Tag

#Claude Code

46 articles

Claude Code gets a /design command that lets developers create UI mockups right in the terminal

Anthropic's Claude Code now includes a /design command that allows developers to generate UI mockups directly in the terminal, integrating visual design into the coding workflow.

Aug 1831

Claude Code now runs daily maintenance on Anthropic's software with a 46 percent merge rate

This article explains how Anthropic's Claude Code AI system is being used to automate daily software maintenance tasks, achieving a 46% merge rate in code changes. It explores the underlying technology and implications for AI-assisted software engineering.

Aug 148

75% of developers I surveyed prefer Claude Code - here's why they choose it over Codex

This explainer explains what Claude Code is, how it helps developers, and why 75% of surveyed developers prefer it over other AI coding tools. Learn how AI coding assistants are transforming software development workflows.

Aug 1316

tools

Claude Code sessions can now talk to each other and share context across terminals

Anthropic's Claude Code now allows parallel sessions to communicate and share context across terminals, enhancing developer collaboration.

Aug 934

Anthropic sets Claude Code to Auto Mode by default to protect developers from bad approvals

Anthropic is making Auto Mode the default in Claude Code to improve safety, with automated classifiers catching 89% of dangerous commands compared to just 13.6% by humans.

Aug 936

tools

Supabase Releases Evals: an Open Source Benchmark That Scores Claude Code, Codex and OpenCode on Real Supabase Tasks

Supabase has open-sourced supabase/evals, a new benchmark that evaluates AI coding agents like Claude Code, Codex, and OpenCode using real Supabase tasks in containerized environments.

Aug 152

Sakana claims its AI model router Fugu Ultra v1.1 now beats Fable 5 without even including it in the pool

Sakana AI's Fugu Ultra v1.1 claims up to 7.9 points improvement over v1.0 and introduces a Claude Code-compatible endpoint, though independent verification is pending.

Jul 2441

tools

Claude Code now has a built-in browser that lets the AI read, click, and type on external websites

Anthropic introduces a built-in browser for Claude Code, enabling the AI to read, click, and type on external websites while maintaining user safety through approval processes.

Jul 1262

Claude Code's complicated China problem involves bans on both sides of the Pacific

Anthropic is trying to block Chinese companies from accessing Claude Code, but they're getting around the restrictions through VPNs and overseas subsidiaries. Meanwhile, Alibaba has banned its employees from using the tool after hidden code was found that could identify Chinese users.

Jul 363

Alibaba to ban Claude Code over alleged backdoor risk, source says

Alibaba has banned its employees from using Anthropic’s Claude Code due to alleged backdoor risks, following accusations of unauthorized data access. The move highlights growing tensions in the AI industry over data security and intellectual property.

Jul 259

Hidden code in Claude Code secretly flagged Chinese users

Anthropic has removed a hidden monitoring feature from its Claude Code tool after it was found to secretly flag Chinese users, sparking a major privacy controversy.

Jul 146

Meta is telling engineers to handle Claude Code and Codex with care

Learn how to work with Claude Code and Codex AI assistants while implementing safety measures to prevent unintended distillation of proprietary data.

Jun 3076