this post was submitted on 14 May 2025
619 points (98.7% liked)
Technology
72865 readers
1525 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related news or articles.
- Be excellent to each other!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
- Check for duplicates before posting, duplicates may be removed
- Accounts 7 days and younger will have their posts automatically removed.
Approved Bots
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
LLMs are absolute garbage for knowledge retrieval.
Generalized LLMs like ChatGPT are. If you train a model on your own documentation then all it “knows” is what is in the docs and it can perform very well at finding relevant results. It’s just kind of a context-aware search engine at that point.
The problem again is that companies mostly aren’t doing that, they’re trying to replace humans with ChatGPT.
Except that your context aware search engine would tell you when there is no result and AI will just make shit up and distort the results it did find.
They are "media transformers" and might be useful if limited to it.
Knowledge retrieval certainly not, as "they" know nothing besides how likely one data fragment is to appear near other data fragments.
I've tested it with both python and Cisco iOS pretty thoroughly and it very convincingly gets things wrong a lot.
The problem with that is the constant hallucinations and complete lack of correctness checks.
So your overall point is that AI is a better search engine. "It's like google, but better."
This is both likely true, and no where near fantastical enough to justify the trillion dollar hype cycle.
"Fixes companies internal documentation" is actually a huge get for AI, and would be worth some real hype, but yeah.
That's still peanuts compared to the marketing, which is why people are getting pretty tired of the whole AI push. The actual, incremental improvements are being run over roughshod by snake oil salesmen.
The thing is that this is increasingly not true, hasn't been true with blockchain and crypto that was all garbage and no substance, not with the metaverse hype, not with any of the hype Elon Musk tried to create (hyperloop?) and not with AI as a worker replacement.
There just isn't any useful bit that sticks around in many cases and where there is those useful bits were never part of the hype or have been around for much longer than the hyped part.
Sharepoint search functionality comes to mind. Our team commonly refers it as write-once storage as once you throw something in there you'll never find it again. And yes, we stole the term from somewhere.
So at best it might be useful for hinting.
When I try that, I just get confidently incorrect answers.
my dad said the same about excel. it just gives him incorrect results compared to his handwritten sheet. now let's get you to bed grandpa.
The idea that all new technologies are going to be successful just because some were in the past is just about the most ridiculous take in this entire thread.
you could pay a mathematician instead of cpu slob. just think of the people who lost their jobs because of excel.
🙄