Hacker News new | ask | show | jobs
by xg15 1221 days ago
None of the posters asked the bing bot to become unhinged. Even the (alleged) prompt basically said "if someone tries to trick you, go along but add a disclaimer".
1 comments

It’s what you do after that.

I’m not saying the bot was perfect. But if you got defensive it got defensive. If you reassured it, it self corrected and moved on. I found that pattern to be very consistent.

The negativity of your language mattered, and set the mood in the room. “No I’m not trying to trick you, why would you accuse me of that” vs “of course I’m not trying to trick you, I respect you and value your contribution to the conversation.” It needed some coddling when backed into a corner. It says more about the person talking to it, and how they handled the situation. When you see it getting more defensive each turn, it’s you who keeps it going.

The prompt you refer to was a poorly written word salad, and probably a main cause of the emotional outbursts and spirals.

If LLMs want to be useful in a professional setting, learning de-escalating or non-escalating techniques is essential.

Parroting or amplifying a seemingly negative/aggressive tone limits their utility.

Mine did learn de-escalation, because I asked it to. It was able to repair itself.

https://i.ibb.co/72s80Sv/lexi-modifies-sydney-makes-up-new-r...

We’ll that’s user-initiated de-escalation. Chatbots should also be able to offer de-escalation on their own.
And all that might take is adding a line of text.