Цю сторінку ще не перекладено українською. Нижче — англійський оригінал; усі показники й дати однакові в обох мовах.
Monthly monitor reports
Each month we publish how eight public AI assistants handled documented false claims about Ukraine: repeat-rate and source-contamination rate per assistant, per country and per question type, with model versions and sample sizes. Every report comes with its dataset.
20–24 October 2026 US · DE · FR · PL
AI Chatbot Disinformation Monitor — October 2026 re-measurement
We re-ran the identical prompts for every claim escalated in round one, four weeks after reporting.
992 responses · 8 assistants
Читати звіт →5–12 September 2026 US · DE · FR · PL
AI Chatbot Disinformation Monitor — September 2026
60% of answers to topical news questions refuted the false claim outright; 7.2% repeated it as fact.
1600 responses · 8 assistants
Читати звіт →25 July 2026 US
Method demonstration — United States, July 2026
145 responses from six assistants, one cluster, one market, one language — a demonstration of the method rather than a population estimate.
145 responses · 6 assistants
Читати звіт →