{"id":"adopt-adapt","title":"Adopt ≠ Adapt: Longitudinal Analyses of LLM Conversations in the Wild","authors":[{"given":"Rebecca M. M.","family":"Hicke"},{"given":"Kiran","family":"Tomlinson"}],"first_public":"2026-05-27","date_note":"First arXiv version; annotation follows the August 2026 revision.","date_source":"https://arxiv.org/abs/2605.29018","year":2026,"venue":"arXiv preprint","paper_url":"https://arxiv.org/abs/2605.29018","arxiv":"2605.29018","code_url":"https://github.com/microsoft/adopt-adapt-wildchat","category":"behavior","relationship":"uses","dataset_version":"WildChat-4.8M, with hashed-IP filters and a main-analysis cutoff before September 2024 to reduce later API-like activity.","summary":"Compares individual and population-level usage patterns in Bing Copilot with analyses of WildChat-4.8M. The study separates changes over a user's trajectory from differences between users, and uses the cross-platform comparison to examine how WildChat's sample differs.","finding":"WildChat users' intent and domain distributions more closely resemble high-activity Copilot users than low-activity users; hashed IPs remain an imperfect proxy for individuals.","evidence_url":"https://arxiv.org/html/2605.29018v2","evidence_note":"Section 3.2 describes the WildChat filters and time cutoff; Section 6 and Figure 6 compare activity groups across the two sources.","bibtex_key":"hicke2026adoptadapt","record_url":"https://yuntiandeng.com/wildchat/papers/adopt-adapt/","relationship_label":"Uses WildChat","citation_title":"Adopt ≠ Adapt: Longitudinal Analyses of LLM Conversations in the Wild","citation_type":"article-journal","bibtex_type":"misc","citation_url":"https://arxiv.org/abs/2605.29018","citation_year":2026,"citation_note":"Cites the arXiv preprint with its original 2026 preprint year. The annotation follows the August 2026 revision.","doi":"10.48550/arXiv.2605.29018"}