Live data from Hacker News

AI chatbots are not a replacement for search engines

iai.tv

301–310 of 415 posts

Re: AI chatbots are not a replacement for search engines

#301

Not sure if I'm missing something but if the authors claim: 1. That chatbots don't understand what they are producing -> a search engine doesn't either. 2. The benefit of search is that you engage in sense-making -> you actually need to do that with a chatbot too. 3. You would want access to the sources -> that's already fixed for today's chatbots (see perplexity.ai, for example, which offers links next to its claims…

Providing sources is the most important feature missing in chatgpt and perplexity.ai does indeed attempt to solve it. The other problem is that chatgpt is often factually incorrect and gives no hint of uncertainty.

I've been using perplexity.ai recently and often times the results are more helpful than google and it tends to spew less opaque bullshit than chatgpt.

Re: AI chatbots are not a replacement for search engines

#302

Earlier quoted context omitted.

I agree that a hybrid could work, although ChatGPT struggles to keep context with more than a dozen paragraphs, so I doubt it could summarize millions of results. And in either case, you're not solving the problem that commenters here are trying to solve: Google's bad results will still affect your search, so ChatGPT will be fed largely by dubious blogspam.

Even in a small number of paragraphs language models hallucinate. For example Barack Obama, it’s not hard for me to trick it into saying he was born in Chicago. He was not. But there’s a ton of text about Barack Obama in Chicago. Plus, Michelle was born there. When predicting the most likely next token for “Barack Obama was born in ______” there’s a lot of confounding text. No, there’s a fundamental issue in that sta…

And any kind of "tuning" of the weights to get better results is going to be so bespoke that you might as well just curate the response yourself

Re: AI chatbots are not a replacement for search engines

#303

Earlier quoted context omitted.

OTOH I could imagine a hybrid situation where the AI Bot searches Google for you and restates the millions of results Google gives it

I agree that a hybrid could work, although ChatGPT struggles to keep context with more than a dozen paragraphs, so I doubt it could summarize millions of results. And in either case, you're not solving the problem that commenters here are trying to solve: Google's bad results will still affect your search, so ChatGPT will be fed largely by dubious blogspam.

Though for that matter a ChatGPT based product would be even more vulnerable to the same thing that made Google search suck: content sources gaming its process

Re: AI chatbots are not a replacement for search engines

#304

Earlier quoted context omitted.

The problem with ChatGPT as a replacement for Google is that it was not designed to produce accurate facts, and it shows. This model cut its teeth writing articles about the discovery of unicorns in the Andes[0] for goodness sake! It's a language model, and a very impressive one at that, but language is used to express falsehoods and fiction just as regularly as it is used to express truth. This doesn't mean that it…

RIP google. There's a joke that the best place to hide a murder is on page 2 of google search. The fact is GPT has at bare minimum parsed the top page of google and reasoned about the top results to give the best answer with as much context of why it reasoned so. GPT is basically a superset of google with added reasoning. I can't see it giving worse results than Google. Both will produce a bogus answer if you ask a b…

I think it's really problematic to use the word "reason" to describe what GPT does. As others have commented in this thread, GPT is a language model, which in no way reasons about anything it writes. It is simply writing whatever fits statistically to the prompt and context. Attributing reasoning or too much intelligence to this could prove quite dangerous.

Re: AI chatbots are not a replacement for search engines

#306

Earlier quoted context omitted.

No, you are probably right. It has no guardrails for generating a true citation. When you ask it for citations, its programming generates the form of citation. As the authors of the article discuss, it has no model of reality to understand that citations are not just a form of words and symbols put together.

> As the authors of the article discuss, it has no model of reality to understand that citations are not just a form of words and symbols put together. Which is the exact same issue that plagues it for the answer it’s generating a citation for. I believe that it can be trained to improve this, and I believe it can be nearly solvable but I don’t believe it’s a solvable problem. It can be trained to get facts mostly ri…

The problem is mostly solved though. ChatGPT doesn't have the feature to cite its sources, but some other models do https://www.deepmind.com/blog/building-safer-dialogue-agents

Re: AI chatbots are not a replacement for search engines

#307
post #57

They are not a replacement, but unfortunately search engines are turning into AI chatbots too. When I think of a search engine I want a "grep for the Internet", not an "AI". Looking up part numbers for ICs and other electronic components is the most prominent application where search engines like Google have gotten far worse in recent years, and AI ain't going to work there either.

A grep for the internet is what most of us technical users want, but they are optimizing for the more common user who structures queries more like natural language (e.g. "How can I tie my shoelaces so they don't get untied easily") instead of what me or you would query ("secure shoelace knots") I'm surprised there hasn't been a separation of some sort of more technical search engine for developers and the classic Goo…

They are optimizing for ads. Asking how to tie your shoelaces usually start with three sponsored links where you can buy shoelaces.

Re: AI chatbots are not a replacement for search engines

#308
post #277

Earlier quoted context omitted.

> ChatGPT, if asked correctly, will instead generate one perfect document based on millions of the documents This is the "self-driving cars will obviously be better than human drivers given that they're trained on millions of humans' driving behavior" of chatbots. In my experience, this is a huge stretch and wishful thinking.

I mean, it happens in stages - I’m already using chatgpt for plenty of useful tasks that I would otherwise google (and then some). Similarly self driving cars are better than humans at plenty of specific things (collision detection/aversion for instance) but not a wholesale replacement of humans just yet obviously.

I was willing to give ChatGPT the benefit of the doubt after being initially impressed with its results, but I've also had it confidently tell me blatantly wrong information when the correct information is a Google search away at most or no human would confidently make such a mistake.

What makes it worse is that it spits out paragraphs confidently, where some of it might be right or close to right, but the rest might be subtly incorrect. Without domain knowledge, you might not pick up on it. Hell, you might even be convinced of the false information based on the arguments for it that the AI writes out.

At least with search engines you can cross reference multiple sources if you aren't confident in your ability to assess the first thing you read.

Re: AI chatbots are not a replacement for search engines

#309
In my view, this is an example of a problem with AI ethicists: they tend to naively overestimate the statu quo. In this particular case, the premise seems to be that people obtain reliable information from traditional search engines, hence chatbots cannot replace them because they are unreliable.

The truth: many uses of a search engine aren't even things where reliability matters much (what's the weather tomorrow? what's artist X's latest song?). For those where it does matter, results are unreliable as well, because the web is full of all kinds of crap and any attempt at sorting the wheat from the chaff failed many years ago. And sure, users can try to assess the reliability of the sources. Good luck with that (not you specifically, well-educated and tech-savvy HN reader, but at a population level). All those extremist propaganda sites that are climate denialists, antivaxxers, etc. have readers that think they are perfectly reliable.

Of course there are situations where checking the sources works (e.g. a scientist working on a literature review)... which, of course, are the situations where those people aren't going to trust ChatGPT anyway.

In summary, I think this kind of criticism widely misses the mark. The problem with this and other current issues is the corporate interests feeding us all kinds of crap, not whether the way of feeding it is more convenient or less.

Re: AI chatbots are not a replacement for search engines

#310
post #22

The way I see it: - Today's search engines will give you links to millions of documents - ChatGPT, if asked correctly, will instead generate one perfect document based on millions of the documents To me, that's a clear evolution of the search engine, especially with all the SEO & ad spam that's plaguing Google and others currently. I wasn't ready to pay a monthly fee for an ad-free Google. I am ready to pay for somet…

Can't agree more.

When using Google & co. most of my time is wasted trying to filter low quality sponsored or high SEO reaults.

ChatGPT gives me an excellent summary of what I wanted to know without all the noise.

Post reply on HN