Anthropic has launched routines for Claude Code, enabling AI to automatically fix bugs, review pull requests, and respond to events without requiring user intervention on local machines.
Anthropic's new routines feature expands Claude Code's capabilities by automating core development workflows. The system can independently execute bug fixes, conduct code reviews, and handle event-driven tasks—removing the need for developers to manually trigger these processes.
Routines operate as background processes that execute without consuming local computational resources. This architecture allows teams to deploy Claude Code across their development pipeline, handling repetitive code quality tasks at scale.
Key use cases include automated bug detection and patching, asynchronous pull request analysis, and event-based code modifications triggered by repository changes or CI/CD pipelines. Developers can configure routines to respond to specific conditions, streamlining code maintenance workflows.
The feature addresses a practical gap in AI-assisted development: many tasks don't require real-time user interaction but benefit from continuous monitoring. By removing this bottleneck, routines enable teams to maintain code quality standards without manual oversight.
Anthropic's documentation at code.claude.com provides implementation details for developers interested in configuring custom routines. The feature has already generated significant developer interest, with the announcement attracting substantial engagement on Hacker News.
This release positions Claude Code as a more autonomous development tool, moving beyond chat-based assistance toward integrated infrastructure components. Teams can now embed AI-driven code analysis directly into their development processes, treating it as a standard tool alongside existing linters and formatters.
The broader implication suggests AI coding tools are transitioning from interactive assistants to background workers capable of handling sustained, unsupervised tasks—a shift that could reshape how teams approach code maintenance and quality assurance.
A developer who scraped artwork for AI training is now collaborating with Cara, a creator platform designed to prevent unauthorized AI data collection, as the service faces ongoing attacks from trolls attempting to breach and publish its data.
Installing a large language model on your personal computer creates a private digital assistant without uploading data to external servers. This approach keeps your information secure while giving you full control over the AI.
LAION has published Big Video Dataset (BVD), an open collection containing 80 million videos and 10 million hours of footage designed for AI research. Models trained on BVD outperform the previous benchmark InternVid by up to 2.1 percentage points.
As generative audio tools improve, AI-created music floods the internet. Some creators deny using the technology until public pressure forces them to confess.