anacodicai-labs/terrier-ta-benchmark
Updated • 101
Production AI for underserved communities · Agentic and multi-agent LLM systems · Retrieval-augmented generation (RAG) · Trustworthy, auditable, provenance-grounded AI · Human-in-the-loop systems · Honest evaluation & reproducible benchmarking · Edge, on-device & offline LLM inference · Probabilistic forecasting & uncertainty quantification · Carbon-aware and energy-efficient inference · AI for education, clinical decision support, livelihoods, and climate