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

LLMs are more persuasive than incentivized human persuaders

arxiv.org

Post reply on HN
Print view View original

101–110 of 123 posts

Re: LLMs are more persuasive than incentivized human persuaders

#101

Post by sitkack »

armchairhacker wrote: post #11
metalcrow wrote: post #3

My guess for the reason behind this is that LLMs have more facts memorized, and thus can make more reasonable and well-researched sounding answers. If you ask an LLM vs a Human "Is a stack in computer science a) a data structure that is first in first out or b) a data structure that is first in last out" the LLM can say stuff resembling "Based on Dijkstra's algorithm proof given in 1943 and the nature of Turing compl…

LLMs also never get tired of arguing. They'll respond to every point from a gish-gallop and provide quality-sounding replies to points that are obviously (to an informed person) flawed or seem (but aren't necessarily) mal-intentioned. EDIT: LLMs also aren't egocentric; they'll respond in the other person's style (grammar, tone, and perhaps maintain their "subtext" like assumptions), and they're less likely to omit im…

Any qualities you ascribe to an LLM is part of its RLHF, ask to get irritated or lazy and it will simulate those qualities. They are high dimensional text simulators. They can and do simulate anything.

Re: LLMs are more persuasive than incentivized human persuaders

#102

Post by sitkack »

Nevermark wrote: post #75
pottertheotter wrote: post #35

Earlier quoted context omitted.

Do you have any examples where you’ve used them for this? Would be interesting to see.

A simple example is I have a series of three ordered connected things. I called the first one “pre” since it “precedes” the others. I called the last one “pro” since it “proceeds” from the others. These are somewhat poetic/whimsical terms, for an abstract arrangement, but it’s nice to have good terms even for non-serious stuff. I couldn’t come up with an equally concise term for the middle. Claude came up with “per”…

Inventing words (neologism) with LLMs is a fun past time, or giving it descriptions and having it define the concept in various languages.

Re: LLMs are more persuasive than incentivized human persuaders

#103

Post by UltraSane »

AlexCoventry wrote: post #88
CJefferson wrote: post #10

Earlier quoted context omitted.

Based on reading bad AI generated student essays it’s worse than that, LLMs are happy to “fill in the blanks” with whatever made up fact would make their argument look best. Most people can’t lie that smoothly, and most readers don’t check carefully, unless they are already an expert in the area. Any kind of maths proof is particularly bad, they will look convincing and clear until you read them very carefully and se…

It depends on the AI. ChatGPT's higher models (o1-pro/o3/o4-mini-high) have some kind of limited capability to detect errors in the user's thinking, and have relatively few hallucinations.

I've had fun debates about things like p-zombies with Gemini 2.5 Pro

Re: LLMs are more persuasive than incentivized human persuaders

#104

Post by Llamamoe »

smeej wrote: post #89
CJefferson wrote: post #10

Earlier quoted context omitted.

Based on reading bad AI generated student essays it’s worse than that, LLMs are happy to “fill in the blanks” with whatever made up fact would make their argument look best. Most people can’t lie that smoothly, and most readers don’t check carefully, unless they are already an expert in the area. Any kind of maths proof is particularly bad, they will look convincing and clear until you read them very carefully and se…

It's funny you mention this, because my father operates exactly as you describe the LLMs, making facts up on the spot, lying smoothly and keeping track of the lies... ...and he's built his whole career in sales because of it. He despises the existence of Google, because the last thing a pathological bullshitter wants is fact-checking in pockets! It's taken me nearly 40 years to understand that anchoring statements in…

I feel like a good half of humanity operates this way, with it being far more prevalent in boomers than younger generations. It doesn't matter what is backed by evidence to them, instead they rely on anecdotes and persuasive quips and factoids. Having a friend who claims to have experienced X and listing off several other anecdotes means more to them than any amount of evidence.

Re: LLMs are more persuasive than incentivized human persuaders

#105

Post by namaria »

AlexCoventry wrote: post #90
1oooqooq wrote: post #70

Earlier quoted context omitted.

not even Idiocracy predicted that one.

These students are probably intellectually gifted, they're just playing a stupid game for the sake of an item on their resume.

I question the intellect of anyone engaging in silly games with the sole purpose of impressing other people.

Re: LLMs are more persuasive than incentivized human persuaders

#106

Post by bardan »

School-Cotton wrote: post #98
OJFord wrote: post #81

Earlier quoted context omitted.

And the judges of these tournaments not only understand it too (I can understand an opponent understanding if they've practiced the same thing) but seriously value it in scoring? Again/stepping back: what is the point of winning a debate tournament like this, or that values this 'debate'?

What’s the point of winning a chess tournament or any other intellectual game/sport?

The equivalent would be speed chess, wouldnt it? There is nothing intellectual about speaking as fast as possible.

Re: LLMs are more persuasive than incentivized human persuaders

#107

Post by bardan »

namaria wrote: post #105
AlexCoventry wrote: post #90

Earlier quoted context omitted.

These students are probably intellectually gifted, they're just playing a stupid game for the sake of an item on their resume.

I question the intellect of anyone engaging in silly games with the sole purpose of impressing other people.

Seems like a competition that started reasonably and mutated into nonsense over time as the rules were exploited (and never modified, I guess). If it's an established debate style and offered to kids as legitimate you can't blame them. Kids do what is available to them.

Re: LLMs are more persuasive than incentivized human persuaders

#109

Post by johnisgood »

beeflet wrote: post #86
upghost wrote: post #62

Earlier quoted context omitted.

This is a consequence of the fact that any argument not responded to "flows across" the score sheet and is automatically a win for the team making the argument, no matter how silly. So a "natural" tendency would be to ignore ridiculous arguments like "not paying for school lunches will cause children to hyperventilate, and by the butterfly effect will lead to infinite hurricanes in developing nations causing a collap…

Which is pretty ridiculous. The purpose of a debate should be to change/consolidate the hearts and minds of the audience to your side. To this end, it's usually sufficient to pick apart a few of the key points of your opponent's argument. Nitpicking every aspect of your opponent usually comes off as uncharismatic. Brevity is really important in a debate. Especially in the modern day where someone might turn you into…

Debates these days (especially political ones) are just unnecessary, totally unrelated ad hominems, and people yelling over each other.

Yup to your last sentence. It irritated me how off-topic his responses were.

Re: LLMs are more persuasive than incentivized human persuaders

#110

Post by thih9 »

upghost wrote: post #62
hammock wrote: post #51

Earlier quoted context omitted.

Reminds me of the horrific state of student debate competitions today where the winning strategy is to incomprehensibly rattle off as many arguments as quickly as possible with strange breathy sounds in between

This is a consequence of the fact that any argument not responded to "flows across" the score sheet and is automatically a win for the team making the argument, no matter how silly. So a "natural" tendency would be to ignore ridiculous arguments like "not paying for school lunches will cause children to hyperventilate, and by the butterfly effect will lead to infinite hurricanes in developing nations causing a collap…

I guess winning like this cheapens the victory. Then again, this strategy continues to be used at all levels of disputes and politics. I wish there was a way to stop that, not just in student debates.
Post reply on HN