Why it matters: Google Cloud is moving analytics assistants beyond SQL explanation into model-backed analysis. The tweet names two concrete AI functions now reachable from chat: forecasting and anomaly detection.
A Hacker News post about TimesFM drew 254 points and 95 comments, and the discussion quickly shifted from the GitHub repo itself to harder questions about generalization across domains, trust and explainability in forecasts, and comparisons with Prophet and Nixtla. The thread treated TimesFM 2.5 as a concrete update, but also as a test case for how far a general time-series foundation model can really go.
Google Research said on March 12, 2026 that it is rolling out urban flash flood forecasts with up to 24 hours of advance notice. The system uses a Groundsource dataset built from public reports and extends Google’s flood coverage beyond river flooding toward rapid-onset urban disasters.
Google Research says its March 12, 2026 rollout adds urban flash flood forecasts to Flood Hub with up to 24 hours of advance notice. The system is trained in part on Groundsource, a dataset built by using Gemini to extract structured flood events from public news reports.