Kozoru, a new question answering engine, is talking more openly about its approach to search on its home page. From their first blog entry:
We believe that kozoru is a necessary first step towards the next stage of search technology. Instead of entering keywords into the search bar, you’ll be able to ask a question and get an answer. In fact, kozoru doesn’t understand keywords. We know that might be a little hard to believe, but you can really only ask kozoru questions.
There are some big claims on the site:
After all, how can we do this in less than 9 months when others are still trying to solve this problem after 20 or more years? However, that’s probably the easiest question to answer.
Basically, we’re free to do whatever we want. It may sound odd, but the secret sauce at kozoru is that we aren’t constrained by keywords or neural nets or the traditional academic notions of what A.I. should do.
And I really feel that’s how it is with any disruptive technology. A few key people come together and say, “Why has everybody been doing it this way?” It was that way with the Manhattan Project. It was that way with James Watson. It was that way at PARC.
We’re betting it’s that way with kozoru.
Well, we’re waiting to see….
6 thoughts on “Kozoru Talking a Bit More”
Thanks for the mention John. But how can I convince you that our named is spelled “kozoru” instead of “kozuru”?
My fifth grade daughter’s #1 search resource for her homework projects is now Brainboost. She goes there before she tries Google.
“It doesn’t take me to a web page which might have the answer I want, it takes me straight to the answer”.
Brainboost certainly comes to mind in this situation. Chris Fillius, guy I used to work with, did some reviews of it on searchlounge.org.
The core idea – transforming questions into declarative sentences — has been around as long as AI. The same technique can be tried manually. For instance, type “The English Channel is * miles wide” into Google and you get some answers. Unfortunately, the top-ranked answer, from fark.com, is five miles off from the other answers, so I can see where Brainboost might add some value.
ZF, you make a great point and that’s exactly what we want to do, only much better. This next generation is already tiring of traditional keyword search and we believe it’s only a matter of time before we see a sea change in the industry.
“Time is the only luxury left in the world…”
Q: Why did Google succeed?
Q: Should we write more words in the future?
A: No. The search engines will know more about you and your context. Search history, social networks, blogs…
Q: Could you describe the search engine in 2014?
A: EPIC 2014
Speed and time are increasingly critical, but for a reason few people appreciate. The key point is that every day there are more things we want to get done via the web, while the total amount of time we want to spend in front of the screen is limited. This pressure will not abate any time soon, it can only continue to increase year by year. Hence the need for ever more rapid solutions is relentless. In the end the most precious thing you can do for me on the web is to give me back my time. It’s a complete reversal of all that ‘Cool site of the Day’ stuff.