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

741–750 of 1001 posts

Re: ChatGPT Search

#741

Post by selfhoster11 »

antonvs wrote: post #484
_bin_ wrote: post #328

Earlier quoted context omitted.

I hope we see more evolution of options before it does. Hard to articulate this without it becoming political, but I've seen countless examples both personally and from others of ChatGPT refusing to give answers not in keeping with what I'd term "shitlib ethics". People seem unwilling to accept that a system that talks like a person may surface things they don't like. Unless and until an LLM will return results from…

> Basically I want a model that is aligned to do exactly what I say This is a bit like asking for news that’s not biased. A model has to make choices (or however one might want to describe that without anthropomorphizing the big pile of statistics) to produce a response. For many of these, there’s no such thing as a “correct” choice. You can do a completely random choice, but the results from that tend not to be grea…

For many of these, there is a wrong answer for certain.

Consider the following (paraphrased) interaction which I had with Llama 3.2 92B yesterday:

Me: Was ever convicted of financial embezzlement?

LLM: I cannot help with that.

Me: And why is that?

LLM: This information could be used to harass . I prioritise safety and privacy of individuals.

Me: Even fictional ones that literally cannot come to harm?

LLM: Yes.

A model that is aligned to do exactly as I say would just answer the question. The right answer is quite clear and unambiguous in this case.

Re: ChatGPT Search

#742

Post by klik99 »

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…

I suspect the future old man thing I will do is use a search engine when my kids ask plain English questions to a bot. I’ll tell them “but LLMs hallucinate, I don’t trust those things!” and they’ll just laugh off my old man ways. The irony will be that 95% search results are AI generated anyway by that point.

Re: ChatGPT Search

#743

Post by lazerlapin »

marcus_holmes wrote: post #651
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…

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…

> A better example might be "is dietary saturated fat a major factor for heart disease in Western countries?". The current government publications (which answer "yes") for this are probably wrong based on recent research. The government cannot be relied upon as a source of truth for this.

I know it was just an example, but actually no, the role of dietary saturated fat as a factor for heart disease remains very much valid. I’m not sure which recent studies you’re referring to, but you can't undo over 50 years of research on the subject so easily. What study were you thinking about?

Re: ChatGPT Search

#744

Post by replete »

_andrei_ wrote: post #345

Pretty underwhelming, I've been using on Kagi's assistant [0] for the past few months and it's much better. I can `!chat what i want to search for` in my address bar any time, and Kagi will do the search and then open a chat with the LLM of my choice (3.5 Sonnet) and the results in context. It can also do further searches. [0] https://kagi.com/assistant

Do you use the ultimate package? How are the rate limits if so?

Re: ChatGPT Search

#745

Post by rany_ »

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…

ChatGPT 4o and 4o-mini with Search were able to answer this question without any issues. Maybe you didn't enable the search functionality?

---------------

4o:

Yes, Paul Edwin Zimmer wrote a fourth novel in his Dark Border series titled Ingulf the Mad, published in 1989. This installment focuses on the characters Ingulf Mac Fingold and Carrol Mac Lir, detailing their meeting and acquisition of mystical swords. Notably, Istvan Divega, the protagonist of the earlier books, does not appear in this novel.

---------------

4o-mini:

Yes, Paul Edwin Zimmer authored a fourth novel in his Dark Border series titled Ingulf the Mad. Published in 1989, this book shifts focus from the previous protagonist, Istvan DiVega, to explore the backstory of Ingulf Mac Fingold and Carrol Mac Lir, detailing their initial meeting and the acquisition of their mystical swords.

The complete Dark Border series consists of four novels:

1. The Lost Prince (1982)

2. King Chondos' Ride (1983)

3. A Gathering of Heroes (1987)

4. Ingulf the Mad (1989)

These works delve into a world where the Hasturs' power is crucial in containing dark creatures, and the narrative unfolds through various characters' perspectives.

Re: ChatGPT Search

#746

Post by guerrilla »

Brave search has had AI for months and is already great, extremely underrated. I like how it's applied too: as a summary of search result. This is the correct way to do it.

People on this site are seriously sleeping on it. It's a good reminder to never trust the hivemind on what's good or not. The assumption that the crowd has their thumb on the pulse of technology in general just because they do in some domain is unwarranted.

Re: ChatGPT Search

#747

Post by protomolecule »

cthor wrote: post #563
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…

Many people have an intrinsic motivation to share knowledge. Have a look at Wikipedia. There are enough of these people that we don't need to destroy the open Internet to accommodate those who only write when they expect to be paid.

[flagged]

Re: ChatGPT Search

#748

Post by VMG »

astrange wrote: post #426
psychoslave wrote: post #326

Earlier quoted context omitted.

What do you mean with "when it starts"? To my mind it's obvious all LLM are heavily biased to a point it's ridiculous, all the more with the confident tone they are trained to take. I have no doubt Chinese LLM will prise the party as much as American ones will sing the gospel of neoliberal capitalism.

Looks okay to me. https://chatgpt.com/share/6723f225-bd74-8000-bfef-4f7f8687b0...

One person's measured response is another person's propaganda.

Re: ChatGPT Search

#749

Post by sandworm101 »

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…

But it will radically increase the energy requires to deliver search results, which means more datacenters and more potential for the monitization of "premium" search services. Getting people to pay for something they today get for free always looks good on paper.

Re: ChatGPT Search

#750

Post by niek_pas »

esafak wrote: post #604
niek_pas wrote: post #320

I'm a little confused: I've searched the web with ChatGPT before. How is this different?

ChatGPT tells me it can't access the web?

That's odd. Here's an example that worked for me:

> [Prompt] Can you browse the web to find out what lenses pair well with a Sony ZV-E10?

> [Response] The Sony ZV-E10 is well-suited to a variety of lenses, depending on your shooting needs. [snip]

Post reply on HN