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

ChatGPT Search

openai.com

Post reply on HN
Print view View original

671–680 of 1001 posts

Re: ChatGPT Search

#671

Post by righthand »

mulmen wrote: post #486
righthand wrote: post #482

Earlier quoted context omitted.

> those visions, users simply asked questions and received reliable answers - nobody had to fact-check the answers ever. It’s a fallacy then. If my mentor tells me something I fact check it. Why would a world exist where you don’t have to fact check? The vision doesn’t have fact checking because the product org never envisioned that outlier. A world where you don’t have to check facts, is dystopian. It means the end…

If you can’t trust the result of a query how can you trust the check on that query which is itself a query? If no information is trustworthy how do you make progress?

Do you just inherently accept the result of a query? Or do you always carry some skepticism around? Something something build trust through fact checking.

Re: ChatGPT Search

#672

Post by tliltocatl »

LeoPanthera wrote: post #352
freediver wrote: post #241

Been thinking about this a lot [1]. Will this fundamentally change how people find and access information? How do you create an experience so compelling that it replaces the current paradigm? The future promised in Star Trek and even Apple's Knowledge Navigator [2] from 1987 still feels distant. In those visions, users simply asked questions and received reliable answers - nobody had to fact-check the answers ever. C…

Solving this problem will require us to stop using the entire web as a source of information. Anyone can write anything and put it up on the web, and LLMs have no way to distinguish truth from fantasy. Limiting responses to curated information sources is the way forward. Encyclopedias, news outlets, research journals, and so on. No, they're not infallible. But they're infinitely better than anonymous web sites.

We had this long time before, it is called "books". It is also not very usable for niche topics, or for recent events (because curators need time to react).

Re: ChatGPT Search

#673

Post by marcus_holmes »

judahmeek wrote: post #664
marcus_holmes wrote: post #651

Earlier quoted context omitted.

I agree that this is the core question, but I'd put it as: Who Gets To Decide What Is True? With a search paradigm this wasn't an issue as much, because the answers were presented as "here's a bunch of websites that appear to deal with the question you asked". It was then up to the reader to decide which of those sites they wanted to visit, and therefore which viewpoints they got to see. With an LLM answering the que…

> We're seeing how that pans out in Australia and it's not good. How are we seeing how that pans out when Australia's misinformation bill is still just a proposal?

Fair point. I think just that there's a general acceptance that "something must be done" and that the government are the people to do it is pretty alarming. It's a short step from here to a Ministry of Truth, and I can see Australia taking that step pretty soon.

Re: ChatGPT Search

#674

Post by rushingcreek »

omani wrote: post #653
rushingcreek wrote: post #437

Earlier quoted context omitted.

We're working on a complete redesign of Phind to make it more of a search competitor :) What were the limitations you ran into?

are you from phind? phind got worse over time. what happened? obviously you have changed something. but still, thanks for making it available for free. I hope it stays this way.

Thanks for the feedback —- can you share a bit more about what you feel has gotten worse? Have you just been using the default model?

Re: ChatGPT Search

#675

Post by marcus_holmes »

dataflow wrote: post #659
marcus_holmes wrote: post #651

Earlier quoted context omitted.

I agree that this is the core question, but I'd put it as: Who Gets To Decide What Is True? With a search paradigm this wasn't an issue as much, because the answers were presented as "here's a bunch of websites that appear to deal with the question you asked". It was then up to the reader to decide which of those sites they wanted to visit, and therefore which viewpoints they got to see. With an LLM answering the que…

> To paraphrase a recent conversation I had with a friend: "in the USA, can illegal immigrants vote?" has a single truthful answer ("no" obviously) Er, no, the meaning of the question is ambiguous, so I'm not sure "has a single truthful answer" is accurate. What does "can" mean? If you mean "permitted", then no. But if you mean can they vote anyway and get away with it? It's clearly happened before (as rare as it mig…

At the risk of derailing the conversation down a completely different rabbit hole... As I understand it, only citizens are legally entitled to vote, and voting requires a government-issued ID and the voter to be enrolled.

How did they vote and get away with it previously?

(also, as per another comment, if you know that this happened then surely they didn't get away with it?)

Re: ChatGPT Search

#676

Post by jrflowers »

marcus_holmes wrote: post #673
judahmeek wrote: post #664

Earlier quoted context omitted.

> We're seeing how that pans out in Australia and it's not good. How are we seeing how that pans out when Australia's misinformation bill is still just a proposal?

Fair point. I think just that there's a general acceptance that "something must be done" and that the government are the people to do it is pretty alarming. It's a short step from here to a Ministry of Truth, and I can see Australia taking that step pretty soon.

What is a not-alarming answer to “Who gets to decide what’s true?”

Re: ChatGPT Search

#677

Post by coredog64 »

XorNot wrote: post #667
dataflow wrote: post #659

Earlier quoted context omitted.

> To paraphrase a recent conversation I had with a friend: "in the USA, can illegal immigrants vote?" has a single truthful answer ("no" obviously) Er, no, the meaning of the question is ambiguous, so I'm not sure "has a single truthful answer" is accurate. What does "can" mean? If you mean "permitted", then no. But if you mean can they vote anyway and get away with it? It's clearly happened before (as rare as it mig…

If they got away with it then how do you know it's happened?

Obviously off-topic, but see the recent case of the Chinese student who illegally voted and then turned himself in.

Re: ChatGPT Search

#678

Post by davideg »

GolfPopper wrote: post #602

Every time I see one of these topics, I go ask chat GPT a question to which I know the answer on a topic where I would like to be able to get useful answers to similar questions that I do not know the answer to. This time it was, "Did Paul Edwin Zimmer write a fourth Dark Border novel?" (Real answer: Yes, Ingulf the Mad . You can find the answer on his Wikipedia page.[1]) ChatGPT's[2] answer: "Yes, Paul Edwin Zimmer…

Several folks have already mentioned that ChatGPT with search returns the correct answer to your question (with a source to explore directly).

I really think this latest release is a game changer for ChatGPT since it seems much more likely to return genuine information than ChatGPT answering using its model alone. Of course it still hallucinates sometimes (I asked about searching tabs in Firefox Mobile and it told him the wrong place to find that ability while citing a bunch of Mozilla help docs), but it's much easier to verify that by clicking through to sources directly.

It feels like a very different experience using ChatGPT with search turned on and the "Citations" right side bar left open. I get answers from ChatGPT while also seeing a bunch of possibly relevant links populate. If I detect something's off I can click on a source and read the details directly. It's a huge improvement on relying on the model alone.

Re: ChatGPT Search

#679

Post by ethbr1 »

parpfish wrote: post #669
marcus_holmes wrote: post #651

Earlier quoted context omitted.

I agree that this is the core question, but I'd put it as: Who Gets To Decide What Is True? With a search paradigm this wasn't an issue as much, because the answers were presented as "here's a bunch of websites that appear to deal with the question you asked". It was then up to the reader to decide which of those sites they wanted to visit, and therefore which viewpoints they got to see. With an LLM answering the que…

I was thinking something similar. I like the google auto-ai summary for little trivia facts and objective things (who played so and so in the movie? How heavy is a gallon of milk?) this is stuff that is verifiable and could theoretically just be queried from some sort of knowledge base. But for anything remotely subjective, context dependent, or time sensitive I need to know the source. And this isn’t just for hot bu…

> could theoretically just be queried from some sort of knowledge base

Google bought Freebase in 2010 [0] and scaled it [1].

[0] https://en.m.wikipedia.org/wiki/Freebase_(database)

[1] https://en.m.wikipedia.org/wiki/Google_Knowledge_Graph

Re: ChatGPT Search

#680

Post by intelVISA »

Stratoscope wrote: post #580
hn_throwaway_99 wrote: post #525

Earlier quoted context omitted.

> I'm also cautiously optimistic though. We'll get there, but it's gonna be a bit shakey for a minute or two. But I don't understand how all of these AI results (note I haven't used Kagi so I don't know if it's different) don't fundamentally and irretrievably break the economics of the web. The "old deal" if you will is that many publishers would put stuff out on the web for free, but then with the hope that they cou…

> the history of the domestication of the tomato" that Google essentially forced on recipe sites for SEO competitive reasons That may help with SEO, but another reason is copyright law. Recipes can't be copyrighted, but stories can. Here is how ChatGPT explained it to me: > Recipes themselves, particularly the list of ingredients and steps, generally can't be copyrighted because they're considered functional instruct…

> can't be copyrighted because they're considered functional instructions

by that logic software shouldn't be copyrighted either!

Post reply on HN