Comment by tinco | Hacker News Reader

Comment by tinco | Hacker News Reader

Excellent, I like how it weaves my girlfriend looking for the perfect bra through my research on collision search strategies in physics engines.

Would Google in any way discern between those two sessions? Me sitting at the desk doing some hobby coding performing a query like "DBVTBroadPhase", her on the couch on my laptop looking for inspiration performing queries like "michelle branch instagram".

To a human it doesn't take much to jump to the conclusion that two totally different persons are using the same account at the same time.

But maybe that isn't even of interest to google. Me and my GF are basically one entity to them. We frequent HN and skinnycurvy.com, we like Michelle Branch and Steve Klabnik (;)), we do pilates at the gym while at the same time play underwaterhockey at the sports centre.

Any ads Google shows us might have a 50% chance of being shown to the right person, and that's probably good enough. Maybe they get lucky and I'll mention some womans brand I saw in an advert to my gf sometime.

Dunno what's made it into production or what has changed in the 2 years since I left Google, but when I was working on search algorithms this "entangled session" problem was very much a known issue and a subject of active research. You don't even need two people for it to become a problem: if you're searching for [camping sites near silicon valley] and [rust http libraries] and then try to compute a similarity metric that includes both of those lines of querying, you'll get wildly different results than if you separate them out and then compute similar sites.

> if you're searching for [camping sites near silicon valley] and [rust http libraries] and then try to compute a similarity metric that includes both of those lines of querying, you'll get wildly different results than if you separate them out and then compute similar sites.

Wow, never thought about how complex of a problem that can really be. To hijack your example: searching for [rust http library] and [clean rust from metal bookshelf] should be completely separate lines of querying but without understanding the full context, appear to have many false similarities (rust, library/bookshelf, 'clean' is a word associated with compiling software, and 'metal' can cause confusing with projects/articles on [bare metal programming with rust])

Yeah, disambiguation is a huge problem in search as well. I remember that when I joined (2009), I kept saying we need better disambiguation algorithms, because I was working on UI stuff and getting nonsensical results when I hooked up other teams' backends to the search result page. A bunch of teams were formed and I think the problem was largely solved by 2012 or so - there're some clever tricks you can pull when you have the amount of data and computing power that Google does.

Google drives me absolutely nuts because of it's 'intelligence', if you will. With dumber search engines it is trivial to ban words you would only expect to see on pages unrelated to your search phrase, using '-' or something similar. Similarly, if there is a word I know is associated with another topic, but is unlikely to appear in another topic, it's easy enough to force it to appear using '+'.

Google's methods for detecting clustering, or whatever they are using, are so 'clever' I feel like I'm unable to communicate what I want. I feel like I'm arguing with a particularly intelligent and malicious toddler sometimes.

Say I was to ask a toddler to bring me a beer, and they brought me a root beer. I'd be like, "no, bring me a beer, -root."

A normal child would bring me a normal beer, cause that's the only thing in the fridge that has beer in the title without root. The Google child would bring me some sassafras, because sassafras is a root beer, which is a beer, but it doesn't have root in the name.

Annoyed, I turn off safe search, and I say "Bring me a beer, -root -sassafras -sarsaparilla -ginger -cider."

The Google child comes back and says "I couldn't find what you were looking for." I get up off the couch, look in the fridge, and lo and behold it's completely full of beer.

You're looking for Verbatim Mode:

https://www.google.com/search?q=beer&tbs=li:1

this. Thank you!

Awesome! Is there a way I can make this the default?

You can't do it for all Google, but if you use Chrome, you can set it as the Omnibox default. Go to Menu -> Settings -> Search -> Manage Search Engines, then add a new row at the bottom that says "Google Verbatim", "verbatim", "https://www.google.com/search?tbs=li:1&q=%s", hit Done and click "Manage Search Engines" again, then find that row in the list above (alphabetical) and click "Make default". Now everything in the address bar uses verbatim search.

wow, you just fixed everything that i thought was wrong with google. thank you.

I've found that part of the solution is to give it more to work with, and in a 'dumber' way. Remember, Google search isn't really a query language any more, it's more of an NLP find-what-I-mean interface. So sometimes instead of giving it keywords and logical operations ('beer +fridge -root -sassafras'), you can get better results by just asking a question ('get one of my beers from the fridge').

Are there any that you are at liberty of talking about? I find machine learning especially applied to search and NLP a really interesting problem.

Probably not - when it comes to search algorithms it starts to get dangerously close to things Google considers very confidential.

Machine learning is definitely a big part of it, but you can also get surprisingly far with simple bag-of-words models when applied to enough data.

Would it be worth the effort to set up some kind of "mixer" service, where your requests will be routed through random other people's accounts? The goal is to destroy the information value of your search history: "Yeah, I searched for horse costumes, but so did everyone else in the pool!"

Probably would be easier just to use an anonymous account for every search, but is it easy to destroy all the patterns associated with the searches that would indicate it's the same person.

(The concept is similar to those proxy services out there that pay people to let them use their "good" IP address to e.g. scrape sites that will otherwise automatically block "obvious" server farms. Also Bitcoin mixing pools.)

I believe this is what https://addons.mozilla.org/en-US/firefox/addon/googlesharing... does.

Check out Seeks https://beniz.github.io/seeks/

You can just regularly delete your search history.

Check out Google plus settings, and others you can opt-out for everything. When I checked my activity with above link, my activity is absolutely nil. But I'm using that account for very long time. Opt-out every possible thing.

I think I'd have to trust google to respect that. :-P

I am surprised no one suggested https://search.disconnect.me

Chrome has user profiles you could use to separate things, but it would take conscious effort to switch between them each time.

Only works if there's a carrot. Netflix does this too, and we always use it because (1) it always asks you up front and (2) if we use the wrong user we'll destroy our recommendations.

And if I have to see another frame of Jake and the Neverland Pirates there is a very real risk of a self inflicted injury. Their multiple accounts thing is great.

Not sure what you mean, the benefits of separate browser profiles are huge and obvious - separate tracking for logins, sessions, etc. Before profiles came along my wife and I just used different browsers - otherwise we'd have spent all our time logging out of and back into facebook and twitter and so on. Profiles fixes that.

You can even make desktop shortcuts to launch Chrome with a given profile, so in practice it's like having two different apps. I guess you could launch one instance and swap users but we don't bother.

> Excellent, I like how it weaves my girlfriend looking for the perfect bra through my research on collision search strategies in physics engines.

Sounds like an Ignobel worthy paper in the making.

Sounds like someone doing research to implement jiggle physics in a game engine.

Dead or Alive bounces to mind.

You might have bigger problems than misplaced ads if you let other people use your accounts.

Salting the data. If they get past the blocker they can have some bad data.

Not all that uncommon to let your partner use your iPad or whatever.

Common sense isn't common.

Reply on news.ycombinator.com