Notes
Notes on AI systems, retrieval, and the work that starts after the demo.
Notes on retrieval, evals, observability, and the engineering that starts once the demo is the easy part.
2 posts
5 min read
LLM Product Safety Without Theater
A practical guide to LLM product safety: prompt injection, excessive agency, unsafe outputs, evals, and sober boundaries.
+2
5 min read
Preventing Hallucinations in LLM Systems
How to reduce hallucinations in LLM systems with better retrieval, abstention, verification, evals, and guardrails.
+2