Testing Jev's limits: probabilities instead of definite answers
A developer built an app that uses Jev to count the letter a in a word and found it returns probabilities rather than clear answers, is rarely 100% sure, and occasionally gets obvious questions wrong, making it best suited to fast structured judgments on messy information where errors are tolerable.
here's one of the major bottlenecks of Jev... i made an app that uses Jev to tell me how many a's are in a word it doesn't return a clear answer, it returns probabilities, it's rarely 100% sure it's right most of the time, but it also gets such an obvious question wrong that's not to say it's not useful, it definitely is - but you shouldn't use it in systems where there's no margin of error the sweet spot is using it to make fast, structured judgement in systems where there's lots of messy information