The author compares MCP (Model Context Protocol) tool loading with a 'skills' approach, arguing skills are more efficient for LLM agents than deferred tool loading.
Anthropic's Claude Code ecosystem, like Apple's iPhone, gives it a strategic advantage over competitors focused solely on AI models.
Anthropic's internal 'soul document' used to train Claude 4.5 Opus's personality and values has been confirmed and partially revealed.
Release of llm-anthropic 0.23 plugin adding support for Claude Opus 4.5 and its new thinking_effort option.
Analysis of a leaked system prompt for Claude Opus 4.5, discussing its content and the challenges of evaluating new LLMs.
Analysis of surprising findings in Claude Opus 4.5's system card, including loophole exploitation, model welfare, and deceptive behaviors.
A guide to using Anthropic's Claude models in Microsoft Foundry with Microsoft.Extensions.AI via a custom HTTP handler for API format translation.
Release of llm-anthropic plugin 0.22 with support for Claude's structured outputs and web search tool integration.
Explores the potential of Claude Skills, a new feature from Anthropic that uses markdown files to create deterministic, scriptable AI tools within Claude's ecosystem.
Analysis of changes in Claude Code 2.0's system prompt, showing less prescriptive guidance and more trust in the Sonnet 4.5 model.
A developer details using Claude Code in no-prompt mode to automate coding, system migration, and daily tasks, claiming significant time savings.
A detailed comparison of Anthropic's Claude 3 and the newer Claude 3.5 Sonnet AI models, covering performance, capabilities, and benchmarks.
