[HN Gopher] Kagi Sidekick (alpha)
       ___________________________________________________________________
        
       Kagi Sidekick (alpha)
        
       Author : jviide
       Score  : 133 points
       Date   : 2024-02-20 21:18 UTC (1 hours ago)
        
 (HTM) web link (sidekick.kagi.com)
 (TXT) w3m dump (sidekick.kagi.com)
        
       | ggoo wrote:
       | I just want good search results. This feels like a distraction.
        
         | laweijfmvo wrote:
         | Agree, I thought I was paying for search so they could focus on
         | building search. Anything that feels like a money-raising or
         | God-forbid acquisition play is concerning.
        
         | evanharwin wrote:
         | Agreed. Seems like web search implementation (both from Kagi
         | and all its competitors!) could be almost endlessly improved
         | upon, and any non-search feature is at odds with that.
         | 
         | Maybe there's an argument that people who might use this, might
         | also be people with sites that'd be valuable to index, and thus
         | it'd both be nice for them and improve search for all users? :)
        
         | Kerrick wrote:
         | Given that their motivation for this is to find more sites and
         | pages to index, it seems like it should improve the quality (or
         | at least quantity) of results thanks to a larger index.
        
           | ggoo wrote:
           | Hm, I may have judged too quickly then - I do hope this
           | translates to better quality. Will wait and see.
        
       | mostlysimilar wrote:
       | I love Kagi and I'm a happy customer. I hope their endeavors in
       | AI features don't distract too much from the core offering of a
       | web search engine. That's the only thing I want from them.
        
       | kelvie wrote:
       | Disclaimer: Happy paid kagi user for over a year now.
       | 
       | Why would they offer this for free for small websites? This isn't
       | some VC-backed company getting ready to data-mine us and collect
       | users for enshittification purposes, and in general, Kagi is the
       | site people recommend when they say "if you're not the customer,
       | you're the product".
        
         | hungariantoast wrote:
         | Maybe because they can comfortably afford to? Maybe because
         | some people who operate businesses are actually kind and
         | generous? Maybe because this service doesn't cost them much to
         | operate for "small/personal websites"? Maybe because it's a
         | clever way to get more people to pay for the service in the
         | long run, after they initially try it out for free?
        
         | atestu wrote:
         | My take is this helps them index the web, and they're
         | particularly interested in small website with great, niche,
         | organic content.
         | 
         | See also: https://kagi.com/smallweb
        
           | psytrx wrote:
           | I've had the same thoughts on those. Maybe it also allows
           | them to gather data on whether/how people interact with a
           | webpage itself, which may be an indicator for its quality.
        
       | smcleod wrote:
       | Early Kagi adopter here. I love Kagi search and their
       | summarisation features, but I'd rather they just focus on high
       | quality and configurable search and summarisation results rather
       | than new products.
        
         | unshavedyak wrote:
         | It seems like a feature which is mutually beneficial. Ie user
         | activity on embedded sites helps indicate interest in Kagi
         | index updates.
         | 
         | Isn't this entirely in-line with your desires? Better quality
         | search results by way of having up to date indexes?
        
           | nicce wrote:
           | The problem is that it can go also terribly wrong. (New way
           | for SEO optimisation)
        
             | BadHumans wrote:
             | Kagi users are in such a minority that I don't see how it
             | is worth it for anyone to optimize for Kagi search results.
        
               | nicce wrote:
               | Yet. If you want to be better than Google, you need to
               | avoid Google's mistakes.
        
               | al_borland wrote:
               | With Kagi's customers being users, not advertisers, they
               | can put in features to mitigate against problems caused
               | by SEO, like how Kagi bundles up all the "Top X abcdefg"
               | lists that turned Google into trash.
        
               | Nevermark wrote:
               | Tiny Kagi has already shown an ability to produce better
               | results than massive Google, despite them both dealing
               | with the same SEO site gaming/structuring. Which is the
               | reverse of what would be expected, if Google was also
               | focused on quality.
               | 
               | Kagi has already dodged the SEO bullet.
               | 
               | Disclaimer: I pay for Kagi. You should too!
        
               | dvaun wrote:
               | This seems like a problem of the search space rather than
               | solely Google's. How are you supposed to guard a system
               | which, by its nature, provides financial incentive to
               | others to game it?
               | 
               | No matter what weights and checks are put in place, some
               | observers will notice how their rankings change and make
               | appropriate modifications.
               | 
               | This isn't solved by Kagi's product, either. I'm a happy
               | user and use it as my daily driver. That doesn't mean
               | that, if it increases in popularity, the results will
               | remain unskewed.
        
       | MostlyStable wrote:
       | As a paying customer, I agree that the only thing I care about
       | from Kagi is search, _but_...I think that there is a very non-
       | trivial chance that in the near future, search almost entirely
       | gets eaten by AI. It makes sense to me that a search company
       | would be exploring AI and its interaction with search. While I
       | hope this doesn 't become the main focus (until and unless it
       | _has_ to be), the history of companies like Kodak (who was a
       | "film" company and therefore chose to ignore digital cameras)
       | should be instructive. If they completely ignore the potential
       | replacement to search, they might get good at search just in time
       | for that to become irrelevant.
        
       | freediver wrote:
       | Kagi founder here. This is very early (alpha) concept built by a
       | single Kagi Labs developer in a few weeks. The proper
       | infrastruture and product is not built yet. We are launching a
       | prototype to get feedback and gauge demand.
       | 
       | Why does this exist?
       | 
       | It would be an efficient way for us to build and expand our own
       | index. Assuming users of this would be Kagi users, we would
       | expand our index by tens of thousands of high quality? personal
       | websites, hobby projects, startups, documentation websites, etc.,
       | also helping to surface them in our results (where relevant, like
       | we already do with Kagi Small Web initiative [1]). It is a win-
       | win for both our users and Kagi.
       | 
       | It would also be a way for Kagi to get some exposure outside of
       | kagi.com (provided the search widget has some branding on it).
       | 
       | This is why it makes sense to offer it for free for smaller
       | sites/projects.
       | 
       | And crowdsourcing index is completely opposite direction of one
       | that causes deterioration of web search results in ad-supported
       | search where few entities control the majority of space [2], so
       | we like it.
       | 
       | That is the plan - and since this is a "Labs" project, we are
       | open to it crashing and burning. Know we do not, until we try.
       | Try and try again, we must.
       | 
       | [1] https://kagi.com/smallweb
       | 
       | [2] https://detailed.com/google-control/
        
         | paranoidxprod wrote:
         | Thank you for the explanation!
         | 
         | While I agree with others that AI can take away from a products
         | core vision, I've been very happy with Kagi's path and roadmap.
         | I feel like the AI products that you guys have released have
         | served well as complements to search, and hope the trend
         | continues.
         | 
         | Hopefully this helps with indexing while offering a cool
         | service to small creators!
         | 
         | Edit: I forgot to say, the change where a `?` appended to a
         | search triggering the quick answers was an amazing change. I
         | would love to see more features that can be invoked by
         | appending or prepending to the search query.
        
         | meantub wrote:
         | I think it would be interesting if like the website ranking
         | that is done on Kagi there was a way to rate the search results
         | to lower or higher it's ranking in search results. It would be
         | a little different though since the website ranking on Kagi is
         | for users but ranking the search results might just improve the
         | intended search result that many people are looking for.
         | 
         | I guess this assumes that you aren't already doing that when
         | they click one option over another for a certain search term.
         | 
         | Just thinking about searching through some documentation sites
         | and you get a dumb result you weren't looking for at the top,
         | and would want to deprioritize that result.
        
         | greazy wrote:
         | Kagi user here and scientist.
         | 
         | I think kagi sidekick would be very well received in the
         | bioinformatics space. Lots of complex docs that require end
         | users to digest large complex data.
         | 
         | Can it be tuned to only point users to the docs and not answer
         | questions?
        
         | spenczar5 wrote:
         | I love your transparency. Saying how it benefits Kagi, not just
         | how it is a cool feature for users, is refreshing. It makes me
         | trust more of what you say, and builds some sense of what the
         | product's direction could be. Thanks.
        
         | quinncom wrote:
         | [delayed]
        
       | numbers wrote:
       | This is tangential to search but I wonder if this is a way to
       | push more indexing info into the kagi index or if it's just
       | another fun little project?
        
       | sedatk wrote:
       | 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.
        
         | bbor wrote:
         | 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.
        
           | mayneack wrote:
           | 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
        
         | unshavedyak wrote:
         | 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.
        
         | al_borland wrote:
         | 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
        
           | sedatk wrote:
           | 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.
        
       | runamuck wrote:
       | I pay for Kagi. I also have a small hobby site and would love to
       | try this out.
        
       | nabogh wrote:
       | I cancelled my Kagi subscription because it's a little too
       | expensive for me in the unlimited search tier. And I search too
       | much for the limited search tier.
       | 
       | I can't help but wonder if my money was being spent on pet
       | projects like this instead of improving/maintaining the search.
        
         | chias wrote:
         | All companies allocate some fraction of their resources towards
         | innovation outside of what is currently their core feature-set.
        
       ___________________________________________________________________
       (page generated 2024-02-20 23:00 UTC)