News for hackers. Stuff that matters.
Re:AI behavior guardrails should be public by int_19h on Wednesday February 21, 2024 @05:13PM (#39460384)
Judging by the way it words some of the responses to those queries, they "fixed" it by forcibly injecting something like "diverse image showcasing a variety of ethnicities and genders" in all prompts that are classified as "people".

There are no comments on this comment yet.