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

Improving recommendation systems and search in the age of LLMs

eugeneyan.com

Post reply on HN
Print view View original

11–20 of 98 posts

Re: Improving recommendation systems and search in the age of LLMs

#11

Post by pests »

whatever1 wrote: post #4
dmbche wrote: post #3

Earlier quoted context omitted.

It doesn't solve any problem, you can just search your files using your prefered file explorer (crtl-f) I'd assume most people organise their files so that they know where things are as well.

But file explorer does not read the actual files and build context. Even for pure text files that sometimes search functions can also access, I need to remember exactly the string of characters I am looking for. I was hoping an LLM would have a context of all of my content (text and visual) and for the first time use my computers data as a knowledge base. Queries like “what was my design file for that x service” ? To…

The photos apps do this well now. Can search Apple/Google photos with questions about the content of images and videos and get useful results.

Re: Improving recommendation systems and search in the age of LLMs

#12

Post by jamesblonde »

It is very interesting that Eugene does this work and publishes it so soon after conferences. Traditionally this would be a literature survey by a PhD student and would take 12 months to come out as some obscure journal behind a walled garden. I wonder if it is an outlier (Eugene is good!) or a sign of things to come?

Re: Improving recommendation systems and search in the age of LLMs

#14

Post by ozim »

nine_k wrote: post #5
dmbche wrote: post #3

Earlier quoted context omitted.

It doesn't solve any problem, you can just search your files using your prefered file explorer (crtl-f) I'd assume most people organise their files so that they know where things are as well.

> you can just search your files using your prefered file explorer This only work if you remember specific substrings. An LLM (or some other language model) can summarize and interpolate. It can be asked to find that file that mentions a transaction for buying candy, and it has a fair chance to find it, even if none of the words "transaction", "buying" or "candy" are present in the file, e.g. it says "shelled out $17…

I think the same, people are not organized - even with things that make them money and being organized could earn them much more.

Re: Improving recommendation systems and search in the age of LLMs

#15

Post by josephg »

visarga wrote: post #10
whatever1 wrote: post #2

Why we don’t have an LLM based search tool for our pc / smartphones? Specially for the smartphones all of your data is on the cloud anyway, instead of just scraping it for advertising and the FBI they could also do something useful for the user?

I found that ChatGPT or Claude are really good at music and shopping suggestions. Just chat with them about your tastes for a while, then ask for suggestions. Compared to old recommender systems this method allows much better user guidance.

Yeah, Claude helped me decide what to get my girlfriend for her birthday a few weeks ago. It suggested some great gift ideas I hadn’t thought of - and my girlfriend loved them.

Re: Improving recommendation systems and search in the age of LLMs

#16

Post by thorum »

In the age of local LLMs I’d like to see a personal recommendation system that doesn’t care about being scalable and efficient. Why can’t I write a prompt that describes exactly what I’m looking for in detail and then let my GPU run for a week until it finds something that matches?

Re: Improving recommendation systems and search in the age of LLMs

#17

Post by r4ndomname »

thorum wrote: post #16

In the age of local LLMs I’d like to see a personal recommendation system that doesn’t care about being scalable and efficient. Why can’t I write a prompt that describes exactly what I’m looking for in detail and then let my GPU run for a week until it finds something that matches?

This is exactly what I am hoping to get sometimes (but I would say, 1 week is maybe a little long).

If I go through my current tasks and see, that for some task I need a set of documents, emails, .., why cant I just prompt the system to get it in 30-ish minutes. But as someone already stated Apple Intelligence is supposed to fill this gap.

Re: Improving recommendation systems and search in the age of LLMs

#18

Post by whiplash451 »

thorum wrote: post #16

In the age of local LLMs I’d like to see a personal recommendation system that doesn’t care about being scalable and efficient. Why can’t I write a prompt that describes exactly what I’m looking for in detail and then let my GPU run for a week until it finds something that matches?

Why would it take a week?

Is this because you want it to continuously watch for live data that could match your need?

Re: Improving recommendation systems and search in the age of LLMs

#19

Post by pizza »

anonymousDan wrote: post #9

It's interesting that none of these papers seem to be coming out of academic labs....

Checking if a recommendation system is actually good in practice is kind of tough to do without owning a whole internet media platform as well. At best, you'll get the table scraps from these corporations (in the form of toy datasets/models made available), and you still will struggle to make your dev loop productive enough without throwing similar amounts of compute that the ~FAANGs do so as to validate whether that 0.2% improvement you got really meant anything or not. Oh, and also, the nature of recommendations is that they get very stale very quickly, so be prepared to check that your method still works when you do yet another huge training run on a weekly/daily cadence.

Re: Improving recommendation systems and search in the age of LLMs

#20

Post by pizza »

thorum wrote: post #16

In the age of local LLMs I’d like to see a personal recommendation system that doesn’t care about being scalable and efficient. Why can’t I write a prompt that describes exactly what I’m looking for in detail and then let my GPU run for a week until it finds something that matches?

It's worth pointing out that even with the largest models out there, coherence drops fast over length. In a local home ML setup, until somebody radically improves long-term coherence, models with y minutes of search.
Post reply on HN