More instructions were not making Claude better
Anthropic cut more than 80% of Claude Code’s system prompt for the Claude 5 generation models, with no drop in coding evals.
What interests me isn’t the number. It’s the admission behind it: they were overconstraining the model, through the system prompt, CLAUDE.md files and skills alike, and the competing instructions made it work harder, not better. That is exactly what I keep relearning writing CLAUDE.md files and skills for Mate and for my own AI assistant. Fewer explicit rules, richer references over descriptions, context loaded when it’s needed instead of all of it up front.
On https://claude.com/blog/the-new-rules-of-context-engineering-for-claude-5-generation-models
// MORE SHORTS
Symfony Language Tools stopped taking patches →
Symfony's new Language Tools repository closed its pull request tab. Contributors now start with an issue instead. Maintainers turn selected issues into code, usually with a coding agent doing much of the implementation work. Fabien's reasoning is what stuck with me.
// MORE SHORTS
Roots shipped inside its own deprecation window →
MCP's 2026-07-28 specification deprecated Roots, Sampling and Logging, with at least twelve months before they become eligible for removal. On August 14th, my Roots support PR merged into the official PHP SDK. None of this was hidden.