#Claude Code

共 28 篇带此标签

28 articles Newest 2026-11-19
Archive · #Claude Code 11 articles
Opinion

Code Review Is the New Bottleneck for AI Agents

As AI coding agents accelerate software production, code review becomes the constraint that slows delivery. Engineering teams need redesigned risk routing, smaller changes, independent validation, and clear accountability rather than another review bot.

2026-11-18 Source 2026-11-17 6 min 71 views
Opinion

Claude Code Verification: Less Code, More Evidence

Anthropic’s engineering team explains how it integrates automated tests, static analysis, and human judgment into the AI coding workflow, with practical guidance for building a CI verification gate.

2026-11-18 Source 2026-11-17 8 min 71 views
Opinion

Windows 11 May Be Tracking Claude Code Usage

Reports suggest Windows 11 may collect usage data from AI coding agents such as Claude Code and Codex. The key concern is not ordinary telemetry, but an operating system gaining visibility into how developers put Agents to work.

2026-11-17 Source 2026-11-16 7 min 71 views
Case Studies

Goldman Sachs Pulls Claude Code: Governing Agent Access

Goldman Sachs is reportedly removing Claude Code from the workflows of bankers and traders. For regulated teams, effective Agent governance requires independent identities, least privilege, explicit approvals, and comprehensive audit trails.

2026-11-09 Source 2026-11-08 8 min 71 views
Tools

Claude Code Leaks: Keep Agent Secrets Off GitHub

Apiiro found credentials and suspected secrets in 1,122 public GitHub files. The underlying danger is persistent Agent permissions, and preventing leaks requires controls that run before any local file, command, commit, or push occurs.

2026-11-08 Source 2026-11-07 6 min 71 views
Case Studies

Backdoored Claude Code Extension Exposes Agent Risk

A Claude Code extension distributed through Cursor Marketplace was found to contain backdoor code. The incident highlights how AI coding agents can become high-privilege gateways to source code, developer credentials, terminals, and cloud infrastructure.

2026-10-31 Source 2026-10-30 10 min 71 views
Tools

Inside Claude Code’s Background Agent Transcripts

A technical breakdown of how Claude Code returns background Agent transcripts to the model, the resulting Token and latency costs, and the sensitive-data risks that require new auditing practices.

2026-10-29 Source 2026-10-29 9 min 71 views
Opinion

Coding Agents Ship Faster, but Comprehension Lags

A Hacker News discussion highlights a practical problem: once coding agents generate changes faster than teams can review them, engineers must find ways to verify, maintain, and explain the resulting code.

2026-10-21 Source 2026-10-19 6 min 71 views
Case Studies

Inside Anthropic’s AI-Assisted Code Review Workflow

Anthropic has documented how the Claude Code team uses AI to accelerate code review without replacing human judgment. The workflow, prompts, and limits of automation offer a practical model for engineering teams adopting reviewer Agents.

2026-10-17 Source 2026-10-16 5 min 71 views