Hacker News new | ask | show | jobs
by viccis 148 days ago
By what measure? What's "safe"?
1 comments
conception 147 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.

link
viccis 147 days ago
Cool, another metric to game like they do the other ones.
link