"Y Combinator Is Overrated" - Inside the brain of this 22-Year-Old who built Multiple Viral Products

0:00this is one of our more crazy startup ideas podcast episodes It's with AI schiffman the founder of friend.com he was all over the news for raising a few million dollars and spending most of it on buying a domain uh he's got some spicy takes you know if you if you view your work as art you have no competition and uh you have no fear of failure like move move yeah like like like move fast and break things I think is the thing I I hate the most I mean I think maybe it works for shitty software but like I think let's say in my situation I'm

0:31trying to build Hardware you know I only really get like one real first impression any business really does yeah you know no one no one great ever thought they they couldn't be great you know you really need to have instilled in yourself a deepr rooted self uh you know just you know you need to just believe you are the listen out G um in in a sense and I think will take you further than anything you'll ever hear from someone else he also gives away a free startup idea in the AI space it's highly technical uh so many of you might not understand it but for those of you

1:05who do he gives a Playbook on how to create this technical AI app uh that he thinks could make millions you might not agree with everything Obi says but uh it makes for a very interesting conversation and it probably will get your creative juices flowing start time baby we got AI SCH shiftman on the Pod founder of friend.com 22 years old Harvard Dropout he makes a lot of noise on Twitter and places like that so thanks for coming on man for sure thanks Greg um yeah it's it's cool to be on a podcast to just talk about uh ideas I guess um big idea guy here of course uh

1:52I I think I definitely have large tunnel vision I think what I usually think about maybe more is um like why people are usually failing at their startups or why a lot of people's ideas don't work or like yeah I talk about that yeah I I think that a lot of I mean there there's like a very famous Maxim right where like most people's startups die from suicide rather than competition and I you know I really believe I mean let's say let's say in my situation right like I've been building this AI pendant okay this AI wearable pendant for a while now I started this company back when it was

2:25called tab right in May of of May of last year in 2023 um and since then there's been a gazillion you know large companies and and random kids and idiots and all everyone all alike all trying to build their own versions of this and many more than half of the ones that I remember being started have all failed or you know not you know maybe I'm not going to be too harsh on them although you know they're trying to copy me still but you know they moved on to like other ideas but um you know if I was so worried about all those competitors which I never once was uh you know I

2:58think that would have ruined my startup a lot more maybe I would have eventually you know killed my own startup um I think people are far too worried about that and I think the the true reason or the true true way that you get over that is if you truly have confidence in yourself where you know that you are entirely acting off your own intuition um well I guess you know to to entirely act off your own intuition again you really do need to be confident in your abilities as an idea guy I guess um but uh you you know if you if you view your

3:31work as art you have no competition and uh you have no fear of failure and I think it just removes this anxiety that you have over it needing to be perfect or or anything like that well I mean at the same time like you know it's it's not perfect it maybe in other people's eyes I think it's it's perfect to your eyes which which might be a bit harder but um you know I think that's the way to go I I also think that uh why combinator is is evil and has ruined startups I think it's turned it into this absolute slop um and uh like move

4:01move yeah like like like move fast and break things I think is the thing I I hate the most I mean I think maybe it works for shitty software but like I think let's say in my situation I'm trying to build Hardware you know I only really get like one real first impression any business really does um and like you know do you think like the guy painting the Mona Lisa was like oh you know what okay it's you know it's good enough it was never no artist has ever said that their work is good enough and I I think you know there is a line

4:28you you you know you you shouldn't you know go too far away from but um I I think people should just ship when they when they ship and uh you know maybe if you do also want to kill your startup then kill it but uh I think like just truly freeing your mind away from competition like that um and truly just building what you truly want to build and not being impacted by like I don't know this like wey pocket advice book I see all these Founders like pinned to their uh yeah yeah I don't know I mean like I guess it's helpful for some people I think like you know there's

4:59that definitely a genre of startups these days where a lot of people are building SASS and it's it's very templated and I guess if you need to be you know have your handheld I mean go for it but um there there there was one more point I wanted to make okay I think there's a huge difference between entrepreneurship and Innovation and and I think this is uh something that a lot of people maybe get kind of in not unknowingly stuck in where like I think a lot of what I'm saying maybe applies a lot more to people trying to build something new and and innovate and uh

5:30maybe in that sense it's a lot easier to view your work as art because you are truly creating something new um I think for a lot of people that are maybe not inherently motivated by fulfillment in that sense and are really just trying to make a quick Buck which you know if you want to do that that's fine um I I think it's probably fine to follow advice like that what do you think of Founders who aren't trying to reinvent the wheel who who you know they're trying to create a SAS business that is 510 million bucks a year I just think like we're on the cusp of AGI are you really

6:04going to spend your time doing that like there's only so many things you'll ever work on in your entire life and I think what I hate the most about most people I meet around the world is everyone always is trying to prepare for something you know some people are trying to work at some startup for 10 years or whatever so they can gain startup experience or you know I mean it's not even just in the tech industry and in our little scene it's like just people out there that are a lot of people are maybe stuck in college or a lot of people just don't know what they want to do and I think

6:30one that boils down to the you know skill issue I would say again like it's your [ __ ] problem if you haven't figured out what you want to do by then um and uh quick break in the Pod to tell you a little bit about startup Empire so startup Empire is my private membership where it's a bunch of people like me like you who want to build out their startup ideas now they're looking for content to help accelerate that they're looking for potential co- Founders they're looking for uh tutorials from people like me to come in and tell them how do you do email marketing how do you

7:07build an audience how do you go viral on Twitter all these different things that's exactly what startup Empire is and it's for people who want to start a startup but are looking for ideas or it's for people who have a startup but just they're not seeing the traction uh that they need so you can check out the link to Startup empire.co in the description well I mean I think it's easier you know to create something new than it is to make something better um and I I think maybe it's scarier let's say to to do something unknown for sure but like okay like let's say let's say what I'm really

7:44trying to do which is to build like an embodied AI friend that is something new um rather than necessarily trying to build a a better chatbot although I know I did launch friend.com but I kind of ignore that for a second um right like if I was truly trying to compete with building a chatbot chatbot like it's kind of existed since the 60s with Eliza you know you're you're trying to build something better right you're trying to build a a better user interface that looks nicer and you know the chats are a little nicer maybe which is kind of like what I went through actually you know

8:15with building let's say friend.com right I'm trying to build something that is going to be compared against all these other web- based chat Bots like replica and character Ai and you know even let's say chbc r or or just all these all these chat Bots but you know if I'm trying to build um something entirely new that's like a embodied uh AI friend that you just it's it's entirely new and there's nothing to really compare it with except I don't know maybe like a dog or like a tamagachi or something like that um you know I don't really have to make it so so fancy I don't

8:49necessarily have to have the the best user interface or any of these things it's it's a bit easier to just um have this this novel thing that is I don't know like just yeah there's nothing to compare to and and it stands on its own and it's it it creates new categories it's it's it's easier to create a new category than to try and um you know win in an existing category because if you create your own category you immediately Crown yourself King and I don't know why anyone builds in in categories that already exists unless you're like a like a cuck you know you're truly cucking

9:21yourself if you're if you're building in a existing category there's already a king what what would you say to people who would say that everything is an existing category like what you're building is in an existing category so I mean I you can make different levels of Scopes sure I mean yeah I think there's an argument that yeah all startups are startups or some [ __ ] like that but like I I don't know what to tell you um I think there still is clear differential like categories for sure well maybe you know when you truly uh it needs to truly be like a new category

9:53look you can't just build a slightly better note taking app on you know I don't know it's still a category of productivity even in let's say the consumer social category what is Tik Tok a new in a new category or is it you know like how how would you see Tik Tok versus Instagram um you know that's a good point right like there's definitely situations where you can Dethrone a king of an existing category I think Tik Tok is the only consumer social product that came out after you know the OG ones in the in the earlier 2010s that um actually succeeded and I think truly kind of becoming King

10:31in a way like I Tik Tok is great um but I think that's very hard I guess like yeah I mean like you can go for it you could build a new car like let's say Tesla right like they entered they are okay in some ways slightly different category but overall it is still the same category of like cars um you know they they dethroned uh Ford and a lot of these other existing automobiles but again I feel like they still did something slightly different right like they still are entering a category of let's say automobiles but they still are doing it in a large enough of a

11:03different way and I think there is a large enough of a difference between like like ice cars and you know electric vehicles and there is um you know a not taking app then like a note taking app powered by AI or something like that's not really enough of a a change a categorical change right yeah I think what you're saying is kind of like try to try to build try to build an be a category of one so to speak so yeah it's easier is that yeah I don't know I truly think it's easier because again you have back to like what I was mentioning earlier where people are so afraid of

11:37competition um I think uh you know when you create your own category you have less competition in a sense because there's less people building in that space um and I would really encourage people to also zoom out a little bit with these categories right like let's say it you know in my opinion productivity as a category is over and boring and done and you know encumbrance like apple Google or you know even Beyond technology startups in a sense too it's it's done it's over like build something an entirely new category like to me the the new category that I'm really trying to to truly spearhead and grow is just like

12:14digital companionship or just kind of companionship as a category overall I don't think that I think when most people have thought about technology that's has always been very utilitarian and um you know not not focused on emotions and and love and intim and companionship and like these things um oh and and one point I I always like to mention is uh you know I think that the only real Moe is consumer mind share or just you know mind share as a concept of you know when when people think of a certain category or topic you know their mind immediately goes to just one project or one company right like for

12:50example if you think of chat versus Claude I use Claude you know I don't use chat anymore maybe you're you're the same I'm sure you've seen on Twitter and r seen almost everyone loves Claude right more than Chachi but if you look at like let's say Google search Trends chat is literally at like a 100 and Claude is literally at zero right like Claud is an anthropic is is insignificant nobody knows about them at all they win on mind share more than you know they win on necessarily a better technical product or a better team or financials or or anything like that mind share is the only thing that matters but

13:21it can be a very double-edged sword right like when you think about um let's say Apple TV versus Netflix when you think about Apple you think of them as a Computing or productivity company right you do not think of them as an entertainment company um but when you think of Netflix you think of them as a you know entertainment streaming company right and I think that's why Netflix will still always beat something like Apple TV or you know let's say in my situation I know that meta or Facebook whatever you want to call them has been venturing a lot into like AI Companions and digital relationships you know

13:52they've got little AI friends on messenger or they've got a character AI clone actually on Instagram on the web version of it um but when you think of meta you know I think you truly think of like human- to human relationships and I think it's a very unique situation you're in as a startup to create like a new POV um in my case which is I think like human to AI relationships like that is what you know my mind share concept is um and I think it's very very hard for existing encumbrance to like as I said it's a double-edged sword you know they might have a lot of Mind share in

14:24that in that category then right um but then to like really change that and build build from a new POV I I think is really you know it takes really strong marketing campaigns over a long period of time you know like let's say let's say I don't know chbt is is inherently known as utilitarian and productivity but you know I think Sam Maybe has a hard on for still trying to build like her or maybe her is still kind of an assistant but like let's say a true AI girlfriend type of thing I just think they would really struggle with that ultimately because like their brand is

14:54so solidified and being known as as productivity and I think this is this is the only real Advantage startups have I I always hear people say that your advantage of a startup is that like you know you can be focused or like you can move fast or like you know you're competing I guess maybe against just a small team at Google even though they're a giant company and like sure I guess these are kind of only skill issue reasons but like the only real thing that you have an advantage of is is a fresh slate in like people's minds right of like what your company's values are

15:25and what your what your category I guess in a sense really is I think that is is also only really applicable if you're trying to build something big and real but um you know again still I think the real uh the real Advantage you have right could you create you know a new category without raising venture capital or is this something that you need to raise money to go and do um H you probably could without raising venture capital I don't know maybe you're you're really rich already you can boost strap it or um you know I don't know maybe you've got some sketchy deals I I I

15:59don't know sure I'm not there's definitely definitely not an absolute yeah it's definitely not an absolute that you need to raise VC Capital VC capital is definitely useful you know to spend on domains and stuff like that for sure but um you know I think if you care about Innovation instead of Entrepreneurship in a sense and you really are trying to build something to last a long time I think you should care a lot about you know your Equity um and you know be careful about that to not raise too much Venture Capital but you know you you don't need to raise $100 million you can still raise like $5

16:33million or $250,000 right like you don't need to go extreme with it cool yeah I asked just because a lot of people listening here a lot of people I presume you live in San Francisco or the Bay Area just like a lot of people listening here like that world is so alien to them you know like they they yeah Venture cap capital and and stuff like that so a lot of people listening are are just Building Products um bootstrapping it themselves and so you know to just question yeah yeah I mean I think I think the topic of like raising VC capital for people that are

17:14not uh you know in so networked as well as I guess you are I don't know where you live La New York I'm in Miami okay Fancy Fancy Fancy um but yeah you know I do live in San Francisco and I am on on you know Tech Twitter quite a lot and uh you know I'm very networked of course but like ultimately I think to raise Venture Capital the more you talk about your product and and what you're working on I actually think the harder it really is um because I don't think any seed or lower investor gives a [ __ ] about what you're working on I think it's almost

17:46entirely um you know investing in in you and your ability to Yap um and therefore I think it's honestly quite easy to raise VC in a sense you just you truly just need to be good at yapping and I I also o think that the real way you raise is when it becomes about the deal and not about uh what you're actually working on in a sense um I don't know how to explain that particularly but just like everything VC is a social game um and these VCS are inherently just kind of trying to get a better you know they're competing against their their co-workers and their friends at other

18:18funds and like that's what they really care about they care about who's involved in in certain deals um you know when your when your fundrais is about the deal and not about your product I guess or your company that's I think when it becomes so easy um how to get to that point I don't know you just you either know how to do it or you don't it's not like anyone will really give you some specific advice like that um all I all I think that the only thing that people should really be optimizing for is personal confidence I think it it bleeds into everything from how good you

18:47are at yapping how good you are at recruiting how good you are at um following your own intuition which makes it easier to make you know major product decisions or just any decisions at all um and uh you know how also it it removes your fear of of competition I would say strongly I I truly think that like if I succeed in stuff one day like I really want to write a lot more and instill more of this underlying sense of personal confidence is what most Founders should be working towards rather than like YC advice because if you are confident enough in yourself and again you need to act like I think the

19:21thing is that you still need to actually have good ideas and you need to be smart but like if that's where you're at I I have no advice to give you that's that's your [ __ ] problem but assuming you meet you know the the bare you know bar minimum requirements um you should be maximizing to just believe in your yourself having good ideas essentially um and and if you have that you don't need to follow advice from y comp inator or whatever I'm saying to you as a startup or anything like that because you just you know you believe in yourself and I think you know not there

19:53is a difference between arrogance and confidence in a sense although I think it's only arrogance and hindsight is something I believe for sure I think a lot of people probably think I'm arrogant but I think that's only you know until I succeed I suppose then it's then it's VI as you know confidence um I would not be bothered by by those perceptions though if I was someone um but uh yeah how how does someone gain confidence you know is that is that something that you know you can learn or um I think your VC funding should be spent on trips to IB or something well not not not seriously you know but I

20:27think a lot of people should be focusing a lot more on their personal life outside of their work because it ultimately actually ends up um improving their their work life actually quite significantly I feel like this is also very a much more strong point I'm trying to hit home for I think probably more so younger Founders again I'm I'm 22 you know when I started working on this project I think I'd only recently turned 21 um this is the first time I've even you know lived in my own real place outside of home and like you know I'm basically still a y you know and you're all still weird if

21:03you're in Tech like I'm you know I I think you just i' I've I've grown so much in my own personal confidence and and my own you know sense of self and I think that's because I've spent so much time uh not necessarily working although you are kind of working maybe if you view it that way um to just like travel a little bit like go do things outside of your comfort zone a little bit I mean I think that that that phrasing is cringe I don't I don't really know what to tell people like earlier this year I for example I was in I was in Berlin at

21:33one point um and I went to like barine actually with one of my prototypes crazy you know crazy experiences but like I think these are the kind of things that have instilled maybe like just it's it's cool it's it's confidence it makes you grow as a person and as a result I've noticed that 100% bleed into how good I am maybe at fundraising or hiring or you know convincing people of ideas um and uh you know I think that's had more of an impact than any advice someone's given me or you know anything I've read online or you know just really anything else at all I I don't even really know

22:09why not many people talk about this because any founder that people look up to or it doesn't have to be founder you know artist let's say The Beatles or something like that um they uh that that is like their number one skill in a sense is that they're very confident in themselves and that's you know you think you you you cross a threshold of confidence where everything you do really does become an expression of who you are because it's so in tune with who you are that it truly is you know artwork um I think that is the the ultimate intrinsically valuable thing to to work on as well um and and what will

22:40truly make you feel confidently proud about yourself which I think is the the optimal emotion to truly feel um and uh yeah you know no one no one great ever thought they they couldn't be great you know you really need to have instilled in yourself a deepr rooted self uh you know just you need to just believe you are the listen out G um in in a sense and I think will take you further than anything you'll ever hear from someone else I saw this really good tweet by this guy Aaron Alto he tweeted visualization is the first step and yeah you know I was think I think that's true

23:17in a lot of ways like you know for startup ideas you know it once you know Step Zero is visualization or maybe step yeah maybe actually upon Prim reflection maybe steps you know step step one is find your startup idea step two is visualization yeah I think you know this concept of manifesting and stuff is is actually real in a sense right um you know and I think maybe if you relate this to like your again like your personal self um a lot of people want to visualize like the kind of person they want to be right like I know a lot of girls or something like that like take

23:53photos of the kind of women that they want to end up being right and you just kind of embody that over time um you do need to kind of turn yourself into a you know schizophrenic um but you know pulling you towards where you want to go um I will say I think people that are like trying to come up with startup ideas though it's like I don't really know how to approach saying this and or like saying anything to say but like I don't know I feel like you just got to live and like ideas just kind of come to you um because you know okay it's great to

24:27have like startup idea but like your idea will change like let's say what I'm working on right now it's it's friend right it started out as Tab and it was originally made because I was fundraising for a nonprofit and I wanted to keep track of the people I was meeting so I felt that if I wore like and always on microphone you know and use llms and trans and transcribe all the data you could like automatically build a person's schema right that is completely different than building an embodied AI friend but the underlying Tech is actually still the same um you know you will go down in idea Maze and

24:59you will make thousands and thousands of more ideas you'll make a billion ideas all day every day I think you just need to again I would say work on your own self-confidence and do things in the real real world and when the real ideas come to you you will feel confident enough to spring on them and you will feel confident enough to actually go down the entire idas and continue to believe in your own ideas and and truly see it to fruition um and you know you need to have confidence to allow yourself to actually work on something for you know a year or two or how long

25:26it takes to like truly bring something to Market you think Sam Alman had no confidence in himself while he toiled away at open AI for a billion years until they launched chat um you know I yeah I think I think confidence is the real basically skill issue it is the clear biggest divide between anyone that does anything at all outside you know I'm not even talking about startups I'm talking about again like just just anything worthwhile um it is the biggest blocker I can't think of anyone that wasn't confident that went on to do something that anyone cares about that could be that's actually a good tip so

25:59you know for people listening it's like if you're if you're feeling low confidence maybe ask yourself like what would Sam Alman do in this case if that's some you look up to right uh smoke some weed I don't know chill out a little bit that's what I would recommend there you go I'm serious I'm serious people are way too like I I mean I everyone's different I I honestly this advice I'm giving is is not for maybe it's not really relevant but um I just implore people to do things in the real world and and grow as a person outside of you know i' say focus on real world

26:31relationships too I think that is how you grow more than than anything in in the world um you know not just girlfriends friends too you know family things like that you grow so much from these things it is incredible um it's I think it's a great way to focus on basically your personal growth and maybe a slightly more structured way um that can lead to basically what I'm saying quick ad break let me tell you about a business I invested in it's called boring marketing.com so a few years ago I met this group of people that were some of the best SEO experts in the world they were behind

27:06getting some of the biggest companies found on Google and the secret sauce is they've got a set of technology and AI that could help you outrank your competition so for my own businesses I wanted that I didn't want to have to rely on Mark Zuckerberg I didn't want to depend on ads to drive customers to my businesses I wanted to rank high Google that's why I like SEO and that's why I use boring marketing.com and that's why I invested in it they're so confident in their approach that they offer a 30-day Sprint with 100% money back guarantee who does that nowadays so check it out highly recommend boring marketing.com

27:45there's some people who work 120 hours a week who don't leave their house and just work work work work um and I'm not of that belief I think that you come up with good ideas and of thought when when you work a bit more when you're more balanced do you agree got yeah you just got to kind of like putter around honestly and like just kind of walk around new environments especially and just kind of make sure that you're right like again I I think people think I work very hard uh maybe I give that impression off Twitter although I don't think I really do I'm

28:16mostly posting pictures of motorcycles but um like um I feel like I the how I work hard is in trying to make sure that I'm going to work hard for the right thing right like I think there was this famous I entirely I feel like I switched my mind on this because I I heard this this thing about I think Einstein back in the day where he's like if you gave me 20 hours to solve a problem I'd spend 19 hours defining it or something like that um and it's like kind of true right like it's so easy to go forwards in the right direction when you're sure that is the

28:50right direction I guess and like I think almost everyone that I know honestly works really hard on like the first like it's not even the first Direction it's like the first like cuz you can you can keep the same direction it's just like I think the first angle or the first like starting point of that direction like people just um people just immediately send it and I think like you do get to a point where you're very again in tune with your intuition and you're able to um really send it in the right direction at the uh you know in in the correct place but like I I just would implore

29:23people to uh like go to the club or something like do other things to like just um just keep thinking about your idea in different places um I think you'll uh realize how much of your past stuff has been you know just um I don't know how to describe it like just uh not not thought you know you don't want to think things through too too much right but um yeah one thing I've noticed is that like if I'm brewing an on an idea and I like when I step out of the house and I just like let it Brew in the back burner yeah I'm still like kind of working but

30:01I'm not really like I'm on a walk or I'm riding my bike or doing something those moments I find are just as key as the moments I'm in front of my computer exactly I think people need to get over this this anxiety of feeling that they're not working hard enough because they're not at their computer right like as you were just saying I uh I feel like you as a Founder are like always working right like I feel like I'm always working because I'm not you you don't really view your work as work right for the most part but um you know right now I am working in a sense and I am still

30:33technically thinking through my ideas um and I I'm still open to change you know my perspectives and my ideas no matter what I'm doing and again as most people the way you probably came up with your stupid startup idea in the first place is probably because you were like you know in the shower you were doing something else right and the idea came to you um but as I was saying earlier you know a startup is a billion ideas anyways you will go down a fat idea maze I think it's important for you to um you know just keep keep thinking through some of these these things in your

31:05mind yeah I guess what I wanted to to kind of bring to the table I guess kind of like a request for startups I see that YC does this pretty often is um I'm obviously trying to build a chat bot that you form a relationship with and I think this is like a category that's that's very popular right now you know regarding AI companionship um but I think like there's a broad use case of chat Bots that aren't just like you know AI girlfriends right I think might be what people are going in their minds immediately to but you know there's a lot of people trying to build therapist

31:34Bots assistance you know Mentor things just fun little games you know toys even kind of more what I'm doing which is this kind of like embodied tamagachi friend type thing regardless you know to to have a chat bot that you send more than a couple messages to you wanted to uh you know have a good memory system and uh there's a couple ways people are trying to build memory systems these days I think think at the end of the day it's really just rag which is still honestly kind of a fake way to build a memory system but it works for the time being and you know for the near future

32:06for sure um and what I really want to see is like memory as a service essentially I want to see more people build tools that make it easier for you to extract memories from conversations and uh you know have a very good eval system for your own kind of conversations that happen with your Bot um to make sure it's you know generating those memories and um you know a very quick low latency query system for these memories um you know I think people would probably be worried about maybe offloading uh such a such a crucial part of their application but I I honestly think it's enough of an issue that has

32:43just not been solv that um people people should really be focusing on this you know I I've I've taken a look now at nearly every way of doing this and every project out there and I honestly think the only the only people doing a semi- good job of this is I would say Dot from new computer um they've really nailed uh like the whole memory system because the trickiest part about this I would say is um updating old memories and and having everything be connected to each other because very often I might um you know well for starters you know you're obvious often changing your old memories

33:19like one day you might like a Ferrari the next day you might like a Porsche whatever these things change but um more importantly you want to be able to connect memories that are not semantic Ally related to each other cuz I might say I like I don't know I I like cars but somehow there's like a a memory that's not really semantically related to cars or Ferrari or something like that but it's still relevant to the conversation we're H having right now like maybe I don't know like my girlfriend uh got in this car accident ages ago and like somehow that's like relevant um basically it's a really

33:51complicated problem but uh you know I'm sure people can solve this and I I've taken a look online at some tools and I think the only real open source projects that exist for this is like uh mgpt and and mzero which are okay simple implementations but you know I would I think there's many people that would gladly pay for for a service like this so I'd like to discuss that with you Greg cool so I think a lot of you know a bunch of people listening don't even know what the rag memory system is so I'd love you to walk through I'd actually really love you to walk

34:25through um what that is um just like at a high level because a lot of people aren't super technical yeah and then how to think about like is this a good idea or not because there are competitors out there like how do you know how do you think about like oh my God this is something someone should do and and it would work what do you mean competitors out there like you you mentioned two competitors meaning well I don't know you know they're building like you know they're building personalities like they're building these niche uh I say Niche but like you know they're building chat Bots and like honestly if you're

35:02worried about competition then that's your problem you shouldn't be building a startup in the first place I don't know what to tell you you know if you if you view your work as art you have no competition you have no fear or failure um that is entirely your problem I'm not I'm not here to discuss your fears of competition but um rag stands for I believe a retrieval augmented generation I think um which just means that you know you give memory like just uh like facts or memories or whatever as part of like your system prompt or user prompt um and those memories obviously change the output right like if I ask a

35:39question to uh you know you have a system prompt that just says like I am a helpful assistant and then I ask a question you know what is my favorite car um obviously that bot is not going to have any memory of that and it's just going to say well I don't know you never told me that but uh if you have a system where when I say what is my favorite car it's able to take basically what I said and then I I believe the way it kind of works right now is you would basically embed that so you would kind of uh I don't know how to explain embeddings

36:10necessarily um you kind of just create like a like a semantic like relational map I guess of like that sentence that I said so you know you would basically just take like car right and find something that you know is the closest match to car right but you would you would you would take that um well I guess before you would do that you you would say to the assistant you know my favorite car is is a porsa okay a Porsche 9911 and it would just kind of there you know the the the models have a concept of automobiles and cars right and like a Porsche 911 is like kind of

36:46close to that concept of a car so if you imagine just like a 3D space right those are they're kind of just close to each other okay and then so later on um if I ask like what is my favorite car it'll you know see the word car and like look for something kind of similar and you know it's not going to be a perfect match right you know Porche 911 is not the word car but it's close enough maybe it's like a 0.8.9 match right something like that like a 90% match um so it's close enough so you would just choose like some of these closest memories so

37:17right now let's say we only have that one memory um we would take that memory and we might put that in let's say the I don't know let's say the user message that gets sent to this this this um this bot where you know the system prom is I'm a helpful assistant then your user message is what is my favorite car and then maybe you have underneath that you know you augment this message and you say like you know in Brackets like the user's favorite uh the user's favorite car is a portion of 911 or you maybe don't even need to you know augment the way that's written you can just say my

37:49user chat message that I sent ages ago like my favorite car is a Porsche 911 right and so when the system prompt sees you know your question and then you know the little context that you have there um it'll be able to say like oh you know your favorite car is a Porche 911 right so that's like kind of how it works um you would kind of store all of these memories in probably some kind of like vector database right um you don't really need to use a standalone tool you know a lot of people are probably using superbase as their database and you can just kind of you know use like PG vector

38:22and there they make it all pretty simple but um you know to set up a system like this that that can extract those memories and put those memories back into your chats uh alone is already you know pretty technical but then again building a true memory system like I was mentioning earlier your memory is a lot more adaptive right like you know you need to update existing memories what if now my favorite car is a you know a I don't know a Pagani something whatever right now now that needs to be updated and if you think about the way your your brain's working too right like you have

38:54like the importance of these memories matters a lot uh and that will degrade over time as well um you know recency matters a lot for some of these memories because if it's trying to maybe maybe you're trying to build a system that updates existing memories and maybe I said my favorite car was a Porsche 911 but that was five years ago or five months ago whatever and and only yesterday did I say that my favorite car was you know uh a I guess I don't know you know [ __ ] cars I I like motorcycles more I'd say like a Ducati 9 16 you know is now my favorite my favorite

39:30transportation thing right like you need to update that memory which means that you really need to have like a a backend system for doing this and and I think like the real way that you would build this is is with like a like a graph Network right which gets pretty complicated but that way you can fix this issue I mentioned earlier of connecting non-s semantically related things with each other like in a sense you know you probably would want to include that I like ducatti 916 even if I ask like what is my favorite car right but you know ducatti is is a motorcycle it's not a car they're not inherently

40:05connected um you know it still might be let's say how I mentioned earlier you know if I mentioned Porche 911 that is like you know a 0.8.9 similarity right and the Ducati is still generally closer to a car than if I mentioned you know a horse right this is my favorite color horse that's obviously going to be maybe like you know 01 let's say it's just so far away but a Ducati 916 is still maybe going to be like you know 4.3 let's say um but uh but yeah do that does that work for you Greg yeah I think uh okay so I'll be honest I I don't feel

40:39personally like I would be able to execute this particular idea and and win that's because I'm just not super technical but I can I'm Tech I'm techn I'm technical enough to hear what you're saying and be like that's a real problem someone is going to do really well to fix it and and the time is now you know oh for sure I mean I don't know how much longer you know rag is necessarily going to be an issue um but I know for sure that memory is is going to be something that all of these Bots need and you know I think it is again pretty pretty broad

41:12because I know a billion people you know there's a lot of people trying to build chat Bots and a lot of these people need memory systems and I have uh looked at all of these people's startups and I know that everyone is struggling with memory as well no one has truly cracked it even do I mentioned earlier from new computer they get pretty close but you know nothing's perfect um I think memory is essential for bringing users back into you know having higher retention with any of these bots so it is you know a top priority and I think any founder that is stuck with you know their memory

41:44system would uh would go to Great Lengths to make sure it works really well you know myself included this is a request for you know I need help myself totally it gets me thinking that you know if you want to build a startup maybe one and you're looking for startup ideas that are going to work maybe a good way is to just ask a particular type of founder I.E AI Hardware Founders or e-commerce Founders and be like what are the five biggest problems that you would pay money for to solve what do you think about that yeah I mean honestly this is the problem I would pay the most

42:17money to solve it is my real problem like you know I've got a team and we are working on it and I've been thinking about this for a while I think the reason why I'm bringing it up as maybe a very strong priority is I have a lot more context and memories to deal with than you know just a web based chatbot given that I have an always on microphone that is listening to everything you say and that's a lot that's just a lot of data um to parse through especially because think of how often you change your mind right in real life and if you're listening to those

42:49and trying to form memories off of that well man I mean you you need a really robust memory system um I think you know it's great to that all these great ideas are hampered by um you know these are kind of just like simple technical problems that I think will be solved but uh yeah and I guess it is a technical problem but I think it's more I mean I I don't know what to tell you I mean skill issue like every every real idea is going to be technical every real idea is going to be technical what do you mean by that I mean I I can't think of any startup

43:24ideas that would be inherently I mean like okay like no matter what you're working on even if it's like a shovel you know a really good shovel somebody is going to need to engineer it and like sure your role if you're listening to this might be okay you really know how to pitch this as a problem and you find some Engineers that you hire and you know your job is you know you raise funding and everything like that you know I'm not necessarily saying that you need to be the technical person working on it but um I mean yeah like I'm looking at a billion objects around me and I I don't

43:53think any of anything of this is is not inherently technical to have built in the first place but you don't think you don't think that uh business creation has like a spectrum of how technical things are so for example you know morning Brew for example is I think they make like a $100 million do a year or something like that and but it's a newsletter business they're not they're just built on top of you know existing infrastructure versus you know building this memory idea uh to me technical is not like technology like like like high technology necessarily you know like uh like programming okay like I'm looking

44:33around me at there's a whiteboard over there there's a air purifier there's a rug over here a water bottle an SD card a rock that's shaped like a pyramid um I don't know all these things are inherently technical in in many aspects and like even if you are business oriented right like you still there's still technical aspects to setting up a business and you know pitching in a sense like these are everything is I mean technical just I don't even know what the definition of that is just like like details I don't know how to describe it just no I love I love I love hearing because you know it's different

45:09than how I think you know um so um and I you know it's part of the Pod like I want to bring on diversity of thought people right so if is I just want to make sure I was understanding you correctly basically what you're saying is all businesses are technical therefore in order to be like you need me let me just like like all businesses are technical because business is technical is it not I think that some businesses are more technical than other businesses so if you're going to go and like if I were to go to CRA V which is like building like sure warehouses in in

45:48space or whatever I think that's way harder than building a newsletter for example I I do agree with you sure sure I think um yeah I don't think like startup success also is correlated with like how technical you know your thing is right like let's say warning Brew I guess you were mentioning is not you know inherently Technical and maybe the same way that a lot of people perceive that definition but um they you know might still succeed a lot more than someone that's building something so high-tech like someone that's trying to build Fusion reactors let's say or you know something really deep Tech and weird and crazy or some

46:24you know mad scientist trying to come up with some weird idea uh yeah you know tech technical does not necessarily correlate with with success and maybe I think that's a path some people might mistakenly go down you know they think it needs to be more complicated than it really needs to be but I isn't the whole point of engineering to to simplify complexity anyways totally I think that's a beautiful place to uh end sure yeah um any uh anything any last words for for people and and and where could people get to follow your thoughts and better I don't know just don't be boring and uh don't work

47:02on something stupid and you're again you're only going to work on so many things in your life you know you have a short bubble of Consciousness while we're alive right now or who knows maybe we'll extend that during our lifetimes but um you know in the short bubble of Consciousness just just don't waste it something you don't feel confidently proud about um and uh if you if you're if you are then I don't know I think that's just your problem and no one else is going to tell you anything otherwise uh in terms of where you can find me uh definitely friend.com for now or if you

47:32have some popup thingy I mean sure you can go to my Twitter I would highly recommend if you want to see me post videos about motorcycles for the most part but um yeah thank you thank you Greg this is this is yeah I I think this is will go down as probably we've never had an episode like this let's put that way we've never had an episode like this so uh the comment section will be buzzing and I think some people will be excited by what you say and then some people will be like I don't want that as us and yeah yeah I I I I guess I would implore

48:10people that are familiar with who I am and what I'm working on to see that this is why I am completely unaffected by what you have to say about what I have to say um for the most part you know I I've been in the media now for like four or five years and with a specifically friend I will say that it has significantly uptick the amount of people that just do not like who I am and do not like what I'm working on I get it's a very controversial industry but 100% the way I view a lot of people's feedback is it allows me to

48:36experience my own artwork from a different person's perspective and I I love that so you know I implore people to uh view it from that angle but thank you Greg thank you AI appreciate it see you see you [Music] time baby