Ask HN: Do you still use search engines?
381–390 of 609 posts
Re: Ask HN: Do you still use search engines?
#382Earlier 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…
Firstly, "Evolutionary Arms Race" is not tautological, it is a specific term of art in evolutionary biology.
Secondly, "evolutionary arms race" is a correct answer, it is the general case of which the Red Queen hypothesis is a special case. I do agree with you that OP described a Red Queen case, though I would hesitate to say it was because of "equilibrium"; many species in Red Queen situations have in fact gone extinct.
Re: Ask HN: Do you still use search engines?
#383Search 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…
For example: Take the ingredient list of a cosmetic or other product that could be 30-40 different molecules and ask ChatGPT to list out what each of them is and if any have potential issues.
You can then verify what it returns via search.
Re: Ask HN: Do you still use search engines?
#384Earlier quoted context omitted.
Yeah, I need more coffee to decide for myself if double checking all sources is linear or exponential as it progresses to check the checks.
It might even be factorial since you also need to check the checks of the checks! Actually, it might be fully unbounded even for an n of 1.
Re: Ask HN: Do you still use search engines?
#385But now, the veracity of most LLMs' responses is terrible. They often include “sources” unrelated to what they say and make up hallucinations when I search for what I'm an expert in. Even Gemini in Google Search told me yesterday that Ada Lovelace invented the first programming language in the 18th century. The trust is completely gone.
So, I'm back to the plain old search. At least it doesn't obscure its sources, and I can get a sense of the veracity of what I find.
Re: Ask HN: Do you still use search engines?
#386Re: Ask HN: Do you still use search engines?
#387I was among the first to champion AI search, even before Perplexity rose to fame. You.com was the first AI search to quote sources well, and I used it extensively. But now, the veracity of most LLMs' responses is terrible. They often include “sources” unrelated to what they say and make up hallucinations when I search for what I'm an expert in. Even Gemini in Google Search told me yesterday that Ada Lovelace invented…
I mean, for everyone else it was never there to begin with. Hallucinations are constantly raised as the biggest issues with AI. According to the tests, and my experience, newer AI models are objectively better, not worse than the ones from a few years ago. They still have a long way to go/may never be fully trustworthy though.
What I have lost trust in, and what I and many feel has become much worse over the few years, is Google search, and all the other search engines that are based on it.
Re: Ask HN: Do you still use search engines?
#388Search engines are still required for me. LLM's still get lots of very important things wrong. Last night, I asked Claude 3.7 Sonnet to obtain historical gold prices in AUD and the ASX200 TR index values and plot the ratio of them, it got all of the tickers wrong - I had to google (it then got a bunch of other stuff wrong in the code). Also yesterday, I was preparing a brief summary of forecasting metrics/measures fo…
Was a bit more useful at questions like "Rank these stocks by exposure to the Chinese market", as you can prioritise your own research but in the end you just have to go through the individual company filings yourself.
Re: Ask HN: Do you still use search engines?
#389Earlier quoted context omitted.
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.
It's time to bind "Please be concise in your answer and only mention important details. Use a single paragraph and avoid lists. Keep me in the discussion, I'll ask for details later." to F1.
Re: Ask HN: Do you still use search engines?
#390Kagi is like Google in it's prime - fast, relevant and giving a range of results.