Context-Tiering
- Anthropic Cut 80% of a System Prompt — and the Rules That Replaced It
Anthropic removed over 80% of Claude Code's system prompt with no measured loss on coding evals. The six rules that replaced it are an architecture change, not a diet.
- This Week in AI: Verifying Got Cheap, Finding Still Isn't
A self-improving research agent, a broken NIST post-quantum candidate, and a score that tripled on two API settings. The verify side of the loop won the week.
- Claude Opus 5 Is Here — and Half the Instructions in Your Setup Just Expired
Opus 5 reaches near-frontier quality at half Fable's price — and Anthropic's own guide says to delete the verification instructions you wrote for older models.
- Claude Fable 5 Is Here — and the Disciplined Move Is to Route Down, Not Up
Anthropic's Fable 5 is the most capable public model yet — a new Mythos-class tier above Opus. The reflex is to route everything to it. Here's why the disciplined move is the opposite, and the two routing skills I rebuilt the day it shipped.
- Context Is Not Memory: The Context Tiering Spectrum for AI Coding Agents
Your CLAUDE.md is a monolith, not an architecture. Context tiering — hot/warm/cold by access frequency — gives an agent persistent context without drowning it.