It took me a while to figure out how to interpret the benchmark correctly, because on the overview page it says "AA-Omniscience Non-Hallucination Rate," but on the benchmark page…
I self host this https://github.com/chroxify/haptic Pretty neat, mind the fact that is local based, so if you log from another device you will not have persistence
It took me a while to figure out how to interpret the benchmark correctly, because on the overview page it says "AA-Omniscience Non-Hallucination Rate," but on the benchmark page…
I self host this https://github.com/chroxify/haptic Pretty neat, mind the fact that is local based, so if you log from another device you will not have persistence