this post was submitted on 26 Aug 2026
600 points (97.6% liked)
Technology
87572 readers
4602 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 3 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
I like using AI for coding (no, I don't blindly commit massive features), but any time I ask it questions that don't have super clear-cut answers obvious to the layman from a quick google search, it tends to give "good enough" answers which are actually "nowhere near".
Go ask it (well, really, google search) something to do with tuning an Audi 3.0 tdi ASB or BMK engine and it'll think you have a nice Garrett turbo that's easy to build hybrids from and a weak CP4 pump that can implode on you and take out the entire fuel system... Whereas you actually have a weak ass BorgWarner turbo that can't support bigger internals and a super strong CP3 pump because it was shamelessly using forum threads about the newer versions with the 4 digit codes (CDYA, CASA, etc) as the source.
These are the things you easily know when you've either read a lot of forum threads, or peeked under the hood of one of these engines. But most AI tools' web search tends to just look at the first threads it finds and deem that good enough.
As a Cummins owner, it makes me smile to know the CP3 has earned its reputation in other circles.
I once drove to the next city 60 miles away at 55 mph, because that's as much fuel as the CP3 could force past my failed low pressure fuel pump. If I had a CP4 I would have been stuck at the side of the road with a big problem instead.
It's a text generator that strings together plausible word sequences. It doesn't actually understand what an engine or a turbo is beyond the contexts and constellations in which those words frequently occur. It has no reliable way to tell which parts of the prompt are technically critical and need to match exactly.
In that way, it's not too different from laypeople like me: I have no idea about turbos and pumps either. I still might figure out that I need to check for the specific model and engine, but without knowkng exactly what I'm dealing with, chances are I might end up trusting the same (wrong) results.
I would assume if you include the keywords BorgWarner and CP3 pump, the more specific context might bias the probability space of likely answers towards more relevant results. That makes it a potentially useful assistant for people who already have that level of expertise and are just looking for specific answers on particular cases... except you'd still have to read the actual sources to make sure.
Basically, it could serve as a more sophisticated search engine for natural language, an iteration on previous query processing and correlation technologies. If I don't need to remember the exact wording or sender of a mail about a specific topic, a model trained on the terminology might pick out rough matches based on related words without needing to get the exact keywords right.
Frankly, I think that's the most sensible application of LLMs: find sources, not facts. Using it for fact checking is like skating on a recently frozen lake where you can't tell which parts are solid enough to carry you and which ones will suddenly break.
Ah but the thing is, the sources it finds are themselves wrong. They're talking about different things. If it finds the right sources, the information is most likely pretty good.
It's entirely possible that this could still be tuned somehow, but the way it is now, I wouldn't trust anything that comes out of it unless I know enough to verify the output myself, meaning it's pretty useless to laymen (which is whom a "veracity" bot would be for)
That's what I was trying to get at, yeah: The word-correlator can't tell the difference because it can't tell which part of the prompt is critical for the difference. It also can't judge whether the sources themselves are accurate about the things they're actually talking about. It find sources that seem related, then aggregates some likely response from those sources and spits it out. By its own metrics and limitations, that has to be "good enough" (but as you say, may be wildly wrong).
My suspicion is that adding more specific terms to the prompt may increase the textual "distance" between the fitting results and the irrelevant ones, thus tilting the source selection towards the more accurate match, but that requires you to know those specific terms in the first place.
With a general model? I doubt it.
A subject-specific model could probably be tweaked to recognise particular tokens and assign them more weight. Depending on the subject, you might be able to add pre-processing logic to crossreference certain keywords (like model and engine type) with some objective database (like a table describing which pumps a given motor might have, if that makes sense?).
You could also pick the training material more diligently to ensure you only have qualified, reliable sources for that subject. That would require a lot of work, since you also need enough material for the model to be representative.
And you'd have to do that for every specialised field out there.
Hit the nail on the head there. For all we know, it'll "correct" facts by doubling down on common misconceptions.