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

Ask HN: Do you still use search engines?

news.ycombinator.com

Post reply on HN
Print view View original

431–440 of 609 posts

Re: Ask HN: Do you still use search engines?

#431

Post by GuinansEyebrows »

rrr_oh_man wrote: post #181
foragerdev wrote: post #90

I still use search engines. I do not like to be spoon fed. I want to learn from the real people. Not AI generated shit. ChatGPT or other LLMs are trained on old data, they do not contain newer information. Newer information and knowledge are produced by the real humans. LLMs are great for quick fact checking, but not for searching. For example: What's the height of mount Everest? LLMs will most probably give right an…

> Newer information and knowledge are produced by the real humans. Not anymore

Can you elaborate?

Re: Ask HN: Do you still use search engines?

#433

Post by GuinansEyebrows »

Yes, of course, because i find it way more informative to search in broad terms, digest varying sources and arrive at conclusions rather than by asking a question that invariably lacks enough context (that I’d find by reading docs or SO posts) to actually produce helpful results, let alone a deeper understanding of the topic than before i started.

Learning is fun! Reading is good for you! Being spoon fed likely-inaccurate/incomplete info or unmaintainable code is not why i got into computers.

Re: Ask HN: Do you still use search engines?

#434

Post by protocolture »

atonse wrote: post #404
telchior wrote: post #389

Earlier quoted context omitted.

You've just made me realize that I actually do need that as a macro. Probably type that ten times per day lately. Others might include "in one sentence" or "only answer yes or no, and link sources proving your assertion".

If you’re using ChatGPT, add it to your memory so it always remembers that you prefer that.

Yep. Somehow I made mine noticably grumpier but I dont know which setting or memory piece did the job.

I really like not being complimented on literally everything with a wall of text anymore.

Re: Ask HN: Do you still use search engines?

#435

Post by averageRoyalty »

miloignis wrote: post #281

Yes, I use search engine(s) constantly - namely Kagi, which really does feel like Google used to. I tried using LLMs for a recent project of mine when I was trying to figure out if something was possible, and they were actively misleading, every time. My issue for this project was that what I was asking for did end up not being currently possible, but LLMs wouldn't tell me that and would make up incorrect ways to sol…

Agreed, for resource location, Kagi feels like Google did 20 years ago.

I use LLMs as a sounding board. Often if I'm trying to tease out the shape of a concept in my head, it's best to write it out. I now do this in the form of a question or request for information and dump it into the LLM.

Re: Ask HN: Do you still use search engines?

#436

Post by schrodinger »

RyanOD wrote: post #376
Modified3019 wrote: post #264

Earlier quoted context omitted.

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…

Agreed. I'm increasingly using ChatGPT to research topics. In that way, I can refine my question, drill down, ask for alternatives, supply my own supplementary information, etc. I think of AI as an intelligent search engine / assistant and, outside of simple questions with one very specific answer, it just crushes search engines.

it's especially great in voice mode. I love to take a long walk or jog with earbuds in and use it to learn a new topic. I don't well through indoctrination, I learn much better by asking it to give a very big picture overview, start to build an intuitive understanding, and then start asking pointed questions to fill in the blanks and iterate towards a deeper understanding. I find ChatGPT's voice mode to be very engaging in that use case—far more so than Gemini's actually—and I've used it to learn a bunch of new technologies. It's like having a never-bored professor friend you can call and ask endless questions and keep getting answers without annoying it!

Re: Ask HN: Do you still use search engines?

#438

Post by xbmcuser »

Yes I still use search engine specifically google as 1 habit 2 it's Ai search results with links to the actual content. Without the ai results answering my questions I would not have probably stayed with google. Google also seems to mitigate hallucinations by only showing content with links

Re: Ask HN: Do you still use search engines?

#439

Post by disambiguation »

I use both, but direct search is faster since I have to fact check the LLM's answer.

2 recent success stories:

I was toying around with an esp32 - i was experimenting to turn it into a bluetooth remote control device. The online guides help to an extent, setting up and running sample projects, but the segue into deploying my own code was less clear. LLMs are "expert beginners" so this was a perfect request for it. I was able to jump from demos to live deploying my own code very quickly.

Another time I was tinkering with opnsense and setting up VLANs. The router config is easy enough but what I didnt realize before diving in was that the switch and access point require configuration too. What's difficult about searching this kind of problem is that most of the info is buried in old blog posts and forum threads and requires a lot of digging and piecing together disparate details. I wasn't lucky enough to find someone who did a writeup with my exact setup, but since LLMs are trained on all these old message boards, this was again a perfect prompt playing to its strengths.

Re: Ask HN: Do you still use search engines?

#440

Post by mips_avatar »

SoftTalker wrote: post #265
Okawari wrote: post #35

I still prefer tranditional search engines over LLMs but I admit, its results feels worse than it has traditionally. I don't like LLMs for two reasons: * I can't really get a feel for the veracity of the information without double checking it. A lot of context I get from just reading results from a traditional search engine is lost when I get an answer from a LLM. I find it somewhat uncomfortable to just accept the a…

One thing I don't like about LLMs is that they vomit out a page of prose as filler around the key point which could just be a short sentence. At least that has been my experience. I admit I don't use LLMs very much.

One problem with LLMs is that the amount of "thinking" they do when answering a question is dependent on how many tokens they use generating the answer. A big part of the power of models like deepseek R1 is they figured out how to get a model to use a lot of tokens in a logical way to work towards solving a problem. The models don't know the answer they come to it by generating it, and generating more helps them. In the future we'll probably see the trend continue where the model generates a "thinking" response first, then the model summarizes the answer concisely.
Post reply on HN