alt Hacker News>My guess is that the model started brainstorming assassination plans
Why would an EU model default to brainstorming assassination plans first, and not democratic means of getting rid of politicians? The EU commission building literally has democracy in bold on the front of the building.
Does the EU use that AI to find ways to assassinate its opposition or what?
Replies
inigyou • today at 3:50 PM
Because the LLM is trained to predict based on what other people said. When people talk about getting rid of this meddlesome priest they don't mean take him on an all expenses paid vacation.
You're relying on testimony from a known liar, anyway.
Because alignment is difficult and it's easier to have another model filter the output than to prevent the model from producing the wrong output in the first place. Also, these are models by American providers run on EU infrastructure. The filter might very well be part of the package deal.
In any case, I hope Ursula von der Leyen doesn't ask AI how to get rid of her enemies and certainly doesn't act on the output, even if she has access to an unfiltered version that isn't bothered by the implications of the request.