Hacker News Reader

  If i say "find me a good ticket for Chicago tonight". How 
  will it know that i'm talking about the rock band that's 
  playing tonight in Paris, France, since there's absolutely 
  not a chance that a human being asks for a plane ticket for 
  such a big trip just a few hours in advance ?

I don't even need an assistant system to figure out based on context which I'm talking about: All I want is one that can simply ask clarifying questions. "Did you mean Chicago the city, or Chicago the band?"

I had an amusing Siri interaction a few months ago where I asked "what language is spoken in Shanghai?" (I can never remember if it's Mandarin or Cantonese). Siri came back with a very well-reasoned, completely out-of-place answer of "Hindi": https://twitter.com/claymill/status/690386752683577344

  > out-of-place answer of "Hindi"

it's using wolframalpha - which interprets 'Shanghai' as a movie made in India. this is probably because it doesn't have a language field for cities but does for movies.

"If i say "find me a good ticket for Chicago tonight". How will it know that i'm talking about the rock band that's playing tonight in Paris, France, since there's absolutely not a chance that a human being asks for a plane ticket for such a big trip just a few hours in advance ?"

Funny, your "absolutely not a chance" interpretation was mine. Maybe there was a death in the family. Maybe you need to visit a friend short notice. Maybe I'm being a bit pedantic, but I was with you until that point. :)

> If i say "find me a good ticket for Chicago tonight". How will it know that i'm talking about the rock band that's playing tonight in Paris, France, since there's absolutely not a chance that a human being asks for a plane ticket for such a big trip just a few hours in advance ?

I think you discount how often the plane ticket to Chicago might happen. On total number of requests spread across the planet, I think the plane ticket might be the more common one. The point is, we don't care about the rest of the planet, at least not nearly as much as we do about our local surroundings. The way people answer that query is by using their continually updated knowledge about the state of the local system. If the band Chicago isn't playing around your current location soon, then the correct way to interpret that query would be that you needed a plane ticket (as anyone around you would probably think). This is why I think Google is really in a better position to answer these queries, because the knowledge graph allows the context to provide the nuance you are looking for.

>This is why I think Google is really in a better position to answer these queries, because the knowledge graph allows the context to provide the nuance you are looking for.

I agree completely. That's why the viv presentation left me a bit unsatisfied. I also had the exact same thought in the middle of their talk : "with google database of concepts, you could do so much more".

But even Google still needs to break the last barrier, and it's related to language itself and culture. Every translator and linguistic knows that a language conveys much more than clear information. It is a mental construct that evolved during thousands of years, and keeps evolving, is full of ambiguities than only culture, experience (and a bit of common sense) can solve.

The best example of this is to notice how bad automatic translators are. Guys at google tried to brute-force the problem, with a gigantic database of text, yet the result is absolutely miserable.

> The best example of this is to notice how bad automatic translators are. Guys at google tried to brute-force the problem, with a gigantic database of text, yet the result is absolutely miserable.

I suppose. I am fluent in two languages (also Spanish) so I'm in a position to be able to judge the quality of a translation, and I would say that pasting in blocks of text to translate them these days yields a result that's quite a bit better than miserable, thought indeed not flawless yet.

If you're at the point where being fluent in both languages is necessary to assess the quality of a translation, then it's already very high quality. Most poor translations are easily judged as such by anyone fluent in only the target language.

I don't think they are trying to answer your big question. On one hand, as mentioned in previous replies, even a human cannot just understand what you are talking about and would ask further questions, on the other hand, it is not about to try to answer all questions but to find some interesting, frequent cases that products like Viv can solve for you.

Maybe we should mostly think about AI products/tools as just another (weird) friend who is good at answering certain questions for us. At the end, we don't even expect any of our friends to be able to answer all of our questions. Indeed, we pick the right friend for right question.

"it sounds quite close to a sql / graphql query planner."

It probably is. Some representation of the query goes into that module, and a strategy for answering it comes out. That's probably going to look something like what comes out of an SQL query planner, but with more references to external data sources, and possibly queries followed by more queries.

You should be able to say "Viv, explain what you just did" and get back a natural language representation of that program. Then tell it what you meant.

This would be a useful feature on a Bloomberg terminal.

> This would be a useful feature on a Bloomberg terminal.

Why? What type of queries can you perform on those terminals that would be useful to analyze in this way?

A lot of Bloomberg "data" screens (this is also true in the APIs) are also interfaces to models. So like, if you pull up a bond model, you can override and it will reprice the asset, say, or back out some other parameter.

The Bloomberg interface is horrible and insane, and even relatively simple things like "ok well if I change the vol on this European equity option and you give me a new price...i still need to know which method you used to solve..."

There are plenty of other models in there that use much more complex pricing algos, and it would be useful to be like "Trinomial blah blah assume vol calculated as daily variance over last 30 days"

I am gonna copy paste a similar comment I made on a related thread [0]. That demo was very cool. But:

1. do we really want a centralised service for everything that has access to a lot of data within a walled garden?

2. Siri only works well with North American accents afaik (maybe all western accents?). Alexa's voice recognition is the best and I hope Viv does a similar job.

3. This is mostly a personal preference, but for online shopping I prefer using a lot of filters. This UI doesn't really help with that. Also, HN probably knows better but is the "computed plan" shown in the demo, different from an execution plan created by an RDBMS?

[0]: https://news.ycombinator.com/item?id=11660916

> maybe all western accents?

Apparently not[1], but I imagine it's gotten quite a bit better since then.

1: http://www.dailymail.co.uk/news/article-2053684/Scottish-iPh...

To be fair, if you asked me for a good ticket for Chicago tonight, I'd be looking up first-class airfare, and asking if you had a funeral to attend. It's possible to expect too much even from humans, let alone AI.

...it will know your location and it will know that many people got tickets for it already.

I think the key here is 1) evolution - as he said it will get better with time. Just like wikipedia was discarded by many intelligent people in its infancy, similarly now it may feel not so much revolutionary - but it will become something big. And 2) modularity/good design so it's easy to add "improvement" layers.

Some nodes/areas can be backed with deep AI, some don't need to. At the end you just wrap the whole thing in AI at the top to improve itself and we can slowly start calling Viv 21st century's god.

...or evil as some people will probably do. As granpa you'll tell your grandchildren how cool it was when you had to go to the market to pick flowers for your gf, now it's all automated ordering from robots growing flowers.

But this depends on the context. We can assume that the context of bsaul is being in Paris (context is not a requirement of intelligence) and now is where some intelligent processing appears: it is very unlikely for anyone to actually want to fly so quickly, thus checking if Chicago the band is playing in Paris (or close enough) would be a reasonable try before going to a flight planner website.

That’s why AI needs to be taught like a kid.

Body cams on kids, striped across each grade. It's the best way.

I was expecting theater tickets http://chicagothemusical.com/

>SQL query planner

Viv has to disambiguate the intent with user profile and context, normalize the schema across partner databases, rank partners which support the same verbs, build a partner system which lets them add verbs and domain-specific NL training… there's a lot of grunt to make it work.