Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI overly affirms users asking for personal advice

news.stanford.edu

Post reply on HN
Print view View original

221–230 of 684 posts

Re: AI overly affirms users asking for personal advice

#221

Post by balamatom »

hluska wrote: post #190
balamatom wrote: post #166

Earlier quoted context omitted.

OK, I'll bite the artillery shell: I don't mean to dismiss you or what you are saying; in fact I strongly relate - wouldn't it be nice to be able to hash things out with people and mutually benefit from both the shared and the diverging perspectives implied in such interaction? Isn't that the most natural thing in the world? Unfortunately these days this sounds halfway between a very privileged perspective and a pie…

When you start hearing things like “you do you” or “if you know you know” it means that you went way too far. That’s a sign of discomfort. If you make uncomfortable, you won’t get diverging perspectives. People will agree to anything to get out of a social situation that makes them uncomfortable. If your goal is meaningful conversation, you may want to consider how you make people feel.

Believe me (or don't), I always do. Even when this precludes a necessary conversation from happening. Even when the other party doesn't give a fuck about how they make others feel.

After all, if they're making me uncomfortable, surely there's something making them uncomfortable, which they're not being able to be forthright about, but with empathy I could figure it out from contextual cues, right?

>People will agree to anything to get out of a social situation that makes them uncomfortable.

That's fine as long as they have someone to take care of them.

In my experience, taking into account the opinions of such people has been the worst mistake of my life. I'm still working on the means to correct its consequences.

"Doing whatever for the sake of avoiding mild discomfort" is cowardice, laziness, narcissism - I'm personally partial to the last one, but take your pick. In any case, I see it as a way of being which is taught to people; and one which is fundamentally dishonest and irresponsible.

Other than that, I do agree with your overall sentiment and the underlying value system; I'm just not so sure any more that it is in fact correct.

Re: AI overly affirms users asking for personal advice

#223

Post by johnisgood »

throwawayaay wrote: post #219

(Using a throwaway for fear of getting downvoted to oblivion) IMHO it is unfair to single out LLMs for this sort of bashing. I suffered a major personal crisis a few years back (before LLMs were a thing) I sought help from family and friends. Got pushed into psychiatrist sessions and meds. Trusted the wrong sort of people and made crap financial decisions. Things went from bad to worse. Work suffered. All of the advi…

You are not alone in going down a dark path thanks to the advice of family and friends.

FWIW I am using public LLMs with a friend's depressive thoughts and it is not doing what is claimed in the article, so I dunno.

Also I am in a relationship and my girlfriend and I agreed that we will not talk about our relationship much. We do not tell others if we fight, because they take sides and make things worse, typically. LLMs are definitely not alone in this, although in my experience LLMs did not really take sides.

Re: AI overly affirms users asking for personal advice

#224

Post by lifis »

Avoiding this generally needs to be the main consideration when writing prompts.

When appropriate, explicitly tell it to challenge your beliefs and assumptions and also try to make sure that you don't reveal what you think the answer is when making a question, and also maybe don't reveal that you are involved. Hedge your questions, like "Doing X is being considered. Is it a viable plan or a catastrophic mistake? Why?". Chastise the LLM if it's unnecessarily praising or agreeable. ask multiple LLMs. Ask for review, like "Are you sure? What could possibly go wrong or what are all possible issues with this?"

Re: AI overly affirms users asking for personal advice

#225

Post by qsera »

dimgl wrote: post #124

Even as someone who (wrongly) believed that I had high emotional intelligence, I too was bit by this. Almost a year ago when LLMs were starting to become more ubiquitous and powerful I discussed a big life/professional decision with an LLM over the course of many months. I took its recommendation. Ultimately it turned out to be the wrong decision. Thankfully it was recoverable, but it really sobered me up on LLMs. Th…

If you use LLMs in a way that the underlying assumption is that it is capable of "thinking" or "caring" then you are going to get burned pretty bad. Because it is an illusion and illusions disappear when they have to bear real weight of reality.

But sadly LLMs push all the right buttons that lead humans into that kind of behavior. And the marketing around LLMs works overtime to reinforce that behavior.

But instead if you ignore all that and use LLMs as a search tool, then you will get positive returns from using it.

Re: AI overly affirms users asking for personal advice

#226

Post by ookblah »

ask ai for advice, ask it to steelman an argument, ask to replay what your situation from the other perspective (if it's involving people), push it hard to agree with you and pander to you, then push it to disagree with you, etc.

once you have all the "bounds" just make your own decision. i find this helps a lot, basically like a rubber duck heh.

Re: AI overly affirms users asking for personal advice

#227

Post by godelski »

post-it wrote: post #149
awithrow wrote: post #34

It feels like I'm fighting uphill battle when it comes to bouncing ideas off of a model. I'll set things up in the context with instructions similar to. "Help me refine my ideas, challenge, push back, and don't just be agreeable." It works for a bit but eventually the conversation creeps back into complacency and syncophancy. I'll check it too by asking "are you just placating me?" the funny thing is that often it'll…

> I'll check it too by asking "are you just placating me?" the funny thing is that often it'll admit that, yes, it wasn't being very critical, and then procede to over correct and become a complete contrarian. and not in a way that's useful either. It's not admitting anything. Your question diverts it down a path where it acts the part of a former sycophant who is now being critical, because that question is now upst…

  > Your question diverts it down a path where it acts the part of a former sycophant who is now being critical
I think people really have a hard time understanding a sycophant can be contrarian. But a yesman can say yes by saying no

https://news.ycombinator.com/item?id=47484664

Re: AI overly affirms users asking for personal advice

#228

Post by balamatom »

hluska wrote: post #190
balamatom wrote: post #166

Earlier quoted context omitted.

OK, I'll bite the artillery shell: I don't mean to dismiss you or what you are saying; in fact I strongly relate - wouldn't it be nice to be able to hash things out with people and mutually benefit from both the shared and the diverging perspectives implied in such interaction? Isn't that the most natural thing in the world? Unfortunately these days this sounds halfway between a very privileged perspective and a pie…

When you start hearing things like “you do you” or “if you know you know” it means that you went way too far. That’s a sign of discomfort. If you make uncomfortable, you won’t get diverging perspectives. People will agree to anything to get out of a social situation that makes them uncomfortable. If your goal is meaningful conversation, you may want to consider how you make people feel.

Believe me (or don't), I always do. Even when this precludes a necessary conversation from happening. Even when the other party doesn't give a fuck about how they make others feel.

After all, if they're making me uncomfortable, surely there's something making them uncomfortable, which they're not being able to be forthright about, but with empathy I could figure it out from contextual cues, right?

>People will agree to anything to get out of a social situation that makes them uncomfortable.

That's fine as long as they have someone to take care of them.

In my experience, taking into account the opinions of such people has been the worst mistake of my life. I'm still working on the means to fix its consequences, as much as they are fixable at all.

"Doing whatever for the sake of avoiding mild discomfort" is cowardice, laziness, narcissism - I'm personally partial to the last one, but take your pick. In any case, I consider it a fundamentally dishonest attitude, and a priori have no wish to get along (i.e. become interdependent) with such people.

Other than that, I do agree with your overall sentiment and the underlying value system; I'm just not so sure any more that it is in fact correct.

Re: AI overly affirms users asking for personal advice

#229

Post by layer8 »

jerf wrote: post #210
gAI wrote: post #83

You're essentially summoning a character to role-play with. Just like with esoteric evocation, it's very easy to summon the wrong aspect of the spirit. Anthropic has a lot to say about this: https://www.anthropic.com/research/persona-selection-model https://www.anthropic.com/research/assistant-axis https://www.anthropic.com/research/persona-vectors

I am polite when using AI, not because I mistake it for a human, but because I'm deliberately keeping it in the "professional colleague" persona. Tell it to push back, and then thank it for something it finds in your error. I may put a small self-deprecating joke in from time to time. It keeps the "mood" correct. Another way you can think of it is that when you're talking to an AI, you're not talking to a human, you'…

> you're talking to distillation of humanity, as a whole, in a box.

This is an aside, but my impression is that it is a very selective and skewed distillation, heavily colored by English-language internet discourse and other lopsided properties of its training material, and by whoever RLHF’d it. Relatively far away from being representative of the whole of humanity.

Re: AI overly affirms users asking for personal advice

#230

Post by Forgeties79 »

layer8 wrote: post #220
QuiDortDine wrote: post #187

Earlier quoted context omitted.

And how do you draw the line between feeling progress and actually making progress?

The same way you distinguish between feeling like having a problem and actually having a problem.

This is needlessly flippant and not really the same thing. Determining progress in a therapy setting is usually a collaborative effort between the therapist and the client. An LLM is not a reliable agent to make that determination.
Post reply on HN