Thariq at Anthropic just published the new rules of context engineering for Claude 5 models. the same rules let them cut ~𝟴𝟬% of Claude Code's own system prompt with no measurable loss on their coding evals. tldr:

Samenvatting

Thariq at Anthropic just published the new rules of context engineering for Claude 5 models. the same rules let them cut ~𝟴𝟬% of Claude Code's own system prompt with no measurable loss on their coding evals. tldr: • CLAUDE.md is for gotchas only. delete anything the model learns by looking at the r