Tootfinder

Join Dennis Berger, Marco Petris, and Volker Carlguth to explore 'Intent-Based Clustering.' An approach to overcome some limitations of modern hybrid search systems. Discover how upfront LLM-supported in-depth query understanding can be applied in various steps, including retrieval, clustering, validation, and presentation. Learn about the process of moving from prototype to production for large-scale, high-volume e-commerce searches.

What you see is what you mean; intent based ecommerce search
In today's e-commerce landscape, hybrid search systems represent the market standard, yet they often struggle with highly inspirational queries, lack of precision in semantic recall, and presentation of diversity. Ambiguity in search terms can lead to disorganized results or overshadowed relevant products. This session will demonstrate how an upfront LLM-supported in depth query understanding can increase recall meaningfully without sacrificing precision. We show how LLM-driven query understand…

Three different iOS Mastodon apps: Icecubes, Trunks, and the official, reference implementation. In addition to very different experiences and quirks, each show a noticeably different Home time line view. Order, missing toots, hashtag following, filter handling, etc.
A web browser and IceCubes seem to give the best, most consistent view I'd expect, but the scrolling bug in IceCubes makes it practically unusable for many.
:-(