Cuil Sucks At Search (Go Google!)
I love the idea behind Cuil, the latest search engine in a long list of failures (Mahalo, Ask, Powerset) to challenge Google. As Mashable explains, they are pulling out all the stops to hit Google from multiple directions across their core search competency:
Enter Cuil, a very serious competitor, packed with ex-Googlers (Tom Costello and Anna Patterson are the backbone of Cuil, and they’ve both worked at Google), and claiming to have the largest index of websites – 120 billion – in the world.
It doesn’t end there: Cuil pulls pretty much every trick in the book. Big claims about the biggest index, privacy concerns (IP addresses of users aren’t saved, making it impossible for a third party to request it from them), semi-semantic approach (Cuil’s engine recognizes the relations between certain words on a web site, which helps it rank pages better). Hell, they even pulled the energy-saving trick: the front page of Cuil is completely black, in contrast to Google’s eye-poking whiteness.
Check out the Slashdottie thread for more discussion. I’m not interested in going there; rather I’m more concerned with how relevant the results from Cuil are, compared to Google, in a stricter context of information retrieval. After all, a search engine is about finding information.
Let’s start with a query “how to rip a dvd” in Cuil and Google:
4 of the 9 total results are spam from Ebooksbay. An additional 4 are for converting MP3s. The final result (which is quite spammy) is for ripping DVDs to a variety of formats. Score: 11%.
Google gives you 7 DVD ripping guides, and three spams site of ripping software. Essentially, you have to give it a Score: 100%, since it’s pretty much the baseline in our test. Just based on what I’ve seen so far, this will be a comparison not of relative merits, but of how much less relevant the results from Cuil are compared to Google.
Wait, what is that in the rightmost result!!!? Yes, that winsome young woman is carefully inspecting a ConcurrentHashMap! Ahm, bad image / search results correlations aside, the search listings fail to list the authority Java documentation source (Sun’s website) and instead list 2 mirrors (java 5 and 6), 4 bug reports, 3 mailing list discussions, and 2 random libraries with a similarly named class. Score: 50%.
Google nicely gives us the Sun Java page as the first result, 2 snippets of code using this class, 6 guides to using concurrent hash maps, a benchmark, one of the same random libraries as Cuil (Oswego), and a different random library (backport-util). I’d give them Score: 80% at this task.
Anyway, I’m getting tired of writing this. Cuil just doesn’t deliver fast, consistent, high-quality search results. The relevance is quite low, in spite of the interface improvements and searching / clustering / recommendation features.
| This entry was posted on Tuesday, July 29th, 2008 at 9:16 pm and is tagged with ripping dvds, relative merits, semantic approach, tom costello, googlers, ripping software, google, whiteness, privacy concerns, finding information, final result, how to rip a dvd, information retrieval, competency, backbone, ip addresses, competitor, baseline, cuil, third party. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback. |
12 Responses to “Cuil Sucks At Search (Go Google!)”
Leave a Reply
I’ve seen quite a few articles bashing cuil for it’s poor search result.. But your article shows some empirical comparisons.. nice work..
The “matching image with result” algorithm seriously needs work.. yours is a much forgiving example than some of the website I’ve seen..
After 20 minutes of using Cuil, I decided to switch back to Google. The search results are never what I’m looking for. I really like the layout, logo, and energy saving black but this engine is unusable in my opinion.
Think Cuil sucks? Prefer Google?
Why not register your annoyance as a counted vote against Cuil by visiting
http://www.cuil-sucks.com/
I can’t believe people aren’t commenting on the issue of how they’re using images – they’ve set themselves up for some serious slander and copyright infringement issues if they don’t make some drastic changes now.
They’re taking random images from sites and slapping them next to whatever search result they want, without referencing the original source nor linking to the site on which they originally appear.
It’s common for search engines to index images, but they are linked and credited to the source, not used as a vehicle to promote search listings at random. Typically, a copyright notice is also included to warn others about using the images without permission.
I found my original, copyrighted images (some of myself and my children) displayed and linked to other search listing results.
That would be like me going to any website and slapping their images all over my site – I’d be guilty of copyright infringement and it wouldn’t be tolerated.
I think they’re just begging for copyright infringement cases. I, for one, don’t want my images promoting other sites. Images are content and copyright-protected.
If a webmaster tried this, they’d be in hot water. I hope the same holds true for Cuil and they’re forced to clean up their act. I won’t tolerate this kind of abuse of my content and I’m sure others will feel the same.
I like the graphics of Cuil, but honestly it really sucks, i tried searching our copmany by typing key words, compnay details, I even typed the website it self http://www.otm.com.jo and it coudln’t find it !!!!
Nice – Great Work!
I agree you have to be a Fuil to use Cuil!
This was hilarious: “Yes, that winsome young woman is carefully inspecting a ConcurrentHashMap”
Depending on the search term used, I have found photos on my listing that don’t belong to me, and I have found my original, copyrighted photo on a competitors listing.
They have a right to take a snippet from my site. They do not have a right to use my copyrighted photo to promote a competitors site!
I’m waiting to see how long it takes for this stupid idea to get fixed. It’s a simple fix – if the photo ain’t from the site being listed, don’t use it!
Ed
I searched a common shopping term & the 2nd site listed tried to download a virus. Not cuil.
It would be a shame though, if this mess influenced the next possible worthy SE contender to not enter the fray.
A few days ago, searching for “cuil” itself returned completely useless results. Seems they’ve fixed it now, but it was an excellent, slightly ironic, example of how it fails.
Also, I’m sure I read somewhere that Google’s index has reached 1 trillion URLs (granted, they’re not all unique pages).
Poor search results = cuil.com …. period.
Demonstration:
My name is Mielus.
Compare http://www.cuil.com/search?q=Mielus
with
http://www.google.com/search?hl=en&q=Mielus
I cant believe how dumb cuil is.. first people would be confused..is it ciul or cuil?
First I tried my searching my business “Cafebpo”… I was speechless when I saw it threw an error
“No results were found for: cafebpo
If you’ve checked your spelling, you could try using fewer or different keywords to broaden your search.”
How much fewer words, idiots ??
Then with easy searches, the search results dont look like a normal search engine search results…
I will never go back to cuil or ciul or whatever carp. After hearing their VC story, I hate VCs even more !!