Alex Jacobs

Lift up my agent in prayer.

I ran 32 experiments comparing small LLMs to BERT on classification tasks. Turns out 2018-era BERT is still really good at what it does.

The real limitations of pgvector in production: index choice between IVFFlat and HNSW, why real-time search is hard, pre- vs post-filtering pain, how performance degrades at scale, and when a dedicated vector database is the better call.

An empirical analysis of LLM application patterns that successfully scale in production systems, focusing on extraction, generation, and classification use cases

OpenAI

A practical guide to FastAPI integration tests with pytest: mocking JWT authentication and the TestClient, patching external API calls, and faking MongoDB and S3 with mongomock and moto.

A simple an effective approach for handling end users who struggle with errors