News for hackers. Stuff that matters.

A comment on AI behavior guardrails should be public. Parent comment

Re:AI behavior guardrails should be public by int_19h on Wednesday February 21, 2024 @05:58PM (#39460814)
Can you please explain how outright refusing to draw an image with from the prompt "white male scientist", and instead giving a lecture on how their race is irrelevant to their occupation, but then happily drawing the requested image when prompted for "black female scientist", is promoting inclusion and equality?
[ Parent | on HN ]
Re:AI behavior guardrails should be public by anomaly_ on Wednesday February 21, 2024 @08:31PM (#39461990)
He can't.
[ Parent | on HN ]
Re:AI behavior guardrails should be public by lomase on Thursday February 22, 2024 @06:58AM (#39465862)
It is pretty clear to me.

Reality has a bias, most scientist in the world are white males.

This IA is overtuned in the opossite direction to inspire kids who have not ever seen a person like them, not white, in those kind of jobs.

[ Parent | on HN ]
Re:AI behavior guardrails should be public by QuizzicalCarbon on Thursday February 22, 2024 @11:08AM (#39469155)
Saying most scientists in the world are white males seems like a very Anglo-centric perspective, at least based on the numbers available from statista.com.
[ Parent | on HN ]
Re:AI behavior guardrails should be public by int_19h on Thursday February 22, 2024 @03:04PM (#39472350)
Most scientists in the world are either Indian or Chinese. And, either way, that's not the point here.
[ Parent | on HN ]