Hacker News Reader

Comment by sedatk | Hacker News Reader

I've been a paying Kagi user for a few months now. The only thing that made me miss Google results was immediate answers: the answers that are extracted from a prominent web page and shown directly, so you don't have to click the link. Actually, Kagi has some of that for certain queries, but it's not as extensive as Google's.

So, contrary to the most of the comments here, I support their AI endeavors for the sake of providing answers directly, saving us from clicks.

Their search results are already very good. Can't wait to see Kagi flourish.

View on HN

I have personally started to avoid Google’s and others immediate answers, because they are often very wrong because they are picked out of the contex.

They try to show what you want to see, but it often means something else.

This is so true! While planning a trip abroad last year we were unsure about whether $thing is legal in $country. Google proclaimed in bold letters that, yes, $thing is legal in $country, but this line was taken from a site with the title "common misconceptions about traveling in $country" an in fact $thing was not legal.

Such a basic mistake, I haven't trusted the instant results ever since.

I remember there was another story here about Google returning bad results for what to do for a particular medical emergency. The page had a list of "Do"s and "Don't"s, but Google had grabbed the list of the "Don't"s and displayed it as the immediate results.

I have used Kagi for several months now, and I find that the ability to decide which searches I want quick answers for to be useful. There are certain searches where I feel comfortable with accepting a quick answer, and others where I don't think it would be useful. Being able to avoid the clutter unless I want it is nice.

Sports scores and stocks. If kagi inlined those results I would be very happy to not need to use the Google bang.

Additionally, the google bang destroys suggested terms and with no kagi history I'm typing the whole query.

I don't really web search for those things but I can see why that would be useful. There is a feedback site that they are very responsive on; you should post there if it hasn't been posted yet.

Re: bangs ruining suggestions: you can put the bang at the end of the query instead of at the beginning.

I just tried two searches in Kagi: "aapl" and "super bowl 2024". Both gave me inline "quick answer" things. Maybe it's new or inconsistent?

Sometimes they're wrong period. The source was clearly a bad one and every other source disagrees.

They just released a major improvement to these, actually :). So keep trying it! At the risk of sounding like a shill: kagi is by far the best money I spent last year. The “programming” “academia” “small web” and (especially!) “PDF” buttons are worth their weight in GOLD.

These are the main two improvements from last week:

  We added Wolfram|Alpha to enhance our capabilities in calculations, unit conversions, and time queries for better results. This solves a huge number of issues reported for these kind of queries as the results now come from a computational knowledge authorithy.

 In the same spirit of getting answers faster, now simply starting your query with an interrogative word (what, where, who, which, when, how) or just ending it with a question mark (?) will automatically trigger Quick Answer.

Oh, interesting. I was actually wondering what had changed. That wolfram integration needs some work. Right now it's consistently just simplifying fractions. I keep having to "!g" in brave to get google to do simple math for me.

https://i.imgur.com/ghmUcAh.png

That's.... good, though?

What happens if you ask for 23000.0/10500?

As someone who has used wolfram alpha for a long time, I wish they'd just put both. They do on queries like 23000/105000, but not on queries like 23000 = x*105000

It's not wrong, I suppose, but a break from the behavior I've learned for this sort of instant answer across google, ddg, and kagi as long as I can remember.

I can't actually think of a situation where I want to simplify a fraction like that.

I’ve been really liking the quick answers[1] that Kagi added. The doc gives some info as to what triggers it so it seems less random.

[1] https://help.kagi.com/kagi/ai/quick-answer.html

Oh that's awesome. I think I bumped into it once, but my search flow is usually always in a rush that I haven't had time to stop and think about it.

You can click the "Quick Answer" button on the search results page to trigger the same feature. I think it appears whenever there is more than one word in the search query.

You can also force its appearance by sticking a ? at the end of a query, either space separated or otherwise.

Thanks for linking to the docs. I really like this feature, but as you said, it felt like it showed up at random

Since last week, it will trigger whenever your search query ends with a ? or starts with How or Why or other interrogative words https://kagi.com/changelog#3179

They disabled the interrogative words trigger because people found it too intrusive. ? still works

One thing I miss from Google is a reliable built-in calculator. I know I could just use some other calculator app but the habit of just typing stuff into my address bar is hard to shake.

Kagi also has a calculator, but for a lot of queries it gives questionable results, for example for `210/8` it returns `105/4`. Technically correct, sure, but almost never what I want.

FWIW I think this has improved radically in the past few weeks thanks to their integration with Wolfram. I haven't tried it yet though but was pleased to see that in the changelog

It's apparently the Wolfram|Alpha integration that returns 105/4.

I agree. I've also found out that "210/8.0" returns the desired result.

Just tested this out, you can add "in decimal" to get it as a decimal.

just "decimal" works too

Ultimate/normal customer, and i agree. Personally i think AI _is_ Search, and while we don't need to force them together in some massive behemoth now - laying foundation for being familiar, comfortable and well integrated in the future seems foundational to today. In my eyes at least.

Strongly held belief that I think is backed up by academic consensus: we should not treat LLMs as stores of knowledge. As my mantra goes, “language models, not knowledge models”. So the future of search might involve LLMs at a very fundamental level (and I think it will!), but they’ll never be the central component. Humans will never ever ever invent a better knowledge system than a database / a piece of paper, I guarantee.

Agreed but there's nothing about this discussion that requires LLMs are the store for anything. That's an implementation detail. One that's not that controversial imo. The current tech is clearly too destructive to "store" anything.

If anyone from DDG is here, please sort out your calendar one? I reported it in early January that it was (understandably) erroneously assuming 'jan calendar' still meant current_year+1; still doing it for February.

March is ok though, so I think actually the implementation was always buggy, not just now it's 2024, but it's checking if month is <= current month where it should just do <.

If you are looking for an answer, not a web page per se, type "!quick your question".

As an example: https://kagi.com/search?q=most+deadly+battle+in+world+war+1&...

I am also a paying customer providing my 2c; only rarely do I use google, and then mostly for maps and image search. I enjoy not seeing ads and the power functionality within the engine.

chatgpt is on the extreme side: you only get immediate answers without the webpage

> immediate answers

wildly varying in accuracy :)

Reply on news.ycombinator.com