←
Doug Turnbull21,544 posts
Doug Turnbull avatar

Doug Turnbull

@softwaredoug

Trying to figure out how search works Retrieval Researcher @ Self

◷ Joined March 2009▧ 911 Photos and videos
Bojan Tunguz avatar
⟳ Doug Turnbull retweeted
Bojan Tunguz@tunguz·18h

Meet Nesnej, NVIDIA’s new CEO.

Post attachment
Doug Turnbull avatar
Doug Turnbull@softwaredoug·Nov 16

There's a place for old school classic RAG when you don't trust the agent to even know what question to ask search, so you just want to inject some context before work even begins

Doug Turnbull avatar
Doug Turnbull@softwaredoug·Nov 16

My search consulting moved away from LLM judges. Now I: * Vibecode a facsimile of my clients application * Let agents act as users to use the app to solve search use-cases When using agent evals, I stay in the lane of sessions, clicks, etc - not NDCG softwaredoug.com/blog/2026/1…

Connor Shorten avatar
⟳ Doug Turnbull retweeted
Connor Shorten@CShorten30·Nov 16

Hey everyone! I am super excited to share our new research report! 🎉 Scaling Reranked Retrieval 🚀 Thread with more details! 🧵 (1/17)

Post attachment
Doug Turnbull avatar
Doug Turnbull@softwaredoug·Nov 12

Ranking based on an article trending, or job commute distance, or web pagerank, or ... can dominate why items are considered relevant

Doug Turnbull avatar
Doug Turnbull@softwaredoug·Nov 12

Why is 'classic' Learning to Rank still relevant in a world of embeddings and cross-encoders? Because classic ML still does a good job of accounting for the full range of domain-specific ranking factors that have nothing to do with unstructured text similarity

Post attachment
Doug Turnbull avatar
Doug Turnbull@softwaredoug·Nov 12

Instead of LLM-as-a-judge, let agents simulate traffic on search UI's. The search UI adds as much friction as ranking. And its hard to disentangle ranking from the display of search results. (Of course, human traffic teaches us more, but agents help with cold-start problems)

Doug Turnbull avatar
Doug Turnbull@softwaredoug·Nov 11

Turn user search traffic on your site as a corpus to search itself. No model training. No deploying GPUs. Just simple aggregations That's what I did with Alamo Drafthouse's search. They have a fat head query traffic, benefiting from just knowing the right answer for every query softwaredoug.com/blog/2026/1…

Swann Bessa avatar
⟳ Doug Turnbull retweeted
Swann Bessa@swann_bessa·Nov 10

Introducing e-means, an algorithm beating k-means in 10x fewer epochs. With order of magnitude wall-clock speedups, e-means is released in FAISS and needs no hyperparameter tuning beyond k. It is robust to various scales and datasets. Still skeptical ? Just try e-means [1/10]🧵

1:24
Trey Grainger avatar
⟳ Doug Turnbull retweeted
Trey Grainger@treygrainger·Nov 10

The recording is now available for enrolled students, with late enrollment still possible. Today, we covered a broad overview of many different AI query modalities (single vector, multi-vector/late interaction, personalized search with clustering-based guardrails, various hybrid search algorithms, behaviors vector spaces and queries, etc. Tomorrow is Blitzrank for Evals. Thursday is Learning to Rank / Building Ranking Classifiers. Many weeks still to go after that (until Dec 4).