Claude Code v2.1.68: Opus 4.6 defaults to medium effort, reintroduces ultrathink keyword
Claude Code v2.1.68 release notes
Anthropics has released Claude Code v2.1.68 with changes to effort settings and model availability. This update primarily affects how the Opus 4.6 model handles different types of coding tasks.
Key changes in this release
- Opus 4.6 default effort changed: For Max and Team subscribers, Opus 4.6 now defaults to medium effort instead of the previous setting. According to the release notes, "Medium effort works well for most tasks — it's the sweet spot between speed and thoroughness."
- Effort control: Users can change the effort setting anytime using the
/modelcommand. - UltraThink keyword reintroduced: The "ultrathink" keyword has been re-added to enable high effort for the next turn. This allows users to temporarily boost the model's processing for complex tasks without permanently changing settings.
- Model deprecation: Opus 4 and Opus 4.1 have been removed from Claude Code on the first-party API. Users who had these models pinned are automatically moved to Opus 4.6.
The release was published on March 4th by ashwin-ant and includes commit 0b3f7cb. These changes are specific to Claude Code, Anthropics' coding-focused implementation of their Claude models.
📖 Read the full source: GitHub Claude-Code
👀 See Also
Claude's policy filter blocks bioinformatics work with pathogen names
A computational virology researcher reports Claude's usage policy filter flags legitimate bioinformatics scripts when pathogens are named, requiring workarounds like describing tasks without organism names or downgrading to Sonnet 4. The issue affects Claude Code, claude.ai, and both Opus 4.6 and Sonnet 4.6 models.
Claude Cowork for Windows ARM64 Released with Compatibility Checker
Anthropic has released Claude Cowork for Windows ARM64 devices, requiring Windows 11 Pro with Hyper-V and virtualization enabled. The company provides an EXE compatibility checker tool to verify system requirements.
AMD Threadripper Halo Station: 96-Core AI Workstation with MI350P
At IFA 2026, AMD announced the Threadripper Halo Station, a workstation packing a 96-core Threadripper Pro 9995WX and dual liquid-cooled MI350P accelerators, designed to run trillion-parameter models.
Yann LeCun's AMI raises $1B for AI world models, challenges LLM approach
Yann LeCun's startup AMI raised over $1 billion to develop AI world models that understand the physical world, arguing LLMs alone won't achieve human-level intelligence. The company will build systems with persistent memory, reasoning, and planning capabilities for manufacturing, biomedical, and robotics applications.