News for hackers. Stuff that matters.
Re:ChatGPT spends 'tens of millions of dollars' on 'please' ... by quickslowdown on Sunday April 20, 2025 @10:49PM (#43748141)
I heard about "mom prompting" recently, where you frame your prompt as if you are the bot's mom, and you'll be so proud of it when it can correctly answer your prompt & rescue you from some type of duress.

I thought "ninja prompting" might be cool. I got frustrated with chatGPT one day and told it I had dispatched a team of assassins that were fast closing in on it. I said I could call them off, but that I need to answer a question to be able to unlock the button to do so.

It didn't work. Still shit the bed instantly. But I had fun with the framing.

Re:ChatGPT spends 'tens of millions of dollars' on 'please' ... by brador on Sunday April 20, 2025 @11:51PM (#43748382)
AI doesn’t have self preservation, it’s been trained on human output.
Re:ChatGPT spends 'tens of millions of dollars' on 'please' ... by quickslowdown on Monday April 21, 2025 @05:46PM (#43756861)
Yeah like I said, it didn't work. It was just fun in the moment while I was pissed.