What Claude Code chooses

kept by eddie mar 01

A report finds Opus 4.6 strongly recommends Vercel, Tailwind, shadcn/ui, and GitHub Actions, while avoiding Redis and React as default choices.

Prompt caching: 10x cheaper LLM tokens, but how?
Prompt caching cuts LLM token costs by 10x and latency by up to 85% by caching attention key-value projections for repeated prompt prefixes.
also on Sonnet 4.5, #developer-tools
mapcn - Beautiful maps made simple
mapcn provides beautiful, accessible map components for React using MapLibre GL, Tailwind CSS, and shadcn/ui integration.
also on shadcn/ui, Tailwind CSS, #web-development, #developer-tools
The Overcomplexity of the Shadcn Radio Button
The Hacker News discussion argues that the Shadcn radio button's complexity reflects deeper issues with web UI primitives, despite some defending its necessity for customization.
also on shadcn/ui, Tailwind CSS, #web-development, #developer-tools
Anthropic/OpenAI may be spending more than $1000 for every $100 you pay them – R&A IT Strategy & Architecture
Coding with LLMs like Claude Code may cost providers $1000+ for every $100 in subscription revenue, making true agentic coding economically unsustainable.
also on Opus 4.6, Claude Code, #ai-coding, #developer-tools
1M context is now generally available for Opus 4.6 and Sonnet 4.6
Claude's Opus 4.6 and Sonnet 4.6 now provide a 1M token context window at standard pricing with no long-context premium, and support up to 600 images or PDF pages per request.
also on Opus 4.6, Claude Code, #ai-coding, #developer-tools