Comment by ameliaquining 6 days ago I don't understand this comment, are you saying they should allow it to appear in training data? 5 comments ameliaquining Reply philipwhiuk 6 days ago They're saying this is a very poor defence. ameliaquining 6 days ago Well, it seems better than not doing that? ajs1998 6 days ago It is eager to do things it shouldn't do. But I suppose it's better than lying about it. Although they do that too.From top to bottom, I still think nobody developing these things really cares about security. Davidzheng 6 days ago I think it should be allowed yes. I don't think our strategy is hoping the agents never learn that misalignment is an option. ameliaquining 6 days ago Well, no one's saying they shouldn't also do other things about the problem.
philipwhiuk 6 days ago They're saying this is a very poor defence. ameliaquining 6 days ago Well, it seems better than not doing that? ajs1998 6 days ago It is eager to do things it shouldn't do. But I suppose it's better than lying about it. Although they do that too.From top to bottom, I still think nobody developing these things really cares about security.
ameliaquining 6 days ago Well, it seems better than not doing that? ajs1998 6 days ago It is eager to do things it shouldn't do. But I suppose it's better than lying about it. Although they do that too.From top to bottom, I still think nobody developing these things really cares about security.
ajs1998 6 days ago It is eager to do things it shouldn't do. But I suppose it's better than lying about it. Although they do that too.From top to bottom, I still think nobody developing these things really cares about security.
Davidzheng 6 days ago I think it should be allowed yes. I don't think our strategy is hoping the agents never learn that misalignment is an option. ameliaquining 6 days ago Well, no one's saying they shouldn't also do other things about the problem.
ameliaquining 6 days ago Well, no one's saying they shouldn't also do other things about the problem.
They're saying this is a very poor defence.
Well, it seems better than not doing that?
It is eager to do things it shouldn't do. But I suppose it's better than lying about it. Although they do that too.
From top to bottom, I still think nobody developing these things really cares about security.
I think it should be allowed yes. I don't think our strategy is hoping the agents never learn that misalignment is an option.
Well, no one's saying they shouldn't also do other things about the problem.