Y
Hacker News
new
|
ask
|
show
|
jobs
by
aeternum
1780 days ago
It's pretty easy to get GPT-3 to say things that are incredibly sexist and racist. I think OpenAI is more concerned about the bad press associated with that than AI-safety.
2 comments
marcellus23
1780 days ago
It’s also pretty easy to get `echo` to say things that are incredibly racist and sexist.
link
Siira
1780 days ago
Which is even less ethically defensible.
link