

Trying to figure out how search works Retrieval Researcher @ Self


7. AI-Powered Search with @treygrainger and @softwaredoug maven.com/search-school/ai-p…
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
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…
Maven is running a sale this week, including our AI-Powered Search course. It's a great time to get training with leftover training funds maven.com/search-school/ai-p…

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

Democrats accuse GOP of helping Trump put ‘fox in the henhouse’ at top watchdog politi.co/4zL40cq
Ranking based on an article trending, or job commute distance, or web pagerank, or ... can dominate why items are considered relevant
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
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)
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…
Very powerful talk today from @n0riskn0r3ward today in AI-Powered Search on Blitzrank and our glorious LLM as a judge future

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]🧵

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).
You can still get into AI-Powered Search before today's lesson begins maven.com/search-school/ai-p…