Thanks, this seems like an obvious and important question that I’m sure a lot of people here have thought about. I’m interested to hear the answers!
Its obviously very difficult though with the lack of clear outcome measures, but not reason why it shouldn’t be tried. I also wonder if there are any AI safety evaluation orgs?
Thanks, this seems like an obvious and important question that I’m sure a lot of people here have thought about. I’m interested to hear the answers!
Its obviously very difficult though with the lack of clear outcome measures, but not reason why it shouldn’t be tried. I also wonder if there are any AI safety evaluation orgs?