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

471–480 of 609 posts

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

#471

Post by dharmab »

sshine wrote: post #360
star-glider wrote: post #159

This is my favorite thing about Kagi; you can do both. If you just append a question mark, it'll run the search through a simple LLM and give you those results (with citations) right before standard search. From there, you can proceed into a more sophisticated frontier model if that's more effective. "Search" can mean a lot of things. Sometimes I just want a website but can't remember the URL (traditional); other tim…

And sometimes you have all the data, but it’s too much, so you ask for a summary and ask elaborating questions.

I've found this ineffective for anything where I need a factual answer and brilliantly where I need the vibe of subjective or fictional things.

Bad: summarizing scientific research or technical data

Great: finding travel ideas or clarifying aspects of a franchise's fictional universe.

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

#472

Post by jeffhuys »

BobaFloutist wrote: post #196
saltcured wrote: post #171

Earlier 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.

Everything reminds me of her… and she’s called Factorio. We’re on a break. She’s not good for me, but oh my do I love her.

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

#474

Post by emptyfile »

jacobr1 wrote: post #317
anoldperson wrote: post #288

AFAICT ChatGPT is mostly useless and can't be trusted to answer questions accurately. So no, mostly all search engines. To be honesty I'm surprised anybody uses it for anything other than trivial uses.

Are you using a paid version? Do you use web-search? And have you tried alternatives like Claude? I've mostly switched to using Claude these days, with MCPs for websearch and fetching specific remote or local files. It answers questions generally very accurately (from the source documents it identifies) and includes citations. I've found that people that haven't really tried the latest models, and just rely on whatev…

[dead]

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

#475

Post by dailykoder »

mips_avatar wrote: post #441
wruza wrote: post #329

Earlier quoted context omitted.

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.

Yeah but it kind of kneecaps the model. They need tokens to "think". It's better to have them create a long response then distill it down later.

You need tokens to create more revenue for the company that is running the LLM. Nothing more, nothing less

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

#476

Post by Kostic »

I've stopped using search engines actively 18 months ago. My first stop is an LLM. Once I understand what I actually need, I do a web search to go to the product/tool website. I do this not because LLMs are that good but because web search result quality went way down in the same period.

One interesting trend that I like is that I started using local LLMs way more in the last couple of months. They are good enough that I was able to cancel my personal ChatGPT subscription. Still using ChatGPT on the work machines since the company is paying it.

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

#477

Post by Hard_Space »

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.

No matter how many times I get ChatGPT to write my rules to long-term memory (I checked, and multiple rules exist in LTM multiple times), it inevitably forgets some or all of the rules because after a while, it can only see what's right in front of it, and not (what should be) the defining schema that you might provide.

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

#479

Post by voidUpdate »

jacobr1 wrote: post #317
anoldperson wrote: post #288

AFAICT ChatGPT is mostly useless and can't be trusted to answer questions accurately. So no, mostly all search engines. To be honesty I'm surprised anybody uses it for anything other than trivial uses.

Are you using a paid version? Do you use web-search? And have you tried alternatives like Claude? I've mostly switched to using Claude these days, with MCPs for websearch and fetching specific remote or local files. It answers questions generally very accurately (from the source documents it identifies) and includes citations. I've found that people that haven't really tried the latest models, and just rely on whatev…

It's an interesting business model to give a version that everyone says is awful to people just trying it out, and locking the actually useful version behind a paywall, so anyone who doesn't want to immediately give money gets a bad experience...

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

#480

Post by exe34 »

brokencode wrote: post #303
exe34 wrote: post #275

Earlier quoted context omitted.

that sounds like a really great example of..... searching through vector embedding. I don't think the LLM part was technically necessary.

Okay, so how does the average person search through vector embedding? I would like to try this out.

I didn't say the average person should use it, I was thinking the search functionality could be implemented that way and save on burning up the planet to tame Moloc.
Post reply on HN