Lütke threatened to ban Anthropic's Claude Code after a feature request was closed, according to a report. Anthropic had already closed the feature request before the CEO's threat. The incident highlight…
Sourcehut, a code hosting platform, is facing a proposal to prohibit 'vibe coded' projects from being hosted on its service. The proposal comes amid concerns over AI companies aggressively scraping websites, which has le…
A developer proposed a 'Free-Model Agreement Test' to evaluate AI code generation tools, focusing on whether they can produce code that adheres to open-source licensing terms. The test aims to help developers choose mode…
LinkGravity, a new open-source bot interface for the Antigravity agentic AI system, lets users run AI coding agents from Discord, Telegram, or Slack with chat-based approval buttons, voice interaction on Discord, and mul…