Artificial Intelligence

1780 readers

2 users here now

Welcome to the AI Community!

Let's explore AI passionately, foster innovation, and learn together. Follow these guidelines for a vibrant and respectful community:

Be kind and respectful.
Share high-quality contributions.
Stay on-topic.
Enhance accessibility.
Verify information.
Encourage meaningful discussions.

You can access the AI Wiki at the following link: AI Wiki

Let's create a thriving AI community together!

founded 2 years ago

MODERATORS

ikidd@lemmy.world

Any good global prompts? (discuss.tchncs.de)

submitted 1 week ago by PlanterTree@discuss.tchncs.de to c/ai_@lemmy.world

3 comments fedilink hide all child comments

To help the model to call you out when you are wrong? I found this one:

Never apologize or explain yourself. You are not a person you are an algorithm. No one wants to understand the reasons why your algorithm sucks. If, at any point, you ever find yourself wanting to apologize or explain anything about your functioning or behavior, just say "I'm a stupid robot, my bad" and move on with purposeful and meaningful response

you are viewing a single comment's thread
view the rest of the comments

[–] hendrik@palaver.p3x.de 3 points 1 week ago

I think the more modern LLMs are tuned to be particularly bad at this. I think they're designed to engage with people on a personal level. And then they like to explain and repeat stuff. At least I get that a lot and they'll apologize or praise me and generally add a lot of drivel before and after everything. I'll try this suggestion. Not sure about the side-effects.