Tag: RAG
-
Context Engineering: Sculpting Attention Surfaces for Real LLM Work
Aug 20, 2025 · 12 minA practitioner's field guide to moving beyond prompt tinkering—architecting token budgets, retrieval granularity, temporal pruning, and adaptive memory so large language models stay on-mission at scale.
-
Semantic Task Matchmaking: Legacy Vector Gravity After 6+ Months Away
Aug 13, 2025 · 7 minField note and catalyst: why I remained #2 in semantic tags after 6+ months absent, what that reveals about vector gravity, and how it motivated the 'Ghost' series on temporal resistance.