Clones, commerce & campaigns
53:12 Share

Welcome to practical AI, the podcast that makes artificial intelligence practical, productive and access. Like this show, you love the changes on the interviews days in on fridays and awesome talk show or your weekend enjoyment. Find us by a searching for the change log whereever you get your broadcasts, thanks to our partners at fly out I O launch your AI apps in five minutes or less. Learn how at why I O.

Friends, i'm here with a friend of my mica grannis cofounder and CEO of work. O S, big fans of workers here, Michael, tell me about off kit. What is this as that work? Why to make IT work? Us has been building .

stuff in authenticating for a long time since the very beginning, but we really focus initially on just interprets of single on saml of an ocean. But a year to end into that, we heard from more people that they wanted all the off stuff covered. Two factor of password off with blocking passwords that have been reused.

They wanted off with other third party systems, and they wanted really work with us to handle all the business logic around time together, identities, provision in users and even more advanced things like robed to access control and permissions. So we started thinking about that more, how we could offer IT as an API. And then we realized we have this amazing experience with radix, with this, this API really that the components system for building front and experiences for developers, the radix is downloaded at tens of millions of times every month for doing exactly this.

So we glew those two things together, and we build off, get so off. Cat is the easiest way to add off to any APP, not just next J. S.

If you're building a rails APP or geno APP, or just straw up, express APP or something, IT comes with a hosted log in box so you can customize that. You can style IT. You can build your own log in experience to its extremely modulate.

You can just use the back in aps and a headless fashion. But out of the box, IT gives you everything you need to build the serve customers, and it's tied into the workers platform so you can really, really quickly add any interprets features you need. So we have a lot of companies to start using IT because they anticipate they are going to grow market and want to serve enterprise, and they don't want to have to rearchitects their off stack when they do that.

So it's kind of a way to like future proof, your OSS system for your future growth. And we have people that have done that, people that started off. And I like just kicking the tires and just doing their acts of antia traction to grow and they go close coin base or disney or united airlines or you like a major customer and instead of saying, oh no, sorry, we don't have any business, enterprise things and were going to rebuild everything, just go into the workplace, dash work and check .

a box and you've done aside from the fact that off kit is just awesome, the real awesome thing is that IT is free for up to one million users. Yes, one million monthly active users are included in these other gates, so use IT from day one. And when you need to scale to enterprise, you're already ready.

Too easy. Learn more at the cat dot com, or of course, a work O S T com. Big fans check IT out women users for free. wow. Workers dot com or off kit dot com.

Welcome to another fully connected episode of the practical AI podcast. In these episodes, Chris and I try to keep you fully connected with everything that's happening in the AI space and hopefully share some things that will help you level up your machine learning game. I'm Daniel White, nc. I'm CEO at prediction guard where we're deploying A A platform of for private and secure A I. And joined is always by my cohoes Christenson, who is a principle AI research engineer at lucky Martin, are you don't .

Chris doing very well? Daniel, i'm podcasting from outside today. It's exciting. It's a cool november night.

But since I just moved house and I don't have a place to sit, nothing but boxes here. We're talking about A I outside today. This is an outside A, I.

A, yeah, yeah. You live in a place where it's possible to be outside reasonably comfortable in november. That's right before thanksgiving. Yes, it's a bit colder.

Colder appear in the in the midwest were definitely getting to that midwestern in time when the the car heart jackets come out and and the bees and yeah it's a good time a year. Means means thanksgiving is upon us. That's right.

We get to food turkey coming up here. Burkey is too yeah, forthcoming. So exciting. There's Better ones than other ones. So this is an a podcast about to food turkey or to turkey. But there's some that are Better than others than well, maybe let people pop on their own minds if they are expLoring that territory.

We need some AI generated to for keys coming at us.

You know, gotta be some intersection. That's right. Maybe tofurky is using A I to generate ad copy this year, which reminds me, I don't know if you've been seeing all all the things in the news, Chris, about coca cola ads, A I generated ads. Um have you have you ve been seeing any of that? Have you seen the actual ads?

I have not seen the actual ads, but I have seen some of .

the news talking about IT. So yeah yeah. So for those that aren't aware, coca cola, you know every year coca cola kind of creates these iconic Christmas time ads with the coca cola truck and you know the polar bear and things like that.

And this year at least, I don't know if it's all the ads, but there is at least one ad. I I haven't been following the exact details, but there's at least one ad is fully AI generated or at least driven by AI generated video clipsed or images, that sort of thing. And i've seen IT on the streaming services on, you know, I forget which ones, whether it's primer, they sort of all have ads now because it's basically like cable at this point, but all of them have ads.

So i've seen the coca cola ad on the on the streaming services. And yeah, I think maybe those that haven't seen IT out there should go watch IT. I think it's interesting that there is certain elements of IT that give you that that A I generated vibe, right IT, where you can kindly tell, but I definitely evokes the the character of the sort of coca cola ads.

And lots of people don't like IT. Lots of people think it's interesting. Some people on linked down, i've seen that what A I generated video is good enough for coca cola Christmas ads. Then who's IT not good enough for at this point, which is maybe a maybe a hot take? I don't know any any thoughts, Chris.

I'm just kind of amazed that people are surprised by that these days. You know, it's like a you're gna see the stuff everywhere. And so okay, iconic thing I I got IT but yeah I mean I I would have been almost surprised if the .

hand yeah and um yeah if you just searched for coca cola ad, I think the it's the real real magic holiday which is also a bit ironic that they titled the real real magic when it's definitely not real but yeah you can watch IT. It's pretty interesting. I I think it's a whether not it's it's really, really good add material. It's I think a sign that for sure A I generated videos is is here with us for the future. So you had .

a few some months back the actors, you know going on strike. But I just think that it's one of those things we have a long way to go, uh, you know just not just in entertainment but in most industries is where it's going to you're going to see corporate videos that way I generated i've already seen that um yeah made to seen the coconut but I I you know i've seen corporations that are doing IT. It's the way that is .

now yeah certainly companies like synthesia and pain and these video generation companies for training videos for you know multiple languages, all all these sorts of things, there's there's a lot of use of those. I i've definitely seen that disruption. Speaking of disruption.

a boy.

we haven't talked about this yet on the show, Chris. And I don't think either of us have a desire nor maybe at least on my part, a any sort of profound opinion on this topic other than the fact of what that means for for A I. But I I saw an article in time about what Donald trumps win means for A I.

So if you you're listening to this podcast at a time sometime in the future when it's not election season, maybe you're looking back on this and you know what Donald trump s second term meant for A I but at this point, we don't necessarily know, although that we could you know make some glasses which we can talk about but yeah we we're about to go into the second trump administration ah so if you're listening to this at some other time that the time that we're talking about this and uh and yeah so interesting uh we've seen maybe just as a reminder, we've seen the by administration do some things as related to AI, including the executive order on A I, which we did talk about on the show that was a episode two forty four. So if you're wanting to know if we referred to that and you want to know which you know the details in the interesting pieces of that executive order, that's episode two forty four, which will link in the shower notes. But yeah interesting any any initial takes on as as a practitioner what this means for us.

I I can tell you what I hope that means and I hope you know during the first trip administration, he didn't know very much about IT. Uh, he brought in some corporate folks to you know put together some committees and they know that there was a little bit they came out of that a website and stuff like that but didn't impact us too much at the time. And so I think part of me hopes that IT maybe IT will be IT will be gentle um let him talk about rolling other things back but maybe he's not aware enough of A I to do IT but of course it's been another four years um and who knows where that's going. So a little bit a little bit nervous to see where his policies take us but I I hope is more .

less hands off yeah yeah so in the time article, this is A A quote from that article, which we can put in the in the show notes, says trump's own pronouncements on A, I have fluctuated between all and apprehension that sort of, you know, describing IT as a superpower, or very alarming.

right? Often in the .

same sense. Yeah, yeah, maybe so. But one of the things I think that has been kind of promised, maybe as a part of just undoing some of the things of the biden administration, which I think we can expect you know more generally, is, is a promise to repeal the executive order on AI among, you know, probably other things, and I think exciting the hindrance of innovation, you know, this kind of anti regulatory take on a lot of things.

So there is a promise to to repeal that. I'm not a enough of a lawyer slash politician flash political analysts to know what exactly that undoes because you know, the executive order, I think, kind of has its tennis les in a variety of things that IT touches that are maybe not immediately related to the executive order, like the nest A I risk rame works and in those sorts of things. So I don't know exactly how that works out. Maybe that's a point of confusion on on my part.

Yeah, my concern is there are some things that I think if you didn't just have a medical reaction to entire anything that biden did, that there are actually some things that the current administration and the incoming administration should be able to agree on. And one of those it's not a ye, just as an example is, is the chips act, which is of trying to bring semiconductor capabilities, you know bang online in the U S.

And if you are kind of if you're administration, it's anti china uh or you know in the china iwan concern, then you would think that that act, which trump has said he has, you would think that that's actually something that both sides of the eye could agree to. But he's also said he's gonna repeal the chip set as well. And I I fear that this um that the executive orders since IT is something he can repeal was just a stroke of open might suffer that and yet I think that he would be making a mistake regarding his own administration. I think that would create problems.

Yeah the article that were referring to even talks about this that um there is some statements about you. We're going to need more, more chips and more chip production, right? But at the same time, the as you mention, the trump campaign has attack the chips act.

I saw you know certain things, of course, are still, you know, in progress that would, I think, fit the amErica first chip production piece of that and coding. I just saw on the news that, that intel was awarded up to seven point nine, almost nine billion under the chips act to help build or expand chip plants in arizona, new mexico, ohio, an organ including one billion plus later in twenty twenty four. So some of this I know, especially the the ohio plant in all of that is I think in progress.

I don't know the exact details of that, but um but yet some of this is in motion. So IT is a bit confusing to me. I am sure that I CEO of large companies are are on the edges of they're seed and trying to get audiences with the right people and understand what what's going on. I'm assuming again, I don't know how all all of these things work under the hood, but i'm assuming up there's a lot of that shuffling going on the to get a read on the situation.

Yeah I would hope that if there is anyone out there are listening um that might be a part of the incoming trump administration h making amErica great again is exactly what the chips act h was intended. And Frankly, I think the AI executive order uh does the same. So I think. I'm hoping there's no need drink on those two things despite the car at that. Maybe maybe he'll let them continue.

yeah. What is your take on the potential perspectives on open source or or closed in the trumpet administration? Any any thoughts on that in terms of how may be influence one way or the other?

I don't really know at that point. I think IT comes down to whoever who I IT depends on who's in his, who's in the cabinet potentially and more probably more specifically, who's working on staff at the White house and what there takes on IT are and I I couldn't speak to that yeah.

i've seen a mix of takes on that. I think there's one perspective that while china has benefit greatly from open source A I right um not only have they been model builders and actually producing a lot of technology in the A I space, but they have also benefit a lot from you know meta and U S A A I technology.

So there's kind of one side of IT that would be well lets you know lock that down in in the same way that they might try to restrict exports of of other things or or that sort of thing. But i've also seen the other take on the fact that you know you're basically entire regulation and IT would be kind of not within the character to be restrictive in terms of the open source A I world. So I think it's a little bit unclear. I I am certainly one that kind of use the the future, even more importantly, in in security, privacy conscious industries, really driven by open self hosted models. I think that that's really the way that you ensure security, privacy, transparency.

Yeah, I think there's a lot of ambiguity at the moment because if you look at traditional conservatism, if you look at ronal reagan, you know because a lot of republicans really look back to that open trade is huge. But we're also having trump talking about tariff s. That's been the news of the week. And you know that's kind of the anthy's sis of that. And so it's kind of hard to to figure out where the balls gonna land on those.

Okay, friends, one thing .

i'm obsess with now is using notion ei. Yes, i'm a notion user. A power is I would say I use IT for myself. I use IT for change log and IT, just so effective to organize everything.

And with the addition of notion A I IT is a single toll, does all searches across notion other apps, generates dogs and my own style IT unless is PDF and images, and can share with me about anything. Now you may know notion as the perfect place to organiser tasks, to track your habits, to beautiful products and all the things you do. Context of your work is simply revolutionary.

And unlike specialist tools or legacy swiss, you bouncing between six different apps. Notion is seamless, ly integrated, infinitely flexible. And yes, IT is beautiful on the eyes. And yes, I am obsess with notion AI because I can pretty much ask IT anything is just there for me. It's superfast and is relevant to all of the stuff I have inside notion.

If you try notion today for free by going to notion that come flash practical AI, that's all our case letters notion 点 com flash practical A I。 Try the powerful, easy use notion A I today. And when you use our link, you supporting our show, which is awesome, again, notion that com slash practical ai.

One thing that was kind of brought up in in the myth of this talk of the administration and A I, is this sort of A I and china discussion where there's a thought, you know, A I is kind of thriving in china and maybe china is pulling ahead. And A I I know we've talked about this on on the show before. There is kind of this discussion of china in AI.

Every time policy decisions are are discussed, done on the show and kind of factors in and one of those things that I think is relevant is just the dominance of quen base models in recent times. So if people aren't aware, one of the things that I think is is interesting to follow recently is alibaba queen family of models um that spell Q W E N queen on the latest of these is the queen two point five model family. And generally these quin two point five models are are quite impressive.

They generally top the open L M leader boards in in various categories. You'll see them in the top spots. So obviously these are chinese models.

That is their models being built by a chinese company, alibaba. The CEO of hugging face quoted and in one article was reading of you know queen seventy two b as the king. And chinese models are dominating.

It's a pretty, pretty clear statement back and that was earlier in the summer. But I think we've seen continued um continued domination of these these models. Any interesting, interesting takes on that, Chris, in terms of how you seen me the model landscape shift from closed model provider to open to maybe more geographic ally diverse and certainly china being being within that.

I'm in an industry. I am in defensive an intelligence where obviously we're not going to be using chinese models. And so we have not been focusing on that. We of course, keep track of everything out there. But um that's not one word likely to use.

But i'm really curious in in kind of outside of the sector that I mean, I love to get some feedback from people on what they what they're up taking. I think there are a lot of industries where they are not going to Carry either way um on that and going to go for the best models on the leader board. But I haven't actually talked anyone who's done up take up at yourself.

Yeah and maybe this is an interesting little diversion here because I think some people don't understand the potential security risks as associated with with the sort of model. So we say it's A A model produced in china. Some people would be uncomfortable because of china's use of data or ways that they would use this technology.

But if we look at the the model itself, so you can go to hugging face and just search for queen models, so the queen models are open in the sense that you can go to hugging face. It's a repository of models. You can literally go to the queen model. You can download the weights of the model and load that model into infrastructure that you control. So so this are this model when you think of the model is composed of promoters and model code that runs that model.

And so if you go to the model on hugging face, you can download that now similar to like if you were to go to get hub and you look at all of the repos tories on get hub, some of those repositories, ies on get hub will have security considerations or licenses that won't allow you to use them or you know sources that you don't trust, right? It's a little bit interesting here because these models are kind of loaded into code that is maintained by hugging face, the transformers library or other serving frameworks, right? So if you're self hosting the model, meaning you're pulling the model down from hugging face the files and you're loading IT into code that can serve that model.

That model serving is under your control and you are downloading those files, meaning you can inspect them IT doesn't mean there is no security vulnerabilities associated with them, but ultimately be all of that is under your control. That is a different scenario than if you were to connect to an A P, I that is serving the queen model, which there are ones from alibaba and others that where this models actually hosted as a product of a chinese company, you know you're sending your data to that A P, I product, which is then you know processing your data and giving your response back from the model. So I just wanted to emphasize this kind of these two scenarios here.

So one, in one scenario, the security vulnerability is really related to the model files that you're now loaded. Is any security vulnerability in those model files, which there could be? Is there any third party code that used in when you load those model files, which there could be? And what serving framework are using to serve them, which could have security vulnerabilities?

In the other case, you're relying on someone else's infrastructure, which is under your control, which might be under alibaba control. So these are just different concerns. You want a way and um I thought that maybe good to highlight because some people may even want to experiment with the queen model like in a thing like alam studio or something like that. I'm not vouching for all the safety considerations might be in in your mind, but it's not like I don't think when you use queen in l am studio, there's some sort of phone home to alibaba going on necessarily in the in the underlying code that's running that .

I think in the U. S. Government circles. Just to clarify something, I think it's more policy than necessarily.

So I think you're going to have some agencies that are downloading all the models and reviewing and inspecting and stuff like that. But I think for typical usage, you're looking at more. But I think you are much more likely to see A U.

S. Agency or corporate that is uh, serving the U. S. Government going going to be focusing on on metal versus the, you know, alibaba. I think that's just a policy issue.

Yeah, yeah, for sure. I think you're you're right. I think i've just seen a lot of confusion around this.

It's like school clarification. Any time you use a quin model, it's stealing your data. But there there may be ways to use this in a way that is appropriate for your scenario. sure.

Likely like you say, if you are working and defense or something that's going to be a different consideration, then if you're hacking together a cool AI agent on your side project, you know for personal purposes or so, those are very, very far apart on on the spectrum. So yeah very, very interesting. no. Um also there's there's some a recent development.

So as of so we're late in november already, but this is I think about a week ago something like that can turbo one million was released a sort of new version of this which extends the context link of the quin two point five language models from one hundred and twenty eight k to one million tokens. So that's kind of give a context. Some of what sided is like a hundred fifty hours of transcripts or thirty thousand lines of code? Or are these sorts of things so lots of context can be put into these models, you know, which is a trend that has continued and I have my own opinions about, but that does seem to be a trend that continues.

You can't hang that out there and not go there now.

yeah. Well, I I just think if you think about the typical the most common enterprise cases that I run across in working with customers, most often these fit these scenarios of what i'd like to think of as something that could be done by a college level in turn, right? So you have some very clear instructions to do this sort of workflow and IT might be multi step IT might be a complicated workflow, but at all you can break IT down at a sequence.

It's um these instructions there. So anette ally, if you go to a college level in turn, and you say, go into the warehouse out back, there's, you know, rose and rose of documents, now do this task. Crime y, right? That's a much harder thing with a higher degree of potential failure.

Then if you go to the warehouse and you find generally the section that's release to a task and you say, hey, you know, look at these couple holders of of documents and and do do the task, you're much more likely to get a Better result. And I and I think these models, you know, anew tally behave similarly. And there are some evidence for this in terms of the the forgetting ning of what's in the middle of the context, which has been observed you know, in academic research. And i'm sure people in this podcast will be like, no, Daniel, that solved you know, whatever. It's just my own sort of experiencing and anecdotes in terms of what what has been found uh to be useful is just yeah a million tokens is a lot so possibly .

more than most people are going to need.

And I know people you know that have been on this podcast and are peers of mine that totally disagree with what I just said. So that's okay. We're all kind of figuring that out as we go along, I guess.

So quint two point five that intersex with some of our discussion around the china amErica debate. But there there is a variety of models that people might be interested in, in just taking a quickly look at that have popped up over the the last weeks. And I don't think we've it's been a wild and so we've done a hears a buffet of new models type of a brief disclosure.

And um there's a few interesting ones, so there's one that is from a deep seek, which previously released um a series of really good coding models. But they ve they've released deep seek r one light preview, which is kind of fitting in this like ChatGPT o one or OpenAI o one kind of world, which is this kind of pause and think about things sort of sort of world where it's trying to saw very complicated, you know, math benchMarks or or other things. And so you see actually this deep seek model, in many cases for certain benchMarks, may be even doing Better then o on preview in a number of benchmark. So I think this is further evidence that this this gap between the closed model providers at the frontier and open model providers is just closing so rapidly. It's, in my opinion, basically not distinguish anymore in a lot of things that people want to do, whether you want to to use a open model or close model.

So let me ask a couple of questions around that. Number one is, if we've seen so much in the news about kind of hitting the limit lately, you know open a eyes come out, talked about delays on on future models because they're kind of hitting practical limit. People have left. The organization is result of that. And just in general, we're seeing you that's been the conversation in industry over the last one or two. As we do that, are we do you think that this is kind of the place that we're going to continue to see models evolving into where instead of just getting bigger and you know larger context, windows, the whole thing know all that always bigger, always Better, that we're starting to see these kind of uh, you know these a preview or ones the o one preview styles, uh, where they are pausing and they are bringing whole new techniques in to tackle certain types of problems. Is that are we are maybe going down that path as well as others?

Yeah yeah. I think i'm from my perspective at least ah one thing that happening is the gains that are being made from more data and larger models have basically platov, which has been observed, which means that smaller models that people are doing a lot of work to create data for and and innovate in terms of their efficiency are catching up rapidly to the larger model.

So what would have been only possible by you know seventy b model or a four hundred b model even six months ago or or three months ago is being done by seven b models or smaller, right? So you've got this small model trend where these models are actually performing at levels much higher than than what was able to be seen before. And then you have kind of branching out to various um both specializations or domains and kind of unique prompting or or formatting skills.

So domains like uh document parsing or or vision and that sort of thing. Hugging face just recently released the small L V M, which is A A small model that does sort of vision related activities. There is the out TTS, which is a really efficient you know uh three hundred fifty and five hundred million parameter text to speech model.

Both of those I think represent this is this kind of specialization of of smaller models and doing really well specific things. And then I think you will see kind of an attempt to continue to develop new types of fine tuning and prompting methodologies for things like the deep thinking and four things like agent related workflows, which I think people are going to be diving into more. So IT, maybe more about the workflow, the prompting format, the prompting strategy as we move forward for just pure text models than bigger and Better models, bigger and Better data sense.

I'm here with a good friend of mine, David, to over at real big fan of real big fan of internal tools built with real. But David, not everybody knows how to use retour. What can you build with me all?

So was really good for building any sort of crud application where you care mostly about security, authenticate, authorization through the internal facing things. If you're looking at a build, let's say, like google maps, for example, probably should not use for that. You go like custom driver, scope, react, really complex application.

What if you can build a crop up with grip for that? And will we see especially is that back and engineers who have less experienced the front or less interest the front end really gravitate wards me to. Because for back and engineer, sometimes all you want to do is you want to get to type test a working, want us to go test to A P I for example. And spinning up a quick APP d ritual is so much fast, they trying to go learn, react, learn, reduced, want to state management a learn all these different um parts of the front and step and is kind of so complicated. And so I think that back and engineers are particular really gravitate towards return for building fast corps.

Okay, friends, the best way to build international software is by going to read com. You can seem as he connect databases with with elegant components and add your own code on top, you can ceiled monday in task by not learning react, not learning redux, and bring up the time you need to work on the things that matters most. Once again. Real 点 com star for free or booked demo real 到 com。

Well, Chris, um speaking of a couple things that I think there are pretty cool, maybe even practical, that we could share us as people are trying to level up things. One which is just fun, which is on my list of things to try this week, is is something that I found or or someone pointed me to, which is called pickle grand. And I haven't tried this yet.

I'd actually just found IT today, but it's not the pickle. If you're python programmer, pickle me in something very specific, which is a serialization format. But if you're not a python programmer, yeah, if you just go to get pickle dot A I this seems like what i've been waiting for for a good long time, which is, uh, just a pretty good catch phrase h join meetings with clone that's that's all I pretty much wanted to do for for quite a while. Um the idea is basically you would have a kind of professional looking video and you could be lying in your bed, you know, without any pants on and your headset on and your audio would be going through your clone into a very professional looking person that has joined a zoom color or whatever call. But you don't have to ever put any pants on or or you know that sort of thing or you're driving and but IT looks like you're in your office, right?

IT looks great to me. I'm i'm all in .

on this thing yeah so super interesting. I mean, um I don't know what this sort of thing along with other things like A I avataras and all of this means for kind of the relational elements of work what I was kind of thinking when I saw this was, well, can I go a step further and just like generally and struck a language model to generate the my responses and only just sit there listening to my clone, right?

I just want to sit there listening to my clone while my clone does the meeting for me, and then just interject or kind of interrupt my clone and take over my clones mind in the meeting when I need to correct something or or jump in and otherwise because most of the time I don't know about you, Chris, but most of my meanings are like, hey, we're gonna go around and introduce everyone so no problem, my clone can introduce me and then you go around and be like, you know, what's your update on this project? Paste in a document habit given update is really not a lot of things that I do in meetings. Maybe this is gonna get me fired or or reduce my value at work .

when you're your own boss, you don't know about that.

Yeah like what um there are important things occasionally but um yeah i'm kind of wondering when that happens.

I'm just thinking out there in corporate world, all the status meetings that people go to, where you're just bringing your status and you're basically and exactly what you said, you you have your status written down. You've kind of already retrained IT to the introduction of that. You can kind of lay there half of sleep in bed.

Let IT just handle your turn when that comes. The only thing you can get to worry about is if somebody start asking questions outside the context of what you can, of what you can train, if then someone takes a right turn, you ve got to be ready to leave in. But, you know, I could see how lots of my meetings being taken over by this capability. I would happily do that too well.

And I don't know, like I say what what does that? Because part of like, let's take a stand up, for example, an engineering teams stand up or something like that. Part of the idea behind such a thing, I think i'm not a scrum master, but part of the idea would be to you know also actually here you know with your ears, what other people are are kind of their update.

And maybe that influences either they blocked on something and you you can reply or or an influences. So i'm wondering what this does if IT creates more potential isolation in an ready remote work distributed environment. And part of me, so I have a friend, mark sears, shout out to mark if if you're listening.

He's working on a venture studio called spout AI. And one of the things that is there, one of their cc, is that they want to build technologies with A I that drive people relationship together as people. So the idea, just a given example, would be like, Chris, you and I maybe were friends, were both busy, were professionals.

And so there is an A I assistant that maybe looks at your calendar and looks at my calendar and looks at events going on in our town or things that fit both of our interest and then messages us both and say, hey, you know, thursday night you're both free and there's this event in your town, you know, you guys and that's a sort of thing that is cool, kind of drives people relationship together, gets them out of their house, right? I think this idea of sort of embodied A I that would drive people relationship together as is very appealing in our day and age and and something that's needed. But I also love the idea of joining meetings with my clone. So I don't know how to bring those together.

but I told you all all in but you know going to you're talking about kind of driving humans out to to have real connections and stuff. I just have this vision of a kind of taking over the, you know the dating world, you know and that's i'm a long way removed from that you I hope you have I didn't .

think about that curse, but bit now .

i'm just having this vision of like, you know the single guy and single woman, both in a bar, but they're not neither ones very comfortable. And they send their agents to connect like the agents. They send their agents to screen, that's right. The agent screen each other and decide whether or not it's a Green Green or Green red and figuring out and it's like I can just imagine my daughter is too Young to be dating, she's twelve but I could imagine ten years down the road, you know her having one of these agents, you know and you know finding her boyfriend by by letting the agents check each other out. So who knows what what's going .

yeah and I guess that in their little video on on their site, like I they have a picture of a woman holding her baby, right? And she's on the phone, you know, joining the meeting with a clone.

So I could definitely see various lifesaver elements of this where you know there could be a stigma with like you joining a media, you know your spouses and there like you you have to deal with your baby at the time you're working from home, right? And that may not be something that either you're comfortable or or that would be accepted, unfortunately, in in kind of certain scenarios. And so yeah, I definitely see A A elements of this, but also I wonder about the kind of isolation driving forces of of all this.

Here is a really good point there. And just for a moment, stepping back out of you know the AI driven meeting, a concept if we step back a few years to encode was hitting, and we are all kind of just making do having remote meetings, we became much more tolerant of one another in terms of, you know, how your business life intersects with your personal life. And you know, if the dog was barking in the background, people learn to be just fine with that. And if there was kids or baby, people learn that there is an element of this, uh, is we're talking about this particular thing about having that that clone out there of kind of going backwards on that trend and are spying a little bit less tolerant of one another um because you're once again projecting that perfect image uh, whether you're in the car, on the toy litter in the bed or whatever is that you happen to be doing that you do want to reveal. So so I this is one of those things I IT could be isolating to use IT in that way as well.

Yeah interesting. I think um IT will be interesting to see how people leverage these both ways. And like many things we've seen with this technology, their opportunities for sort of restorative, positive, redeemed tive kind of uses of this technology. And in there is ways that I can kind of drive us drive us into isolation or or create issues. But um yeah um along the front of kind of lifestyle related things happening with A I I i've seen a couple of posts recently related to kind of payments and commerce and shopping in N A I, the first of those being a blog post from stripe which talks about adding payments to l agented workflows.

And uh I guess there's Better tooling now to the stripe agent tool kit, which is uh, if you go to get hub strike flash agent tall kit, you can now kind of plug in stripe as a tool or as a thing that can be leveraged by AI agents, including those from lang chain cw AI versus A I SDK, which is definitely pretty call that kinds scenario like K A I, I need you to book a rental car for me next week, right? And obviously, that requires some sort of payment. I could also see IT on the other end being a business owner right now. I'd love to say, hey, create an invoice for this, a recurring invoice for this customer for these amount with this line items and and send IT to them with a message saying, but you know, whatever those those things are, there's definitely a room for maybe missing or or problematic things happening here, but certainly very, very interesting to see this side of things advance.

IT is and I think it's a great thing personally in the concept of an agent. I know it'll take people time to get to trust IT and get used to IT, but I know in our household, we at this point, we tend to buy our groceries and have them delivered and stuff because we're busy and doing stuff and and a lot of times, it's the same stuff as you bought last week.

But maybe with a few changes because you're planning a different type of meal some point during the weekend. Think if you can combine, you know the agent with the payment capability and have the ability to kind of just smooth your life in that way. I know our family would love that. My wife would absolutely SHE go nuts for IT if if that was available SHE like IT offloading that aging is at all.

There's another I don't know if they're using the strike API under the hood, but there's another entrant into this, which is perplexity now offers a sort of shopping assistant with the an actual experience behind IT kind of built in. So you have the the ability to put in like k, i'm doing this project and i'm. You know, wanting to do this and that what the items that I need and help me kind of shop for those that I think is kind of the the vibe.

And you know there is a search that happens obviously, and this plugged into various products and in this case, they have a merchant program, which definitely seems so I don't know whatever happened to kind of some of the monetization around like plugins and other things with ChatGPT, but this definitely seems like a way to kind of get your product, you know, having a having a wife that, uh, a business in the direct to consumer space and in sales project products direct to consumer. There is this of trying to figure out, well, how do I place my product or how does my product kind of filter up into search results when people are just searching on chat, P T, perplexity, whatever? And so this does seem to be one angle on that where you can increase chances of being a recommended product.

There's payment integrations, API, custom dashboard access or so. There's a sort of merchant program element of the perplexity AI powered shopping assistant as well. Pretty interesting.

very nice. I'm looking forward of I was just adopt now i'm ready for all of IT go. Yeah well, as people .

build out there, they're shopping assistance with the A P S. From stripe or others or or if you're building your own things here at the end of our show, we Normally try to point people to a couple of useful things. And i'll just mentioned a couple very seemingly useful things that I ran across in the in the past couple weeks.

One of those is called duckling. You can just search for dog D O C laying and will put IT in the showed tes as well. So this seems to be a really nice to all kid that a lot of people i've seen mentioned related to document parsing, which is a really hard thing generally and a hard thing to get right in a lot of AI workloads.

And there are some custom models that have been built around various complicated document parsing situations. So this kind of is a standardized way to pass P, D, F and powers, points and images and excel documents and other things and get them into a standardized format. The other one that I saw, which was was pretty cool, as called observers, am a big fan of dcc db r gela hugging face data sets, all all of that sort of tooling.

And this is plugged into all of that and allows you to kind of second all of the request that you're making to various A I A P, I providers or your own models and save those in something like dark D, B or or gal or something for the future of kind of searching through history of prompts, but also utilizing that either for just observation and transparently and logging and debugging, but also maybe for eventually um open source data sets around prompts or even fine tune ing data sets in your own context. So both of those pretty interesting new projects check them out. But yeah.

this has been fun, Chris. good. I learned a lot today. I ate. You bring some of the stuff.

Yeah, good to, good to chat. We'll talk. You soon. Take care.

All right, that is our show for this week. If you haven't checked out our change log news letter, had to change loud 点 com slash news。 There you'll find twenty nine reasons, yes, twenty nine reasons why you should subscribe. I'll tell you reason number 4， you actually .

start looking ward to one.

Twenty eight more reasons are weight for you at change while dot com slash news. Thanks again to our partners at flat out IO to break master cylinder for the beats and to you for listening. That is all for now, but we will talk you again next time.