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

481–490 of 1001 posts

Re: ChatGPT Search

#481

Post by bruh2 »

encom wrote: post #388
steelframe wrote: post #306

Earlier quoted context omitted.

> Search is pretty much dead to me. I've heard reports that requesting verbatim results via the tbs=li:1 parameter has helped some people postpone entirely giving up on Google. Personally I've already been on Kagi for a while and am not planning on ever needing to go back.

Fuzzy search is cancer. I search for $FOO, click a result, Ctrl-F for $FOO ==> Not found. Many such cases. If there's a way to force DuckDuckGo to actually do what I tell it to, I'd love to hear it.

I thought this problem will disappear upon switching to Kagi, but it suffers from the same disease, albeit to a lesser extent.

I remember reading a Google Search engineer on here explain that the engine just latches on some unrendered text in the HTML code. For example: hidden navbars, prefetch, sitemaps.

I was kinda shocked that Google themselves, having infinite resources, couldn't get the engine to realize which sections gets rendered... so that might have been a good excuse.

Re: ChatGPT Search

#482

Post by righthand »

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…

> 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 of curiosity and the end of “is that really true? There must be something better.”

You’re just reading into marketing and not fact checking the reality in a fact-check-free world.

Re: ChatGPT Search

#483

Post by greenavocado »

umvi wrote: post #451
whizzter wrote: post #300

This is probably Google's Altavista moment, by making their results crappier by the year in search of Ad dollars everyone has felt that there is a potential for search to be better and once that becomes available they'll be in a continious game of catch-up. Yes, Google has their own AI divisions, tons of money and SEO is to blame for part of their crappiness. But they've also _explicitly_ focused on ad-dollars over a…

At some point it seems like Google switch to ML-based search instead of index based search. You can search for very specific combinations of lyrics and scenes: "eyes on me pineapple bucket of water house of cards chess time loop" and you won't surface a link to the music video featuring all of those things ( https://www.youtube.com/watch?v=AlzgDVLtU6g ), you'll just get really generic results of the average of your q…

Has google completely stopped working for anyone else?

I can still search things, i get results but, they're an ordered list of popular places the engine is directing me to. Some kind of filtering is occurring on nearly every search i make that's making the results feel entirely useless.

Image search stopped working sometime ago and now it just runs an AI filter on whatever image you search for, tells you there's a man in the picture and gives up.

Youtube recommendations is always hundreds of videos i've watched already, with maybe 1-2 recommendations to new channels when i know there's millions of content creators out there struggling who it will never introduce me to. What happened to the rabbit holes of crazy youtube stuff you could go down?

This product is a shell of its old self, why did it stop working?

Re: ChatGPT Search

#484

Post by antonvs »

_bin_ wrote: post #328
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 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 great. That’s where RLHF comes in, for example: train the model so that its choices are aligned with certain user expectations, societal norms, etc.

The closest thing you could get to what you’re asking for is a model that’s trained with your particular biases - basically, you’d be the H in RLHF.

Re: ChatGPT Search

#485

Post by orthecreedence »

swyx wrote: post #399
lottin wrote: post #392

Earlier quoted context omitted.

Maybe it's just me but I have no interest in having a computer algorithm interpret data for me. That's a job that I want to do myself .

then you are blissfully unaware of how much data is already being interpreted for you by computer algorithms, and how much you probably actually really like it.

> how much you probably actually really like it.

This comes off as condescending. As things have gotten more algorithmic over the last two decades, I've noticed a matching decrease in the accuracy and relevance of the information I seek from the systems I interact with that employ these algorithms.

Yes, you're right that there are processing algorithms behind the scenes interpreting the data for us. But you're wrong: I fucking hate it, it's made things worse, and layering more on top will not make things any better.

Re: ChatGPT Search

#486

Post by mulmen »

righthand wrote: post #482
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…

> 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?

Re: ChatGPT Search

#487

Post by lofaszvanitt »

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…

Kagi also drinks the koolaid, namely the knowledge navigator agent bullshite.

"The search will be personal and contextual and excitingly so!"

---

Brrrr... someone is hell-bent on the extermination of the last aspects of humanity.

Holy crap, this will be next armageddon, because people will further alienate themselves from other people and create layers of layers of unpenetrable personal bubbles around themselves.

Kagi does the same what google does, just in a different packaging. And these predictions, bleh, copycats and shills in a nicer package.

Re: ChatGPT Search

#488

Post by rurban »

Etheryte wrote: post #472
rurban wrote: post #464

I just detected perplexity for a proper AI search yesterday. My test question today was: Which cbmc solver is multi-threaded? Perplexity gave me the correct and best answers, with links to the relevant arxiv papers. The new ChatGPT search gave me only cadical as answer, plus 2 irrelevant wrong answers (not multi-threaded), but missed all other multi-threaded solvers. => It's crap. Neither Google nor ddg gave me any r…

It's hard to cross check since you didn't mention what you consider are good answers, but the quick answer snippet on Kagi says: > The Yogar-CBMC and JCBMC solvers are notable multi-threaded variants of the CBMC (C Bounded Model Checker) framework: ... Followed by further details and references. The search results themselves look relevant and reasonable to me, but again, outside my area of expertise.

Both are bad answers

Re: ChatGPT Search

#489

Post by JSDevOps »

kernal wrote: post #294

what time is it? >Currently, I don’t have access to real-time data like time and date. You can check the time on your device or search "current time" online for the latest local time wherever you are. Oh dear, we're off to a bad and slow start already.

The world is literally on fire and we are setting fire to more forests because AI can’t tell the time and date
Post reply on HN