271–280 of 609 posts
We're in a bubble here.
No, I find it unwilling to produce factual information. For example Jeep consistently lands at the bottom of the reliability ratings. Try asking GPT if Jeeps are reliable. The response reads like Jeep advertising.
Yes, often unreliable. And, they will give different answers at different times. https://chatgpt.com/share/67f57459-2744-8009-a94e-3b67dce8fd... “[Jeeps] often score below average in reliability rankings from sources like Consumer Reports and J.D. Power.”
Search is primarily a portal - you know a particular resource exists, you just don't know its exact URL. You hear about this new programming language called "Frob", and you assume it must have a website. So you google "Frob language". You hear that there was a plane crash in DC, and assume (CNN/AP/your_favorite_news_site) has almost certainly written an article about it. You google "DC plane crash." LLMs aren't ever…
The reason is pretty simple. If the result you want is in the first few search hits, it's always better. Your query is shorter so there is less typing, the search engine is always faster, the results are far better because you side step the LLM hallucinating as it regurgitates the results it remembers on the page your would have read if you searched.
If you aren't confident of the search times, it can take 1/2 an hour of dicking around with different terms, clicking though a couple of pages of search results for each set of term, until you finally figure out the lingo to use. Figuring out what you are really after from that wordy description is the inner magic of LLM's.
Exclusively. I don't want to think of a question to ask, or think about phrasing some prompt so I get a useful result, I just want to through a few related words and terms into a search box and see where that gets me, and then use the results to refine my search terms further.
Search is primarily a portal - you know a particular resource exists, you just don't know its exact URL. You hear about this new programming language called "Frob", and you assume it must have a website. So you google "Frob language". You hear that there was a plane crash in DC, and assume (CNN/AP/your_favorite_news_site) has almost certainly written an article about it. You google "DC plane crash." LLMs aren't ever…
IMO an example of a good use case for an LLM, which would be otherwise very hard to search for, is clarifying vague technical concepts. Just yesterday I was trying to remember the name of a vague concept I’d forgotten, with my overall question being: “Is there a technical term in biology for the equilibrium that occurs between plant species producing defensive toxins, and toxin resistance in the insect species that f…
Like I could interrogate an LLM about something technical “X” or I could just search “X documentation” and get to the ground truth.
Earlier quoted context omitted.
> Really, for many “page searches”, a good search engine should just be able to take you immediately to the page. Are you feeling lucky?
Exactly :-) Unfortunately you can’t really show ads if you take someone directly to the destination without any interstitial content like a list of links…
I use a search engine 99% of the time. Occasionally i use an LLM, but even for checking the most simple information I am not able to have any confidence that the answer it gives is correct. It seems to lie to me every time i use it and contradicts itself when i tell it that it made an error. It provides no citation to where it got its information and that seems completely essential. I very rarely see any use for it.…
Earlier quoted context omitted.
Except when search engines bury the thing you're obviously looking for under an entire page of sponsored ads, then that convenience argument starts to not hold up as well...
If LLMs aren't already doing this, they certainly will soon. And it'll be even more insidious and "invisible" than sponsored search results.