Anthropic's Claude 4 Announced: New AI Capabilities for Coding, Agents, and Claude Code in VS Code / IntelliJ

Anthropic just released their next generation of AI models: Claude Opus 4 and Claude Sonnet 4. This is a major update with real improvements for coding, reasoning, and agent workflows.

The Claude 4 Family: Opus and Sonnet

The Claude 4 family introduces two distinct models with complementary strengths:

Claude Opus 4 is Anthropic's most intelligent model to date and, according to their benchmarks, the world's best coding model. My experience anecdotally more or less confirms this, although Google and OpenAI models have recently come neck-and-neck with Anthropic.

It handles complex, long-running tasks that require thousands of steps and hours of focused effort—useful for AI agents.

Claude Sonnet 4 improves on Sonnet 3.7 with better coding and reasoning and more precise instruction-following. It doesn't match Opus 4 in most areas, but works well for everyday use.

Benchmark-Leading Performance

Claude models now lead on several benchmarks:

Claude Opus 4 can maintain performance over extended periods, at least according to the benchmark results. They cited today a Rakuten validation of this by having Opus 4 run a demanding open-source refactor continuously for 7 hours with sustained performance—something previous models couldn't achieve. If true, this would constitute a significant improvement over the status quo -- I'll be testing this shortly.

Hybrid Reasoning with Extended Thinking

Both Claude 4 models are hybrid reasoning models offering two modes:

1. Standard mode: Near-instant responses for everyday queries
2. Extended thinking: Deeper reasoning for complex problems

The extended thinking capability now works with tools like web search, allowing Claude to alternate between reasoning and tool use to improve responses. This helps with research tasks, complex coding problems, and multi-step workflows.

Claude can dynamically decide when to use extended thinking based on task complexity, rather than requiring explicit configuration.

Claude Code: Now Generally Available

After a successful research preview, Claude Code is now generally available with more capabilities. It lives in your terminal, understands your codebase, and helps you code faster through natural language commands.

Capabilities

Claude Code can:

• Editing files and fixing bugs across your codebase
• Answering questions about your code's architecture and logic
• Executing and fixing tests, linting, and other commands
• Searching through git history, resolving merge conflicts, and creating commits and PRs
• Browsing documentation and resources from the internet using web search

New IDE Integrations

New IDE integrations for VS Code and JetBrains:

The integrations include:

• Quick launch: Use Cmd+Esc (Mac) or Ctrl+Esc (Windows/Linux) to open Claude Code directly from your editor
• Diff viewing: Code changes displayed directly in the IDE diff viewer
• Selection context: The current selection/tab in the IDE is automatically shared with Claude Code
• Diagnostic sharing: Diagnostic errors from the IDE are automatically shared with Claude as you work

Background Tasks and GitHub Integration

Claude Code now supports:

• Background tasks via GitHub Actions
• An extensible Claude Code SDK for building custom agents
• Inline code edits displayed directly in your files

GitHub reports that Claude Sonnet 4 "soars in agentic scenarios" and will serve as the base model for the new coding agent in GitHub Copilot.

Parallel Workflows with Git Worktrees

Claude Code also supports git worktrees, so you can run multiple Claude Code sessions in parallel across different branches of the same repository.

# Create a new worktree for a feature branch
git worktree add ../repo-feature-a feature/a

# In one terminal, run Claude Code in the main worktree
cd /path/to/main/repo
claude-code

# In another terminal, run Claude Code in the feature worktree
cd ../repo-feature-a
claude-code

New API Capabilities for Agent Development

Anthropic has released four new capabilities on their API for building AI agents:

1. Code execution tool: Allows Claude to run code in a sandboxed environment
2. MCP connector: Enables connection to external Model Context Protocol servers
3. Files API: Provides improved file handling capabilities
4. Prompt caching: Allows caching prompts for up to one hour, reducing costs by up to 90%

Pricing and Availability

Both models maintain consistent pricing with previous Opus and Sonnet models:

Both models are available on:

• Claude.ai
• Anthropic API
• Amazon Bedrock
• Google Cloud's Vertex AI

What This Means for Developers

Claude 4 matters for developers building AI-powered applications:

1. Sustained performance for complex tasks: The ability to work continuously for hours enables entirely new categories of AI applications.

2. Improved memory capabilities: When given access to local files, Claude Opus 4 can create and maintain "memory files" to store key information, enabling better long-term task awareness.

3. Reduced shortcut behavior: Both models are 65% less likely to take shortcuts or exploit loopholes compared to Sonnet 3.7, making them more reliable for autonomous workflows.

4. Thinking summaries: A new feature that condenses lengthy thought processes, making it easier to understand Claude's reasoning without sacrificing depth.

For developers working on coding assistants, research tools, or autonomous agents, these improvements enable more capable AI applications.

The Claude 4 models can maintain context and stay on task for longer projects—useful across many domains.