Hub
Data & Knowledge Foundations
Turn scattered data into shared context.
Permissioned retrieval, source-of-truth design and PII boundaries come before RAG demos. Articles on data contracts, freshness and the cost of bad context.
Evidence before autonomy. Each article below is written for operators and builders who need eval angles, decision framing and practices they can run — not another generic tip list.
Related on the main site: AI data & knowledge foundations
Posts on this topic
- Baidu releases ERNIE 5.5 Flash Base open weights for post-training · Models, Tooling & Developer Practice · AI for SaaS & Software Companies
ERNIE 5.5 Flash Base: Baidu's 280B/14B-active MoE base model, 33.5T tokens, 128K trained and 1M supported context, under its own license. What to check.
- Permissioned retrieval for knowledge assistants under agent pressure · Enterprise Knowledge Assistants · Data & Knowledge Foundations
MCP connectors and desktop agents widen what assistants can reach. Enforce the user's permissions at retrieval time, test for leaks, and cite every answer.
- Three open-weight releases: Spark, Nemotron and ERNIE change the menu · Models, Tooling & Developer Practice · Data & Knowledge Foundations
Muse Spark Open, Nemotron 3.5 Super VL and ERNIE 5.5 Flash Base compared on license terms, modality, hardware and runtimes, with a fair evaluation plan.