News for hackers. Stuff that matters.
Re:AI behavior guardrails should be public by int_19h on Wednesday February 21, 2024 @05:28PM (#39460514)
> People can explicitly override the sensible defaults as necessary

They cannot, actually. If you look at some of the examples in the Twitter thread and other threads linked from it, Gemini will mostly straight up refuse requests like e.g. "chinese male", and give you a lecture on why you're holding it wrong.

There are no comments on this comment yet.