Comment by viccis 18 days ago By what measure? What's "safe"? 2 comments viccis Reply conception 17 days ago https://crfm.stanford.edu/helm/air-bench/latest/#/leaderboar...This isn’t the gotcha question you think it is. AI safety is being defined and measured. viccis 17 days ago Cool, another metric to game like they do the other ones.
conception 17 days ago https://crfm.stanford.edu/helm/air-bench/latest/#/leaderboar...This isn’t the gotcha question you think it is. AI safety is being defined and measured. viccis 17 days ago Cool, another metric to game like they do the other ones.
https://crfm.stanford.edu/helm/air-bench/latest/#/leaderboar...
This isn’t the gotcha question you think it is. AI safety is being defined and measured.
Cool, another metric to game like they do the other ones.