In search of the perfect movie recommendation
38:27 Share

Support for the verge cast comes from strike. Strike is a payments in billion platform supporting millions of businesses around the world, including companies like uber, B, M W and door dash. Stripe has help countless startups and establish companies alike reached their growth, make progress on their emissions and reach more customers globally. The platform offers to sweet of specialized features and tools to fash track growth like stripe billing, which makes IT easy to handle subscription based charges, invoices and all reactions ring revenue management needs. You can learn how stripe helps companies of all sizes make progress at stripe dot com that striped out com to learn more, right, make progress.

Welcome to the verge guest, the flagship podcast of interest clusters. I'm a friend, David pears, and this is the third and final episode in our series all about A I in the real world, we talk a lot about A I right now, including obviously on the show all the time, but at somehow all feels really abstract and big and kind of jargoning technical most of the time. So we wanted to find some places where A I is actually showing up in our real lives.

So far, we've talked about using A I as a tool to give everyone perfect memory. And we've talked to with an artist who uses A I to make us think differently about privacy and surveilLance and life itself. Today, I want to talk about movies, and more specifically, why it's so hard to figure out what to watch.

This is a problem incredibly familiar to anyone who gets their entertainment through streaming. right? You sit down, you turn on the TV, and then you spend somewhere between two and two thousand minutes looking for something.

Watch, no matter where you look, it's just stuff all the way down. So I open the afflicts up. And the first thing that shows me is metro, metro and more, the legend of watermark cada, which I feel like, no thanks.

Probably not for me. No offence to water mcadd. I just done to know who then we get my continue watching list, some new suffer netflix top ten shows, because I watched girls fy ever into that binary T V shows.

Today's top picks for me, like eight, rose down. It's giving me personalize recommendations. Then we get some romantic favorites.

My list, corky T V shows, goofy, sit comes your next watch critically claim T, V shows. These are some like the same thing. What are we doing here? I don't get IT.

That's something else. okay? We got a whole and who you starts by taking a long time to load and then we get dressed. My tour no chance that for me um we get a bunch of live stuff and really care TV for me which dressed my tour again bunch a crime document is that my wife house shows short than movies for me.

Continue watching any nominees because I watch time your mother top shows, another recommendation for the same top show trending, newly added TV, full series comedies, newly added moves. These are like just things that who do hats? None of this really feels like it's actually directed towards me at all OK. Now we try max.

Max first shows me A C N N show and then hard knocks with your giants that I will watch and will be very into, uh, recommended for me is up top preciate them continue watching today's picks, which is actually game of thrones and justice league in cake man and a despite documentation, this feels like me then a bunch top tens live true crime designing home just had IT okay, this feels closer to being me. But it's still just kind of like here's a bunch of stuff that we have on max that's the vibe here like do you wanted watch this? Here's some things.

Like I said, it's all a lot of stuff, but IT doesn't feel like anything here is just telling me what to watch. And actually, this seems to me like the kind of thing A I ought to be able to do really well. It's low stakes in the sense that if the model doesn't recommend the objectively perfect thing or if he even makes up a movie because these systems tend to make things up a lot, that's not a huge deal, right?

I just want to be able to tell a chatbot what I want and get some recommendations. To be fair, there are actually lots of ways to do this already. You can do IT with ChatGPT. What's a good movie that kind of like mission impossible or the born identity, but isn't either one of those movies .

you might like sky for. It's a James bond film.

I've seen all the bond movies. What else in .

that case, you might enjoy the man for new plane, eli. It's a stylish spy film with plenty of action and a good sense of humor. Similar to mission impossible and the born identity.

there are also a bunch of plugins in ChatGPT, the custom GPT that are explicit designed for this, though there are mostly just kind of Better formatting on top of the same answers, right? I mean, movies GPT, which cause itself, I go to movie in clip dia, so just deal. I just watched crazy, stupid love and loved IT.

What's a similar movie I probably haven't seen? Says, if you enjoy crazy, stupid love, you might like the five year engagement. This romantic comedy drama directed by Nicholas dollars starts jin sil and and my blunt follow the ups and downs of a couples of prolonged ageing. Blending humor or heartfelt moments, the film explores relationship DNA ics in a way that's both touching and funny, similar to crazy, stupid love for the i'll take that you can also use other A I systems like google, german I, what are some classic ninety eighties action movies that I need to see?

The ninety eighties was a golden age for action movies, turning out some of the most iconic characters in credible lines in cinema history. Hero, a few classics you can't miss die hard one thousand nine hundred eighty eight. Bruce willis redefined the action hero with this game.

Can we don't need to hear that, but the register, die hard riders, la stark, terminator, predator, beverly hills cop. And he says, this is just a small sampling of the many great action movies from nineteen eighties. Still not bad.

I don't know. I'd like learned any new movie is from that, but it's a decent start. These models will happily give you movie recommendations, and you can ask for them in pretty natural language, which is core. So you don't have to just searched for a movie or like a genre. You can actually say, I want a romantic movie that under two hours that is funny and not sad and you get.

how about crazy, stupid love? It's a romantic comedy that's funny and heart warming without being said, I just watched .

that great recommendation. But can you give me a different one?

sure. How about ten things I hate about you? It's a funny and charming romantic comedy, and it's just under two hours long. It's a modern take on shakespeare, the taming of the shoe and has a lot of great moments. Not bad.

right? It's not exactly ground breaking. New title ideas there like crazy, stupid, love and ten things I hate about you, you'd find in one google.

But there are good recommendations, and there's something important in that interaction. I think that is actually a signal of Y. A.

I might be a big deal here. So for years i've been asking people about recommendations, and for years i've gotten roughly the same answers. Recommendations are hard to do, really well, really, really hard.

And the most effective way we ve found over time is to basically say, okay, you like this set of things, which we know because you have either raided them highly or watch them on under times or done something else that makes us confident that you like them. Maybe you gave me a five star of you. There are some other people out there who also like that same set of things.

Oh, and they also like this other thing that you haven't seen. So we bet that you will like that thing too. It's simple.

It's how recommendations worked forever. But IT does kind of work. But A I has the potential to approach the problem really differently.

So there are two components that generally A I seems to be like a good tool to.

right? That's Diana puppis cue a developer and entrepreneur who recently started an A I movie recommendations tool called movie vendors.

We are prety friends of Harry Better, right? And we said we were joking, saying, you know, the movie has to choose you. It's not only that you are choosing a movie, right? You know so we said, and that sounds like the only vendors from, you know, the one is choosing you as as a sort so we said, okay, magic plus that kind of concept, my movie wander sounds really good. This is how the name show up.

I have a high pot tern name. But back to the two components. The first thing AI does really well is just in just and organized data. So so, so much data, all the generals and actor names and everything that you d Normally associate with the movie, but also all kinds of other stuff.

every feedback that people is may be given an iona read IT, twitter, facebook, whatever social media. We give more information that we think right. Every click we are, we are doing its, its its information that goes somewhere, and it's somehow interacting with other information and producing some kind of behavior that could easily be incorporated into an artificial intelligence to learn from.

The second component is that A I can begin to structure that data for you and turn all those articles and reviews and tweets and edit posts and everything else into something kind of like a usable database of information.

So if i'm saying I want to see a movie that has a dog and it's not sad, please, because i'm very sensitive person and and all these things somehow that is interacting with the information that is already sort of flying an internet end, how those those generate a eyes are working. We are not exactly sure the recent Diana and .

others are excited about AI, for making sense of all this information about movies and shows is that otherwise IT doesn't really exist. And to explain what I mean, we have to talk a little bit about data and meta data. As i've talked to focus in this space over the years, i've learned that there are basically four useful kinds of information about a show or a movie.

The first is the medical ata, which is just information about the thing itself, its name, who's in IT, who directed IT the poster. That's the sort of stuff you can find on a search with I M. D B. The second thing is watch data, the single best signal someone can give you about how they felt about something is how they watch IT.

Did they watch IT all the way through? Did they turn that off IT away? Did they watch IT every night, twelve nights in a row? Did they get half way in? And then, bill, that's all really, really useful information.

But that information doesn't exist at any real scale, at least not for streaming services. And IT definitely doesn't exist publicly. Netflix knows what you do on netflix.

Who on who do? Max on max. P cock on p cock.

But they don't know about all the others and watch data, even those lists of most popular titles that you see from these services sometimes is, as a result, a very closely guarded secret. It's crucial data and no one wants to share IT. The third thing is just stuff to recommend.

This is sort of an underrated one, honestly, and not really an AI story at all. But the recommendations you get are only gonna be as good as the stuff there is to recommend, right? Even if you know exactly what I like, that only matters if you have that thing to offer me.

And most streaming services have a few thousand shows and a few thousand movies. And honestly, sometimes not even that. And in theory, even if someone did have the whole available library of TV and movies ever, it's not a very big library.

I M D B S. Library includes six hundred and eighty five thousand movies and two hundred and sixty five thousand TV shows, which is a lot it's more than you'll ever watch in your life. But IT is nothing compared to the amount of content being uploaded to tiktok and youtube and instagram every single day.

The fourth piece of information about movies and shows that matters. And maybe the hardest and maybe the most interesting for ai is what you might call traits deep information about the thing itself, not just who's in IT or whether it's a comedy or a thriller, but one or two or three levels deeper than that. Is that a sad movie or a happy movie? Does IT move faster? Does IT move slow?

Does IT take a while, take IT into? Or does IT capture you right away? Is the soundtrack awesome? Or does the soundtrack kind of suck?

Is that a good movie to watch while you're looking at your phone? Is that a good movie to fall a sleep too on the couch? Is IT a movie you should only see? And readers, this of really matters. And its information about the title that is hard to know unless you really understand the thing itself. I think the easiest way to understand what that might look like in practice is through music, which is actually gotten a lot of this stuff really right back in twenty twenty one, I interviewed ghost of solar strom, who is now the co president of spotify, about the company's recommendation system. He actually described the whole idea of IT .

kind of perfectly. If you actually have no time shifted on the man content, that you have the benefit actually being able to machine, listen to the content, transcribe IT and understand IT. Then the problem is actually quite similar to text recommendation.

If you think about IT, then you have a few things we want to make difference from music. In music, we have these, your phone and half billion players where people are set manually, organized the world, seventy million tracks into, like how they go together. There is nothing like that for podcasts, and not even on the competitive platform, right? So we kind of had to boot strapped somehow.

And so what we started with was the builder, what is called the knowledge graph, quite similar, and artist graphic. This artist has this discography of these albums with these songs, and, you know, belong to these showers. So we started building a knowledge graph, a traditional knowledge graft, quite early on before we had in the listening data to boot strapped.

And then we started adding listening data to that, so we could see that people to listen to this, also listen to that. So we started would actually pretty simple system of a sort of hard coded graph. And then after, well, now that we have lots of listings day, that we started inferring with more machine learning based leaks, both the code on court, traditional collaborated filter, people listen to this, also listen to that, which is kind of what the player is were about people, the players.

This is also players step. But we also started adding much more advanced techniques, like actually machine listening to the context and summarizing them so that we can do things like podcast topic search. And and they were actually just we're not just looking at the headline.

We're actually listening to the content or listening. We're reading the content is transcribed, summarizing IT. And then we put IT into one of these embedding spaces after, as a often called to understand how is similar to other things.

That's the magic right there. That combination is where everyone seems to agree the best stuff happens. And when you stop talks about machine listening, by the way, he's talking about technology that spotify has that can actually break a song into its component parts automatically.

So with that technology, spotify computers can recognize that the song is one hundred and ten beats per minute. IT has a driving guitar arline there is a violin, female leads, singer, anti vibes and lots of other things, tones and tones of different categories, and classifiers for what this song actually is. And that actual understanding of what something is at a content level is really important in getting recommendations right.

And that just hasn't existed in video before. IT hasn't really even been possible. But then just recently, something changed. We got a sick break. And then i'll tell you that I great.

Support for this show comes from the aclu. The acl u knows exactly what threats a second Donald trump term presents, and they are ready with the battle tested playback. The acu took a legal action against the first trumpet administration four hundred and thirty four times, and they will do IT again to protect immigrants rights, defend reproductive freedom, safeguard free speech and fight for all of our fundamental rates and freedoms. Join the aclu today to help stop the extreme project twenty twenty five agenda. Learn more at aclu dot org.

Welcome back. Let me tell you about an A I breakthrough. So in february of this year, google launched its newest A I model called gi one point five german I one point five was all the things that new AI models usually are faster, smarter, does well in benchMarks, all that could have.

But its big new feature was a new context window, which basically refers to the amount of information that the model can take in and consider at a time during a single query. So like one token is a few letters. German I one point five could do a million tokens.

That's like a book. You could just feed a book all at once. Or as in one demo the google showed it's a movie.

The company demo gami one five with a forty five minute buster kn movie called charlock junior. The movie came out to six hundred and ninety six thousand, four hundred and seventeen tokens. If you're curious and just listen to how the demo goes .

in google air studio, we uploaded the video and asked, find the moment when a piece of paper is removed from the person's pocket and tell me some key information on IT with the time code.

then the whole thing processes for a minute, fifty seven seconds, to be exact. And the answers.

the model gave us this response, explaining that the piece of paper is a pon ticket from goldman and company pon brokers with the date and cost. And that gave us this time code twelve or one. When we pull up that time code, we found IT was correct. The model had found the exact moment the piece of paper removed from the person's pocket and IT extract the text accurately.

I remember the first time I saw this demo and being totally blown away by IT. This is an A I model, processing an entire movie for the first time and identifying one thing inside of IT in under a minute. There was one other demo in there also.

Next, we gave you this drawing of a scene we are thinking of and asked, what is the time code when this happens?

The drawing is like a crude stick figure drawing of what I think is a water tower, big Brown thing on two legs. Person below. Getting sprayed by water is either a UFO abducting someone or a water tower. Anyway, here's how good .

the model return this time, code fifteen thirty four. We pulled that up and found that was the correct scene. Like all generative models, responses vary and won't always be perfect. But notice how we didn't have to explain what was happening in the drawing. Simple drawings like this are a good way to test if the model can find something based on just a few abstract details like I did here.

This is obviously just attack demo, and most things are not this easy in this perfect, but the possibilities with that idea are huge. Suddenly, we're heading towards the world in which you can upload a movie to an A I model, and that model can start to understand things about IT. Granted, identifying a water tower is easier than figuring out the mood and vib Epace o f m ovie, but this is still a big leap down that path.

IT is, by the way, a leap filled with copyright violations and complicated legal issues. But just for the sake of our episode today, i'm onna. Leave those to the side for right now, so much of what's coming in A I is going to be decided in court.

But until that happens, this is what we're going to get and this is what we come to. The biggest, maybe thorius question in the whole A I recommendations universe, what actually makes a good recommendation? And actually, no, there's a question even bigger.

Why do you like what you like? There's an example I was give for that one, which is the crown like the first couple seasons of that like was IT was a great I don't know why, but I love that I was. But then like I noticed on whatever stream service IT was on, like I started to recommend like british shows to me, which like, or british royalty was like, I have no interest in british royalty shows.

There was something intangible, I don't know. What about the first couples inside the crown that caught me? That's where it's tRicky.

That's David sAnderson. He's the CEO of a company called real good. Real good is one of those products that tells you where you can stream a given show or movie. But it's also becoming a really important data provider in the streaming industry.

Like I mentioned earlier, there just is no good universal source of data about T, V shows and movies, what they are, whose in them, who made them and where you can find them. I know that one is not and IT is, but it's true that data just doesn't exist. So real good has its own consumer product that you can use, but it's also the database behind a lot of the other streaming search providers out there.

But think about that example, the crown or any other show or movie you like, do you like IT because of the star? maybe. And maybe that means you'll watch anything with that person in IT. That is an easy recommendation problem.

But how do you account for someone liking breaking bad, but not Better call soul or being super in the selling sunset, but really only making the first season, if you like game of thrones, does that mean you'll like house of the dragon or any other show that has dragons? Or was that the palace intrigue that you like? Or just the naked people, or one of the actors, but not only the other actors.

Or did the thing with the starbucks cut make you like IT or something else entirely, like they say there is no accounting for taste. But Frankly, I hate that. And I want A I to fix IT for me.

So real good has been experimenting with A I A lot recently, mostly as a way to try and explain whether you might like something. It's less proactive recommendations and more a way of using. I'm interested in this.

Do you think i'm onna like IT in their APP, you go to a title and you tap on the icon and IT takes a couple of seconds based on what IT knows about you to analyze whether you're likely to, right? So in the real good APP. And one of the recommendations IT has for me is area which i've never heard of before, Vincent, a grief stricken father who son goes missing, find solace to his friendship with eric.

The monster lives on her Edwards bed. True, that's something um looks like beneath combat ches in this. Anyway, I hate the button that should I watch this and that says it's analyzing IT just for me and IT says with its low I M D B audience score of six point nine out of ten and real good score of seventy and nine out of one hundred, eric may not be the best fit for you.

However, this shows crime and drama genre is a line with your interests in mystery and drama that shows suspensory story line about a fathers search for his missing son could keep you engaged but the monster under the bed element might not be you to you're liking. And then if I hit about and this has suggests similar IT just shows me a bunch of other things that I may may not like, including the bear and presumed innocent and Sunny and house of the dragon all would very much do like. So maybe I need to watch, eric, when you think about the four parts of recommendations, meta data, watch data stuff to watch and traits real good is a really interesting one.

IT has lots of meta data that's the database has been building for years. IT has very little watch data because netflix and the others don't share that real good in every other platform like IT just watching. Likewise, all these other recommendation systems are desperate for you to tell them which shows you like in which ones you've seen so that they can try and back into some of that watch data. But it'll just never have a like network has IT, on the flip side, real good has way more stuff to watch and more things to offer you because its library includes lots of streaming services. And when IT comes to traits actually understanding the content itself or that complicated, here's public alesia who runs engineering and data .

for real good. It's the same thing, is looking at a or attack, right? Is a complete a different problems, a way more holistic? Be looking at OK, what are the architect for something something and also like that, like made by actual people like and now is the movies and shoulder. They're like looking at the architect es and like the psychology of them. And that's really maybe the reason why we'd like movies would like the architect es of the character that, I mean, I would say aliens are probably the best equipped, are looking at problems of that will, because you ouldn't need to look at such a breath of tech knowledge at the same time to be able to, like, do that analysis, like humans do. But I would say that we're pretty far away from getting to that level of analysis.

even in the best, most powerful scenario, publish his skeptical that we're going to be able to teach LLM to completely, deeply understand movies and shows, and also understand why people like them.

I know the people that do like l EMS are the way human thing. I don't think that case, let's say this. But the soon then per second, we're still not like elements don't don't perceive the world in any way, shape of from clothes with humans. Do people were giving them that and such a different way. And also, the data that we give them is so limited and like so much context, even if you give them a thousand, they're still individual thousand years of like just imagine that like think of the way you watch movies and shows, right? It's such an emotional understand really are like going to feeling because you're looking at also depends on who you are watching the movie with and always, caterina, that the allow them is not like it's not that that needs to be smarter, like lives in a box, right, ever of us who live in the actual world, right? So there's that part of the problem as that makes me a lot harder for grow to get to the point.

Polo also said he wonders how deep is actually useful to go down that rabbit hall. Like if a model knows that you like a movie, and there happens to be a bird in the shot four minutes and six seconds into the movie, is that why you like the movie? No, obviously it's not why you like the movie. That level of detail is basically totally irrelevant for our purposes here that is such a solution in search of a problem. But if level one of understanding is just title and genera and cast, there's maybe a level two that may be just as useful right now here.

right? This is like the one we use. But the one we're looking at, and I think is the second level is the mood of the people content. so.

If this is like in what mood the person is when they went to watch, this is a problem that would be the second dimension and the one they were most actively looking at right now because it's I mean somewhat solvable, right? Like you can go down the rabid hole of like the architect es of each character. But a quick to so I will take that next time. So you go drama person, we are watching them.

Notice that that both about the mood of the content itself and your mood when you watch IT, I hadn't really thought about IT until people mentioned IT. But so much of the equation here, and really the reason recommendations are so hard in general, is that whenever I sit down on the culture to walk something, my mood changes everything. Yes, I like spy movies, but I don't always want a spy movie.

And yes, I like historical documentary and silly rm comes, but god help you if you try to get me to watch a world war two documentation on like a tuesday night when I just want to follow us watching a food show, you know, I mean, I feel like it's possible that recommendations will never be perfect and that they'll never know the exact right thing every time, because I don't want the same thing every time I am human and the computer isn't. That might always be a problem. So where does all that leave me in my quest to just find something great to watch? I get into that great, great.

Support for the show comes from the crucible moments, a podcast from scope capital. We've all had turning points in our lives where the decisions we make end up having lasting consequences. No one knows this Better than the founders of some of today's most influential, incredible moments.

Let's listeners in on the maker break events that defined major companies like dropbox, youtube, rob hood and more told by the founders themselves. Tune in to a season two of crucial moments. Today, you can listen at crucial moments, stop com, or where every you listen to podcasts.

Okay, back, let's go back to movie vendors that A I movie recommendation service we are talking about. Just for a quick second, I asked ana. Pop is cue how people are using the service so far? And he said, there are basically two things people are doing.

One is, maybe you have already a movie in your mind, something that some movie that you already seen. This happens to me very often, and I know a lot of people like to. We watch movies that they've seen maybe years ago, and they even do very much, but they don't remember the name.

They do remember certain elements of the movie like they, he said, right, to help new york get out like, you know, the main character and stuff like that, right? So they put that in, find, find that that movie to me. So they're looking .

for one specific movie, but they don't know what that is exactly.

They don't remember exactly the name is that. So that would be to find me option and then there is a recommend er is like I don't know exactly what i'm looking for. There's no specific movie that I need, I want to see, but I would like to have certain elements in IT.

You can be as deep as you want, right? You can give the Better you formulate your request, the more specific is going to be that request, the Better is going to be the outcome. So you don't have to fear that if i'm giving too many details, i'm not going to find anything um because eventually you are going to be more accurate if that exists.

Of course. I mean, you can search for some references myself. I love because they have a small kid, and I like a cars movie. So I was thinking, I like cars. Story is like, pretty good, but I don't like the fact that the characters are cars.

Is is there any any movie that has that kind of story, but without cars, like good people and and actually the outcome from from movie vendors, pretty good you know I was like, oh yeah ah yeah sure I want to see all those movies they were explaining with the that's true IT is indeed. So that's a very deep type of question that I want this story, but not with cars, with people. And I was surprised like that level of understanding of the artificial intelligence, to the point where, I don't know, I did some comparisons in between plots and said, o, they are common elements between these two movies.

That last thing is pretty impressive, actually, and very telling. If you go to google right now and you just say, what are some movies like cars? But with people, you're either gna get nothing useful or like a link to the movie cars.

IT will probably be the movie cars. But the idea of A I is that IT can calm through all the reviews, all the synapse size, all the tweet, and say, oh, this movie is talked about ally to the way that people talk about cars. But IT doesn't seem to have any cars in IT.

Maybe that'll work. That's the kind of thing that no system other than A I can do really well and do at scale. In the first case that I mentioned, A I models are already actually pretty great, Frankly, for the same reason because they've injust sted all these recaps, reviews and twists and more.

They can do a good job of guessing what you're looking for just by synthesizing information from all over the web. So when you're like, what's the gym Carry movie with the boat in the TV show? IT gets to the truman show really fast.

That's not recommendations so much, but IT is pretty handy. Personally, i've been using these A I tools for more than a year to try and find stuff to watch. And I found a few tricks that really work.

The first is the show me stuff like option. I add three movies I like and tell the model to find other ones, like IT, that works great, which actually makes sense. These models have injured ted.

All those lists of best spy movies or whatever, can easily compare the summaries that you find on I M D B. So matching things to like things is actually pretty easy. But the problem is, it'll usually spit back really obvious examples.

If I like back to the future, everything, everywhere, all at once. And so I married an x murder. What other movies do you think I might like?

You might enjoy billion heads, extent, adventure, hot tub time machine and Scott pilgrim, sus, the world.

So in that case, what i'll do is ad, but only recommend lesser known titles, or i'll ask only for underwater ones. And that usually reads out some of the most oppoa centers. If I like oceans eleven, the gentleman and heat, what are some underrated movies? Did you think I might like?

You might enjoy layer cake inside man in the town. These films have strong, higher.

I've seen all those. Give me more underrated examples.

sure. How about a simple plan, the bank job in the way of the gun? These movies have gripping stories and clever twists that should appeal to you.

Does a good thank you. The other thing I do now is try and ask just for the vibes that I am looking for. Like, here's one of my go to prompts these days. Can you recommend a good ROM calm that ideally under ninety minutes and doesn't require much brain power?

absolutely. Here's a perfect wrong com for you. Win a date with ted hamilton, two thousand four IT clocks in at a breezy eighty four minutes and is a light hearted watch. IT follows rosey kate bosworth, a small town video store clerk who enters the contest to win a date with the megastar tad hamilton. Josh to mail.

is IT any good?

Win a date with tad hamilton is a classic ROM com that's more about charm than plot. IT has predictable elements, but is still enjoyable for its light hearted humor and performances by kate bosworth and to for Grace .

IT kind of works. I don't know if these are like the platte onic ideal of perfect recommendations, and a lot of these have been terrible movies, but I had good luck with this so far. And as I said earlier, I like this use of A I because it's so low stakes.

If IT recommends a movie i've seen, I just tell that i've seen IT ask for another one, and actually adding that data to my search often gets Better results. If IT recommends a movie that doesn't exist, which, to be fair, has only ever happened to me once or twice in the last year or so, that becomes obvious very quickly. And I just move on.

I found a lot of good stuff to watch this way, and it's taken a lot of the aim was browsing out of my evenings, and I really appreciated just for that alone. What IT doesn't do well is match to the just watches and real goods. And this like, what service can I do IT on piece of things.

I have to get a recommendation and then go to another thing to find where I can actually watch IT. But those are easy problems to solve. And things like movie vendors are actually starting to put those two pieces together.

But after like a lots of people about this, do you know my number one best recommendations, recommendation, it's to do as much of your watching as possible on as few services as possible. Because the thing I heard from every single person that I talk to you is that the best predict of what are going to watch next is what you've watched before. If you want great recommendations, you need a watch history.

This is why youtube and tiktok have such Better recommendations, because they know what you've washed. You watch a lot. You watch IT very quickly. And these systems are able to just build this internal fly whil of what you do and don't like in a way that is much harder when you're sprinkling viewing across ten different streaming services.

If you have the energy diligence, which I Frankly don't, maintaining your profile on something like real good or just watched our letter box where you can keep track of everything you've watched everywhere, is also an excEllent path towards good recommendations that still serves itself. The more data you put in, especially with the strong signals of high reviews and saying you love something and all that, that matters a lot. I think eventually we might get A I that understands us as people and understands movies and shows in a deep and rich way and does, in fact, recommend the perfect thing, or at least the perfect handful of things every time we turn on the TV.

But I get the sense that that's still a ways off the the german I one point five demo is a demo that's not how we're going to start querying movies anytime soon. I don't think for now, if you want netflix or p cock or whoever to find you something great, the best thing you can do on those services is watched, if you like, all the way through over and over and over and over again. IT sounds pretty low tech, but I gotto say it's not the worst one work in the world.

alright? That is if for the verdict today, and that is IT for our AI mini series. Thanks to everyone who is on the show. And thank you as always for listening.

As always, if you thoughts, questions, feelings or movies that you want me to watch, because that is still the best recommendation system out there, you can always email us at verge cast at the verge 点 com， or called hotline. It's six verge one one we truly, truly laugh hearing from you. This shows produced by the marino, liam James and will poor.

And this episode was edited by ander atoms. The verge cast is a verge production in part of the box media podcast network will be back on tuesday and friday this week with our regularly scheduled programing. I'm actually out for the next two weeks, but we have some really fun stuff teed up for you.

And also, there is just a lot of news going on. So people locked. I'll see them rock roll.

Support for this episode comes from A W S. A W S, generate A, A, I gives you the tools to power your business forward with the security and speed of the world's most experienced cloud.