Tuning reward-function weights can very likely cause a constraint threshold to be exceeded accidentally, in part because the coefficients are difficult to reason about.

“And if you try to do this with like the the effective tuning, effectively there's a very high likelihood that you have accidentally something which goes above the the threshold. It's e especially since it's oftentimes really really difficult to think about these these coefficients. The second thing, uh the second big thing is you get”