LLMs have uses far beyond agents. We should all be concerned how quickly GPT-5 thrashed away from those use cases| Doug Turnbull
We need to evaluate agents from a completely new angle: as researchers not reasoners.| Doug Turnbull's Blog
A free introductory search course for anyone who wants better search without all the hard work| Doug Turnbull
AI coding requires a tradeoff between human and AI context, and your job is now to decide where to best spend your limited attention vs to let the AI do work| Doug Turnbull's Blog
You can get started improving search relevance without labels and judgments. Which is an imperfect model anyway.| Doug Turnbull's Blog
Believing in the mission is the new we're a family. Why be a true believer in anything that's about to lay you off?| Doug Turnbull
Big brain spend months building perfect quality metrics. Grug brain no trust, and just want dumb labels from coworkers 👍/👎.| Doug Turnbull's Blog
Can you prompt your way to solving every NLP problem?| Doug Turnbull
High variance NDCG delta in an offline experiment can mean we don't understand our change| Doug Turnbull
Instead of learning complex Query DSLs, we need better API-level abstractions to deal with Top N Retrieval| Doug Turnbull's Blog
Doug Turnbull's Blog | Doug Turnbull's Blog
RAG apps have a big blindspot - using actual user engagement to drive improvement. But its a hard problem. Let's discuss!| Doug Turnbull
Elasticsearch knn query is both a joy and a headache - here is where you’ll get stuck and the hacks I’ve used to overcome them.| Doug Turnbull's Blog
Reciprocal Rank Fusion, while a useful tool, doesnt magically make hybrid search relevant| Doug Turnbull's Blog