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

Ask HN: How do you deal with people who trust LLMs?

news.ycombinator.com

Post reply on HN
Print view View original

101–110 of 236 posts

Re: Ask HN: How do you deal with people who trust LLMs?

#101

Post by esperent »

> They have a question that would be very well answered with a search leading to a reputable source

Can you give an example of what kind of question you mean here?

Given that most people's idea of a reputable source is whatever comes up on the first page of Google or YouTube, I think we should use that as the comparison rather than dismissing LLM results. And we should do some empirical testing before making assumptions, otherwise we're just as bad as the people we are complaining about.

Whatever results we get, the real problem is that most people's ability to verify information was not good before LLMs, and it's still not good now.

So now you're dealing with LLM hallucinations, and before you were dealing with the ravings of whatever blogger or YouTuber managed to rank for this particular query.

Re: Ask HN: How do you deal with people who trust LLMs?

#102

Post by smohare »

chipgap98 wrote: post #3

Is this any different than people who believe random things they read on sketchy news sites or social media?

There is a tendency for people to treat LLMs as oracles rather than token predictors. My guess is because they can answer in seeming technical fashion about a wider range of topics than your typical human. You can take these same people, who say have zero understanding of geopolitics, and they’ll apply a layer of (often misused) skepticism when confronted with information that doesn’t conform to existing beliefs.

That’s just what I’ve seen at a personal level though.

Re: Ask HN: How do you deal with people who trust LLMs?

#103

Post by dlm24 »

b00ty4breakfast wrote: post #98
dlm24 wrote: post #94

I feel like I can trust LLMs more than the majority of info on the web. We used to believe the same of Google searches. For me, for example have seen and experienced doctors making mis diagnosis (and they a reputable source), so what is the difference really? I guess your question depends on the context they using the LLM as well for and what sort of questions they are asking. Scientific fact based or opinion questio…

where do you think most of that info came from though? Not from the public library

I hear you, But my understanding is LLM can consume multiple sources of information and deduce what is the truth better and more accurately than a human clicking on multiple Google links and veryfying information and sources.

Re: Ask HN: How do you deal with people who trust LLMs?

#104

Post by reverius42 »

basilikum wrote: post #82
ericpauley wrote: post #42

Earlier quoted context omitted.

This is an oft-repeated meme, but I’m convinced the people saying it are either blindly repeating it, using bad models/system prompts, or some other issue. Claude Opus will absolutely push back if you disagree. I routinely push back on Claude only to discover on further evaluation that the model was correct. As a test I just did exactly what you said in a Claude Opus 4.6 session about another HN thread. Claude consid…

Can you share your system prompt?

I'm seeing the described behavior with whatever the default system prompt is in Claude Code.

Re: Ask HN: How do you deal with people who trust LLMs?

#105

Post by jazzyjackson »

ericpauley wrote: post #42
eranation wrote: post #21

Ask them to tell the LLM it's wrong... then when it goes "You are absolutely right!" to challenge it and say that it was a test. Then when it replies, ask it if it's 100% sure. They'll lose faith pretty quick.

This is an oft-repeated meme, but I’m convinced the people saying it are either blindly repeating it, using bad models/system prompts, or some other issue. Claude Opus will absolutely push back if you disagree. I routinely push back on Claude only to discover on further evaluation that the model was correct. As a test I just did exactly what you said in a Claude Opus 4.6 session about another HN thread. Claude consid…

If you have 10,000 people flipping coins over and over, one person will be experiencing a streak of heads, another a streak of tails.

Which is to say, of a million people who just started playing with LLMs, a bunch of people will get hit or miss, while one guy is winning the neural net lottery and has the experience of the AI nailing every request, some poor bloke is trying to see what all the hype is about and cannot get one response that isn’t fully hallucinated garbage

Re: Ask HN: How do you deal with people who trust LLMs?

#108

Post by JuniperMesos »

roguechimpanzee wrote: post #30

I think LLMs are fine for a "first pass" on a topic, but if I am researching something, I want a primary source rather than just the LLM-generated output. Do they have the primary source?

No different from what people said about Wikipedia when it was new (and justifiably so). How should one deal with people who trust Wikipedia?

Re: Ask HN: How do you deal with people who trust LLMs?

#109

Post by lokar »

dlm24 wrote: post #103
b00ty4breakfast wrote: post #98

Earlier quoted context omitted.

where do you think most of that info came from though? Not from the public library

I hear you, But my understanding is LLM can consume multiple sources of information and deduce what is the truth better and more accurately than a human clicking on multiple Google links and veryfying information and sources.

Deduce? No.
Post reply on HN