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

Prediction: Semantic search (boring) ends up bigger than generative AI (cool)

news.ycombinator.com

Post reply on HN
Print view View original

11–20 of 33 posts

Re: Prediction: Semantic search (boring) ends up bigger than generative AI (cool)

#11

Post by throwthrowuknow »

falcolas wrote: post #8
fullshark wrote: post #3

Predicting a new technology doesn't live up to the hype is always the smart bet. But that doesn't mean you can't: 1. Carve out a career and build some useful tech with it 2. Get VCs to give you money to build a company that gets acquired 3. Build a genuinely profitable private enterprise with it. Etc. Multiple possibilities for (professional) success here which doesn't involve generative AI being bigger than semantic…

It's both a sign of the times and a shame in my opinion that none of these options include the words "sustainable" or "long term". Just short term, unsustainable play using someone else's money to follow a fad. But that's probably just my elder millennial desire for stability that's beyond my reach.

You need short term playfulness in order to find new markets and ideas. Everyone has these “peanut butter or chocolate” opinions when the answer is always “both”

Re: Prediction: Semantic search (boring) ends up bigger than generative AI (cool)

#12

Post by binarymax »

compacct27 wrote: post #9
binarymax wrote: post #6

I work full time in this space and can tell you with 100% certainty that it won’t be one or another, but a combination of them (plus other tech like learning to rank). A search system is always an ensemble of many parts that make up a quality experience. Generative AI will undoubtedly be a part of that from now on. Look up the retriever/reader pattern to learn more about this. It’s a really interesting field and I’m…

Bought the book, thanks! Dying to learn more here, just did a semantic search project and I have more questions than it answered.

Awesome, thanks!!!

Trey is currently writing more on the Generative AI stuff, and the three of us are giving a panel discussion at the upcoming Haystack search relevance conference https://haystackconf.com/2023/

Re: Prediction: Semantic search (boring) ends up bigger than generative AI (cool)

#13

Post by beepbooptheory »

falcolas wrote: post #8
fullshark wrote: post #3

Predicting a new technology doesn't live up to the hype is always the smart bet. But that doesn't mean you can't: 1. Carve out a career and build some useful tech with it 2. Get VCs to give you money to build a company that gets acquired 3. Build a genuinely profitable private enterprise with it. Etc. Multiple possibilities for (professional) success here which doesn't involve generative AI being bigger than semantic…

It's both a sign of the times and a shame in my opinion that none of these options include the words "sustainable" or "long term". Just short term, unsustainable play using someone else's money to follow a fad. But that's probably just my elder millennial desire for stability that's beyond my reach.

The whole first part of the infamous "Parrots" paper is concerned with the potential negative environmental outcomes of relying/adopting large LLMs, but nobody ever talks about that part!

Many were/are rightly concerned with proof of work mining, now ontop of all that there is an even bigger incentive on a global scale to have a million high powered GPUs running all the time. And then they tell us these things will completely replace not only index-based search, but education, customer service, all document processing, etc.

Even if these things can underpin a viable business, its going to still push the needle that much further into unviable planet. Which, I dont know, doesn't feel like a particularly sophisticated future to me.

Re: Prediction: Semantic search (boring) ends up bigger than generative AI (cool)

#14

Post by theolivenbaum »

binarymax wrote: post #6

I work full time in this space and can tell you with 100% certainty that it won’t be one or another, but a combination of them (plus other tech like learning to rank). A search system is always an ensemble of many parts that make up a quality experience. Generative AI will undoubtedly be a part of that from now on. Look up the retriever/reader pattern to learn more about this. It’s a really interesting field and I’m…

That looks awesome, just ordered a copy too, thanks for sharing the link!

Re: Prediction: Semantic search (boring) ends up bigger than generative AI (cool)

#15

Post by treffer »

I consulted ChatGPT about a bank issue. I didn't have a phone number but ChatGPT was able to spill out a number with a recommendationto call. I verified the number and it was indeed correct (easy: google the number)

I couldn't find the number with searches (I tried before) and I didn't even know that it might be helpful (didn't find it before, so how could I tell) but the AI spilled out and told me how useful it is.

This made me change my mind on search vs. AI. I got what I needed while I was unable to retrieve it with search. It was at least a 10x improvement over search.

But I do think there is space for both.

Re: Prediction: Semantic search (boring) ends up bigger than generative AI (cool)

#17

Post by musha68k »

treffer wrote: post #15

I consulted ChatGPT about a bank issue. I didn't have a phone number but ChatGPT was able to spill out a number with a recommendationto call. I verified the number and it was indeed correct (easy: google the number) I couldn't find the number with searches (I tried before) and I didn't even know that it might be helpful (didn't find it before, so how could I tell) but the AI spilled out and told me how useful it is.…

The compression can be lossy though and the model often “predicts” complete garbage even with GPT-4. It would be great to get a probability for correctness “Mr. Spock” style in chat - especially so as in case of a telephone number…

Re: Prediction: Semantic search (boring) ends up bigger than generative AI (cool)

#19

Post by JohnFen »

> Imagine semantic search for your file system

I've found that the semantic search things I've seen so far for local systems have been unusable, largely because of the time and cycles needed for the indexing.

But if that problem is ever fixed, I'll be all in on it.

Re: Prediction: Semantic search (boring) ends up bigger than generative AI (cool)

#20

Post by ravenstine »

treffer wrote: post #15

I consulted ChatGPT about a bank issue. I didn't have a phone number but ChatGPT was able to spill out a number with a recommendationto call. I verified the number and it was indeed correct (easy: google the number) I couldn't find the number with searches (I tried before) and I didn't even know that it might be helpful (didn't find it before, so how could I tell) but the AI spilled out and told me how useful it is.…

Yeah there is no way I'm giving up my Kagi subscription just yet.

I don't really see ChatGPT as a search engine because I think that's not its strength, though it can certainly deliver in that area sometimes. I like using ChatGPT to clarify information I already have some idea about, and just need a straight forward summary for. This is different than asking it for specific shreds of information. If you treat ChatGPT as an intelligence and not a robot performing reflex over the internet, it's going to be correct often enough. But you always gotta use your head. I don't ask ChatGPT anything that's too far out of my domain of knowledge because, if it gets something wrong, I won't have the Spidey senses to realize it.

Post reply on HN