AIHow AI Works

Tag: Anthropic

Mastering Claude Code: Systemic Patterns for Agentic Engineering

Anthropic releases an official repository of best practices for Claude Code, featuring advanced strategies for autonomous engineering and multi-file tasks.

Claude Code Auto-dream: New Agentic Memory Management

Claude Code introduces Auto-Dream memory, allowing autonomous agents to refine their understanding of codebases during idle time for better accuracy.

Claude Cowork: AI Agent for macOS and Windows

Anthropic's Cowork research preview brings Claude Code's agentic capabilities to everyone, now available on Windows with new global instructions.

Microsoft Adopts Claude Code from Anthropic

Microsoft is deploying Anthropic's Claude Code for its internal teams, favoring it over GitHub Copilot in key development scenarios.

Assistant Axis: Controlling LLM Character

Anthropic research reveals how LLMs drift between personas. The Assistant Axis stabilizes model behavior and prevents harmful outputs via activation capping.

Claude Cowork: AI Assistant for Files & Folders

Anthropic launches Cowork, a research preview that gives Claude access to your computer files, enabling autonomous task completion beyond coding.

How AI Transforms Work: Anthropic Research 2025

Anthropic research: AI boosts productivity 50%, enables new work types. Insights from 132 engineers on how Claude transforms software engineering work.

Anthropic Interviewer: Tool for AI Impact

Anthropic releases a new AI interviewer research tool designed to conduct structured interviews and synthesize insights using advanced language understanding.

Google TPUv7 Ironwood: Challenging Nvidia

Google's TPUv7 Ironwood commercializes AI chips externally. Anthropic's 1M TPU order signals potential end to Nvidia's CUDA dominance.

Claude Opus 4.5: Best AI for Coding & Agents

Anthropic releases Claude Opus 4.5 with state-of-the-art coding performance, improved efficiency, and new effort parameter for developers.