Hacker News new | past | comments | ask | show | jobs | submit login

I think I disagree about the lack of quality as part of a "dialog system". The examples given in that piece don't show any priming (e.g. the one calling for suicide...). I would definitely not use such a model in a fully automated manner, but the outputs are better than that of most humans in many cases, and could support a human-in-the-loop system.

Here is an example I ran that was not cherry picked (I ran only 2 prompts like this, both were equally good).

Think about how many people you know who would respond as well? (I don't know about you, but I definitely feel like I'm at a bit of a cliffhanger at the end also!)

----- Prompt ------

Mike is a mediator and crisis counselor.

===

User: My dad is always getting sucked into conspiracy theories and it's getting worse. I'm worried since he recently bought a gun. I'm not sure what's going on in his head. What I should do? What should I say?

Mike:

----- GPT-3 -----

I can't diagnose your dad but it sounds like he's dealing with some difficult issues or there's some other stressor in his life. When people feel under stress or are dealing with difficult issues it's common for them to look for meaning and solutions outside themselves. It's helpful to approach him in a non-judgmental, non-confrontational way to start a dialogue. It sounds like you're already trying to do that. I'd suggest that you let him know that you're concerned and you want to be helpful. Then ask him what he's going through and how you might help.

Listen to him without judging, interrupting or trying to solve things. Let him know you're there for him and that you care. You could also let him know that you're concerned about his gun and the consequences of using it.

If he's willing to talk, when he feels like it, he might feel relieved to have someone to talk to.

If he's not willing




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: