We built a model to generate 1,000 questions that people actually ask. Not random prompts. We scraped 50,000 real user queries from search logs, forum threads, and support tickets across 12 industries. We clustered them by intent and generated 1,000 representative questions.
We asked those same 1,000 questions to 5 AI models: ChatGPT (GPT-4), Gemini (Ultra), Perplexity (Pro), Claude (4.5 Sonnet), and Llama (3). We ran the experiment daily for 30 days. We tracked every citation at the source level.
The goal: measure citation overlap. How often do these models cite the same source for the same question?
We re teaming up with The Pitch by @Deel, a global startup competition where up to 100 winners will receive $50k in funding and up to 10 winners will receive $1M+.
If you make the cut, you ll also show up on special Product Hunt leaderboards, starting with the first event on April 13.
Hey Product Hunt community! I'm Shawn, founder of Kinetic Mingle, and I'm excited to announce that we're launching here TOMORROW - March 31st at 12:01 AM PT!
Kinetic Mingle is a video-first dating app for adults 21+ who are tired of catfishing and fake profiles. What makes us different: AI-powered matching that analyzes compatibility, mandatory video chat before messaging, verified profiles, voice notes, and a community built on trust.
