Comment by wongarsu

Sure, you can fix that in a couple lines. Then a couple more lines for evaluating multiple questions on the same answer in parallel. Then a couple more lines for the confidence score (which is trivial to compute from all we have, but missing regardless). Then a harness to fine-tune an existing model to perform better on this specific task, and a collection of training data to use for that

I think we can all agree that Jev is not rocket science. It's a good idea executed well, with marketing that might have been a tad too bold