this post was submitted on 27 Mar 2024
39 points (100.0% liked)
Technology
37724 readers
498 users here now
A nice place to discuss rumors, happenings, innovations, and challenges in the technology sphere. We also welcome discussions on the intersections of technology and society. If it’s technological news or discussion of technology, it probably belongs here.
Remember the overriding ethos on Beehaw: Be(e) Nice. Each user you encounter here is a person, and should be treated with kindness (even if they’re wrong, or use a Linux distro you don’t like). Personal attacks will not be tolerated.
Subcommunities on Beehaw:
This community's icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
Literally the worst possible usage. They're syntax generators, not search engines, and not knowledge fonts.
I don't know how to say this in a less direct way. If this is your take then you probably should look to get slightly more informed about what LLMs can do. Specifically, what they can do if you combine them with with some code to fill the gaps.
Things LLMs can do quite well:
These are all the building blocks for searching on the internet. If you are talking about local documents and such retrieval augmented generation (RAG) can be pretty damn useful.
That's not entirely fair either though... They can incorrectly summarize, omit important information, or just make stuff up.
True, though that isn't all that different from people doing knee jerk responses on the internet...
I am not claiming they are perfect, but for the steps I described a human aware of the limitations is perfectly able to validate the outcome. While still having saved a bunch of time and effort on doing an initial search pass.
All I am saying is that it is fine to be critical of LLM and AI claims in general as there is a lot of hype going on. But some people seem to lean towards the "they just suck, period" extreme end of the spectrum. Which is no longer being critical but just being a reverse fanboy/girl/person.
Fair, nuance is an endangered species.
Ask it to search or list all of Bach’s children and you can see the wheels completely fall off. It was inventing people with actual fake birth and death dates and also gave me some of Handel’s children!
What do you mean by "it"? The chatGPT interface? Could be, but then you are also missing the point I am making.
After all, chatGPT is just one of the possible implementations of LLMs and indeed not perfect in how they implemented some things like search. In fact, I do think that they shot themselves in the foot by implementing search through bing and implementing it poorly. It basically is nothing more than a proof of concept tech demo.
That doesn't mean that LLM's are useless for tasks like searching, it just means that you need to properly implement the functionality to make it possible. It certainly is possible to implement search functionality around LLMs that is both capable and can be reviewed by a human user to make sure it is not fucking up.
Let me demonstrate. I am doing some steps that you would normally automate with conventional code:
I started about by asking chatGPT a simple question.
It then responded with.
The following step I did manually, but is something you would normally have automated. I put the suggested query in google, I quickly grabbed the first 5 links and then put the following in chatGPT.
It then proceeded to give me the following answer
Going over the search results myself seems to confirm this list. Most importantly, except for the initial input, all of this can be automated. And of course, a lot of it can be done better, as I didn't want to spend too much time.
Gpt is fantastic at search. Like, check its work but it'll check hundreds of pages of results way faster than you can.