Live data from Hacker News

Ask HN: Do you still use search engines?

news.ycombinator.com

461–470 of 609 posts

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

#464

Earlier quoted context omitted.

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

Can you elaborate?

Whenever you search for some advice (laptop with best battery life in 2025) or reviews (hubspot vs. salesforce) you are barraged with torrents of AI-generated slop. Now that it's also taking over the search engine itself (AI summaries) your whole experience will be dumbed down to the point of mindless automaton consuming pre-packaged tidbits of revenue-generating pre-approved sanitised elite-friendly information.

I've always found it curious how the level of technology in Children of Men seemed to have stalled at around the time of the outbreak. From where I see it, the maturation of LLMs is the zombie outbreak for human communication.

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

#465

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…

Agree 100% I tried perplexity to "search" My use case was similar to one described above.

I know what I'm looking for. I just need exact URL.

Perplexity miserably fails at this.

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

#466
post #372

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…

While I do like LLMs for these tasks, unfortunately this one failed you but was a near enough miss that you couldn't see it. What you were really looking for is the Red Queen problem/hypothesis/race, named after a quote from Through the Looking Glass, with the Queen explaining to Alice: "Now, here, you see, it takes all the running you can do, to keep in the same place." In particular, the Red Queen term is specifica…

> this one failed you but was a near enough miss that you couldn't see it. What you were really looking for is the Red Queen

GP was looking for a specific term that they had heard before. It was co-/evolutionary arms race, and ChatGPT guessed it correctly.

Also GPT-4o elaborated the answer (for me at least) with things like:

    > However, the specific kind of equilibrium you're referring to—where neither side ever fully "wins", and both are locked in a continuous cycle of adaptation and counter-adaptation—is also captured in the idea of a “Red Queen dynamic”.

    > You could refer to this as:
      * Red Queen dynamics in plant-insect coevolution
      * A coevolutionary arms race reaching a dynamic equilibrium
      * Or even evolutionary stable strategies (ESS) applied to plant-herbivore interactions, though ESS is more game-theory focused.

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

#468
Yeah, I still use search engines.

LLMs are amazing for technical research or getting a quick overview and a clear explanation without clicking through ten links. But for everyday searches — checking restaurant hours, finding recent news, digging into niche forums, or comparing product — search engines are still way better.

I don’t think it’s a matter of one replacing the other — they serve different purposes.

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

#470
I've recently tinkered with creating an automated install script for a home server. It was good practice for me and I want to setup a small home server with pihole, sonarr and so on. I've created it with Claude and ChatGPT and both preformed poorly. Huge chunks of code, that might be running, but creates much more mess than it should. Only after going and reading the documentation the old fashioned way and with the help of search, I was able to reduce the size of the script and solve many problems with it.
Post reply on HN