Reading up on Pinecone
5 deep · digging since apr 27
- Evaluation Measures in Information Retrieval
The piece explains four offline evaluation metrics for IR systems—Recall@K, MRR, MAP@K, NDCG@K—with formulas, code, and pros/cons.
- Popular AI Engineer Talks and Transcripts
The page lists over a thousand AI engineer talks, providing video links, summaries, speaker bios, and timestamped transcripts searchable by topic.
- persistent.info: Sierra MCP Gateway Dev Diary
The diary chronicles Sierra engineers’ incremental construction of an MCP gateway, detailing weekly service additions, user adoption, and solutions for secure data access.
- How AI Agent Memory Works
An interactive essay explains how agent memory systems work through context windows, embeddings, and retrieval architectures to overcome LLM statelessness.
- Today's harness is Tomorrow's Prompt
Temporary scaffolding around AI models becomes obsolete as models improve, so developers should build these harnesses cheap enough to discard.