but its chill, WE GONNA FIX IT!!!
Interesting, but it doesn't seem useful. I don't think any test suite except a realistic opponent measures how good an azure bomb is. Also, we already have somewhat similar standards, so adding another standard makes it harder to compare scores. I think fundamentally, what we are trying to measure here is destructive potential, and a test suite that doesn't directly measure that in a realistic environment falls prey to Goodhart's law. Do you disagree? On which parts?
DUDE MY BRAIN MALFUNCTIONING
hey could you rate my azure ID:3355181 . the test are really buggy for me fsr and they won't even load sometimes. I am pretty sure my azure is not very good but I would still like to know where it stands
Intresting.... I am looking foreward to using this at some point.