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

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

this. 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 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

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

You can just regularly delete your search history.

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.

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.

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.

> 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.

Aren't you sexist by assuming only a male would be interested in Steve Klabnik and having a girlfriend? Nothing in tinco's comment indicated that tinco was male.

He is sharing his personal experience. Why are you generalizing it?

Hi, some persons seem a bit offended by my comment. Could you perhaps explain what part of my comment you interpret as sexist? I most certainly don't want to make you throw up.

I think the issue people are having is that you assume it should be clear to anyone that searching for "collision search strategies" would not also be searching for a bra, or like this female singer. This implies difficult physics and programming problems are not for women. There is no reason the same person could not be making all of those queries.

Ok to clarify, what I meant was that these sessions were happening at the same time, and on different devices and had vastly different topics.

Ever have the feeling that you're looking to get offended at things that aren't there?

That's not even it, it could be for a gift (or crossdressing?). It's more that it's unlikely that you're going to search for bras while searching for programming knowledge, unless you belong to a subset of people that really like to multitask or are very easily distracted (and this subset makes the problem harder).

I know someone who had a technology-driven bra startup, but I suppose that's an edge case.

I did that once, or rather, Stackoverflow's advertising algorithms thought I did. I don't remember the exact search phrase, but it did container the words "stackoverflow" and "string", and the advert I got stond out from the ones you usuele get there.

Why are you assuming that tinco is male?

This is actually quite a good point.

It's definitely not.

I don't know why you got downvoted, but you're right. The author seems to claim that Google should know someone searching for collision strategies shouldn't search for bra's or for Michelle Branch on Instagram. Or even suggest that its not possible for one person (male or female) to be interested in both topics.

The post was downvoted (not by me) for its sarcastic tone and for not taking into account that in the OP's real scenario, the queries were being performed by two different people. If Google assumes the same person can't search for two topics like that in one account, obviously they would be making a crude mistake, but Google has preferred data-driven, sociologically agnostic methods long enough that it's common knowledge on HN. For example, the same behavioral research they're doing with their captcha and behavioral-based authentication should help them lock on to different rates of typing, clicking, etc that two people on the same account might display.

> for not taking into account that in the OP's real scenario, the queries were being performed by two different people

gberger's comment was pointing out that the original comment did not take into account that these particular queries could have been performed by the same people.

That said, it could have been phrased more productively.

I definitely came away from Tinco's original comment with the icky feeling that a) Tinco's a little too thrilled with how super interesting and intellectual he is, and b) Tinco doesn't have much respect for his girlfriend's interests, and c) Tinco takes it for granted that Google should know that a single person couldn't possibly be interested in the union of those interests, probably because it should know that all the physics and programming and philosophy stuff is "boy stuff" and the rest is "girl stuff".

gberger seems to be reacting (in a slightly less than constructive way) to that same uncomfortable sense.

I would not dare presume to be more intelligent than my girlfriend. I just wanted to emphasize the difference of topics.

That said, I am very thrilled with my interestingness and intellectuality.

I thought tinco was saying that Google should know that two parallel threads of research going on at once from separate devices implied that at least two separate people were using the same account.

I read it as a literal example - tinco saw those exact examples.

I got the exact same vibe.

> could have been performed by the same people.

But they aren't in the example, and Google is understanding their specific situation wrongly/not in an optimal way. Maybe that's not possible to do, maybe the way they are doing it right now is the best overall, but it is not the best interpretation of the specific situation. Which is all I get from the original comment: "Here is something that they could understand better".

Pointing out that implementing this precisely would be difficult because you can't rely on interest subsets as an indicator would have been a fine response. Immediately accusing the poster of being sexist because it obviously is impossible to do is not, unless you have hard data to support that there is no way to tell the difference.

(I'd assume "disjunct" queries from different devices at the same time very often are different people, or at least worth treating as different sessions. But maybe people use multiple devices at the same time more often than I think?)

That's incorrect. The GP comment (tinco) is simply relaying a story that says that Google should know that he and his significant other have disjoint interests and query patterns (though they share devices and location). It's an anecdotal story. Someone else could have said that they like things in the join of the two interest sets and dislike something else. Tinco's story helps us learn more about the "entangled session" problem - a known area of research in Google (per the constructive response from nostradamons). Claims aren't made about how to go about doing that (people searching for X will never search for Y), just that Google should have a way of addressing Tinco's specific case.

Yes, because it was a facile potshot aimed at a better comment that discounted both the actual content and the nature of the problem; not even a daring one at that, this isn't the National Review.

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.