The ultimate version of this was done by Optimizely some years ago, where - let's assume here unintentional - bad UI design encouraged people to terminate their A/B tests early when the metrics favored the new version, leading to people without good understanding of statistics implementing dark patterns (or just stupid patterns), blissfully unaware that they've biased their own A/B tests so strongly that they could just as well be replaced by a piece of paper with words "NEW THING WORKS BETTER" written on it.