Venture Step

Keywords

Meta, CoTracker 3, MovieGen, robotics, open source, technology, entrepreneurship, AI, innovation, podcast

Summary

In this episode of Vichy Step Podcasts, host Dalton Anderson discusses the latest innovations from Meta, including the CoTracker 3, a groundbreaking computer vision model, and MovieGen, a text-to-video generation tool. He also explores Meta's advancements in robotics and the significance of open-source technology in shaping the future. Despite battling COVID, Dalton shares insights on the potential applications of these technologies in various fields, emphasizing the importance of innovation and collaboration in the tech industry.

Takeaways

Meta has recently launched several innovative technologies.
CoTracker 3 offers advanced tracking capabilities that outperform traditional methods.
MovieGen allows users to create videos from text descriptions.
Open-source technology is becoming increasingly important in the tech landscape.
Meta's advancements in robotics could revolutionize various industries.
The future of technology is promising, with many exciting developments on the horizon.
Collaboration and community feedback are essential for technological progress.
Sparsh, meaning touch, highlights the focus on sensory technology in robotics.
The integration of AI and robotics will enhance user experiences in VR and beyond.
Dalton emphasizes a positive outlook on the future of technology and innovation.

Sound Bites

"Meta has been on fire lately."
"I'm in a state of delirium."
"CoTracker 3 is a game changer."

Chapters

00:00 Introduction to Meta's Innovations
02:56 Deep Dive into CoTracker 3
11:55 Exploring MovieGen: The Future of Video Creation
20:29 Meta Spirit LM: A New Assistant in AI
23:52 Advancements in Robotics and Touch Technology
31:04 The Open Source Revolution and Future Outlook

Creators & Guests

Host
Dalton Anderson
I like to explore and build stuff.

What is Venture Step?

Venture Step Podcast: Dive into the boundless journey of entrepreneurship and the richness of life with "Venture Step Podcast," where we unravel the essence of creating, innovating, and living freely. This show is your gateway to exploring the multifaceted world of entrepreneurship, not just as a career path but as a lifestyle that embraces life's full spectrum of experiences. Each episode of "Venture Step Podcast" invites you to explore new horizons, challenge conventional wisdom, and discover the unlimited potential within and around you.

Dalton Anderson (00:01.4)
Welcome to Vichy Step Podcasts where we discuss entrepreneurship, industry trends, and the occasion book of view. Fair play or playing to win. Meta has been on fire lately, but not in a bad way. In this episode, we're going to discuss some of the things that they have shipped in the last five or so weeks. This is going to include some of their robotics releases, some of their tracking releases, and we'll have a actual demo of a video that I took.

in Japan of a random man walking down a sidewalk and we're going to be tracking him, which is pretty cool. And then there's also some Hollywood ish, not publicly released yet, but met as movie gen. But of course, before we dive in, I'm your host, Dalted Anderson. My background is a bit of a mix of programming, data science and insurance. Offline, you can find me building my side of business, lost in a good book.

You can listen to this podcast in both video and audio format on YouTube. And if audio is my thing, you can find the podcast on Apple podcasts, Spotify, or wherever else you get your podcasts. And another thing I should state before we start this episode is I am in a state of delirium. I have COVID and this is not the COVID that I want to meet again. I would like the kind COVID that treats me nicely.

And this COVID is not so friendly. So I am throwing that out there that I may be mentally a little jumpstarting, like just jumping about in the episode, trains of thoughts, not being complete, just in general. So I'm just throwing that out there. I'm in a state of delirium. I would describe myself as

feeling weightless, but cloudy. That's how it would feel at the moment. So just throwing that out there. So when you are listening to this episode, you are not like, what the heck? This is crazy. This doesn't make any sense. And it may or may not make sense, but this is the issues that I find my, myself in because I have fallen victim to not having episodes in the bank and

Dalton Anderson (02:29.41)
I've never had episodes in the bank. So I've been recording every episode every week instead of having many episodes in the bank and potentially having a keepsake. And yeah, I couldn't have that many episodes in the bank because of the nature of the content I create, but like two episodes would be grand. So just wanted to let you know if

you're a little confused about the stuff I'm talking about and the way that I'm explaining it. That's probably why. Okay. So now we've got that straight. Now we are going to share a screen and we're going to talk about CoTracker 3. So CoTracker 3 is a initiative that was released as a computer, a general purpose computer vision model. It's got many applications, which are quite interesting, but I'm going to talk about that a little bit later.

but I would like to share my screen and if you can't see this and you're listening, I'll talk about it. But if you are viewing it, you can see what it is. So.

Basically, CoTracker 3 is, sorry. I accidentally hit my elbow on the mic. Hope that wasn't too disturbing. So the CoTracker 3 is this way of tracking and it basically pixelizes or puts a point on each pixel and then identifies the object.

and then it tracks and predicts where the object is or will go, which I think is pretty cool. So you will track, but if it's vision gets obscured, it will still be able to pick up on it because it knows or.

Dalton Anderson (04:19.446)
it would already have identified and matched the pixels of the object. So when the object comes back into frame, the object is instantly picked back up, which isn't something that other tracking methodologies can do. So it's better. It's better. And here's some examples. And it compares, it compares some others. So this, this biker,

goes up the hill and then he's, his vision, the vision of the video of the object, which is a kid biking, doing some biking, it gets obscured a little bit and it messes up the other trackers and they get all out of whack. While as co-tracker, it stays right on target the whole time. Cause it predicts where the next movement of the object will go depending on the.

on the flight, I would say like the flight path of like the pixels. And so it picks picks right back up where where it needs to go, which I think is pretty cool. And here's one of like a rhino almost at hippopotamus. I was like, what? It's got horns on its on its on its face. It's talking about state of delirium. That's pretty funny.

Okay, so there's this skateboarder and you can see the skateboarders being tracked by this little point tracker and it's kind of blocking out the other objects. It'll pick them up, but it's really focusing on the focal point and the focal point is this guy skateboarding or this rhino or this person walking a baby. I don't know if that's a man or a woman. but the shorter hair could be a man. I don't know.

because their faces are blocked out.

Dalton Anderson (06:15.31)
But okay, so there's a paper on this. I'm going to review the paper, but we also have a actual demo of a video. So I am going to share this instead. So let's watch the video together. And this is a random man that I, I guess I took a video of. I was really trying to get a video of the city, but I thought it was a pretty good example. You guys.

Dalton Anderson (06:42.52)
And it's pretty short.

Dalton Anderson (06:46.978)
It's pretty short, but it's basically walking in the city of Japan. There's a man in front of me and the vision gets obscured a couple of times. So I've already loaded it up. So I'm submitting it and what I'm doing here is I'm loading into cloud. let me cough.

Dalton Anderson (07:07.172)
All right, sorry. Yeah, as I said, I'm kind of sick. So anyways, so I'm loading it in. It says 20 % or so. So we've got another 80 and I had this loaded before and okay. Now it's done. Okay. Pretty cool. So then I'm just going to hit track. You could identify which, which object you want to track, like by each frame, but I'm not doing that because there's only one object that it'll, it'll be a pick it up.

So it's loading in. So we saw the original videos that man walking, and then it's going to put these points on the map for you. And when I tried this before, it identified what I was trying to look at. So it was fine. So I didn't really see any edits that needed to be done. It did a pretty good job in my opinion.

but hey, I'm not looking for some scientific exact, like wow, it missed the little shadow on the shoulder or something. I'm not zooming in and looking at every pixel. like it's three pixels off. wow. But it's almost done. It's at 80 or so percent. here it is.

Wow. I kind of jinx it every time because I'm telling it, it's almost done. So let me make this full screen. So when the video originally starts, see how it has all the little dots on the map. And then it finally, it picks up to the guy and then it moves the dots off. And then now it starts tracking him. See him? See how there aren't dots everywhere and the dots are being picked up by the object that it's tracking. The man, he just...

I mean, maybe he's working out his left arm, he's just carrying, looks like he's carrying three bags in his left arm and then no bags in his right arm. Life's all about balance, you know? But see how it's tracking again? See, it's got all these points. And so the object left the focal point of the video twice. And then right when it flipped back, it was right there. It was right there every time. It's pretty cool.

Dalton Anderson (09:28.994)
and then it flips back, boom, it's already there. It's already there. It's crazy. It's crazy. I don't know. I think it's pretty sick. All right, stop sharing and then I'll go back to my actual video.

So, okay, so it does tracking. Like why is that? Why is that useful? You know, well, there's a couple things that it could be doing and, maybe to get some interest in some intrigue in the episode, we could start with sports. So you could use it for sports tracking for players or tracking on who is doing what and identifying them on the map and see what they're doing and then track them.

Which would be pretty cool for sports analysis. Something that people may not like and a lot of folks wouldn't like it is surveillance and security. So government surveillance really comes to mind where you're tracking everybody and you're identifying them and then tracking where they go and then making sure they don't go to certain places or doing next things or whatever they're doing.

autonomous vehicles is a good shout. So with autonomous vehicles, you could use something like this to improve their tracking capabilities of tracking objects that go out of frame and then come in frame later. Like it goes out of the frame of vision of the vehicle, but then where does it go? Like where would it go? And then it picks it right back up. So I think those are particular.

interesting. And then there's some for manufacturing. So manufacturing, like understanding where a, I wouldn't say where, like a robot arm needs to pick up an item and then pick it up and put it on something. This tracking mechanism,

Dalton Anderson (11:37.388)
or improve tracking mechanism would be able to pick up these items and know where they're at or identify items that potentially are defective and track where they're going. Those kinds of things. And then there's healthcare. mean, there's probably definitely some ability to use this for like some sort of, I would think like healthcare on the

on the lines of rehabilitation, like tracking the movement of a body. So I would think of it if you were rehabilitating your shoulder and you were doing shoulder rotations or something like that. If you had a tracker and it was tracking your arm and where it's supposed to go and then what you're doing and seeing how you correct it and providing, I think it'd be pretty cool to provide

Like if you were showing someone like your range of movement and then you're with a doctor and then you're tracking the movement of what you have, your mobility on the mobility and then it will show you what you should look like with your tracking and how you would look if you had the right, not access, but.

Dalton Anderson (13:04.462)
maybe the right features unlocked like you're some kind of character where maybe you had your, all your rehabilitation done or you had your surgery or whatever. Like this is what it would look like and or correcting some movement like, you're walking this way really should be walking this way or like running. Yeah. All that stuff would be pretty cool in my opinion.

But next thing that we're going to talk about here is this movie gin we're transitioning. And this is just going to be a list of things that metta shipped. They've shipped so much stuff. So we're transitioning over to movie gin. Movie gin is pretty cool. So if you are watching, you'll see what I'm doing. And if you're on audio, then you won't, but I'll explain it as always. So metta movie gin is a

They're saying one of the most advanced foundational media models in existence. They haven't launched it yet. They're still in.

Sorry, I had a cough. They're still in like creator partnerships, what they call them. But basically MovieGen allows you to not only generate movies or videos via to text, it also allows you to, this is an example. So this one is a text input, a girl running across the beach and holding a kite. She's wearing jean shorts, a yellow shirt and the sun is shining down.

I mean, it's pretty it's a pretty good video. Like you could see this like the steps in the sand and the sand is. Impactful, like not impactful, but like when she's running in the sand. Her. Her feet are hitting the sand and they're leaving imprints, but the closer she gets to the water. The more damn. The sand is so the.

Dalton Anderson (15:15.018)
Not only is the sand start like sticking up when the sand gets it when it when you're approaching the sand was more wet, the the imprints of her foot are more pronounced and the kite is flying in the sky and she's running and her hands don't look weird and can't really see her hands as well. But her her skin complexion on her leg looks a little like odd. But that might be just because like babies legs look weird. You know, I don't know.

but this is something that's pretty cool.

text of a woman in the grass pumpkin patch wearing a scarf and holding a cup and the background's filled with red pumpkins. But the interesting thing here is that you could not only put yourself, personalize videos of yourself or things, you can provide a face shot of your friend or of yourself and you can make a video from it, which I think is pretty neat.

Dalton Anderson (16:21.006)
So look.

These are more videos from text generation. This is some slaw. This guy's got fire. And then this is pretty cool. So you could have an original video that you have. So maybe you're doing some, this example is like running or maybe you're with your friends and you're, you're at a party, like a house party. And maybe you want to change it to a nightclub or some kind of sky rooftop bar.

You can do that. So in this original video, the, this person is running and then it says add blue pom poms to his hands. And now he's running with pom poms. And then his other one says turn, turn it into a Caxus desert and does. And then the next one says, replace the running clothes with an inflatable dinosaur costume. And it looks pretty real. Like, I don't know. It's crazy.

Dalton Anderson (17:25.358)
This one, I'm sorry, I don't know if this costs are getting picked up, but I've been having a cough. This one has this original video is some chick in like a room doing some weird hand movement stuff with her hands. think she's doing like be all she's doing VR stuff. And then it changes the VR headset to change the VR headset to binoculars. And then the next one says, remove the VR headset.

I don't know how it generates the eyes and the rest of her face because all that stuff's covered up, but that's pretty incredible.

And the next one says add bubbles and futuristic effect. Pretty sick. And then this one's changing the color of this guy's t-shirt and the background.

Stuff's incredible. I don't know how they're doing it. It looks so real. Like I don't know what's going on here. There's some black magic stuff. Like I've seen some cool stuff before, but when I saw this, I was really wowed. Really wowed. I was like, wow, that's pretty neat. And this is gonna be, you what is the practical application here? Well, maybe you don't like your shirt that you're wearing in that video. Change the shirt.

Or change the background. Like this is original video warming up for a run. looks like, and this man has this, changed his shirt in the background, changed the background to an outdoor stadium and he's warming up with a blue shirt. I guess they didn't tell us to change the shirt, change the background to an outdoor stadium. I guess it changed the shirt on its own. Weird. That's a bit on. I don't know why I did that.

Dalton Anderson (19:04.132)
I don't know. So then the next thing that's pretty cool is you can make personalized videos. So can take a selfie of yourself and then I'll make a video of you doing something like this guy took a video of himself and then he made it. He became a scientist. This woman. Who just had a selfie with, I don't know, I would say bad lighting. It's overexposed.

has herself in a painting video. She's painting and the hands look great. Lots of dexterity there.

Dalton Anderson (19:41.252)
man, this smile is odd. But it. I mean, it looks a little exaggerated, but I think it's the angle that the guy like his smile to what he gave is pretty close in certain spot, like in the beginning part of the video, it's like it's really extended. But I think it's the angle of which like he's like, say his photo. But yes, this is pretty cool stuff.

Pretty cool stuff. And then you can add a sound, like create effects and soundtracks for your videos. not only can you create a video from text, you could also personalize the video and put objects and or things. You can edit the video with text, completely change the background or objects in the video. You can personalize it putting

putting in yourself and then you can add sound like then you can create soundtracks and effects for your video.

crazy. This isn't released yet. There are only

They are only...

Dalton Anderson (20:59.084)
allowing creator partners to use these videos or this movie gen thing, which is a bummer because I really wanted to use it, but whatever it is, what it is. So that's movie gen. So movie gen is pretty cool. I don't know. Wow. I said, that's probably the first time in a long time. Anyways, so

There's this other object that they release called the Meta Spirit LM, which is originally I thought and was explained to me as like a Google notebook LM competitor, but open source, but really it's a different approach where it's, it's less about standardizing information and more about just having like an assistant nearby that you could process. It's multimodal. can process texts, audio,

and just having an assistant nearby, like on your computer locally, which is a different approach than notebook LM by Google, because that's clearly a summarization and educational tool. Whereas meta spirit LM is

Dalton Anderson (22:23.364)
mean, just overall a different approach. Like it's like having something on your computer that, you know, can process text and audio. Notebook alum can't do that. And then it can respond back in audio. The voice is a little odd and very, I would say somebody said in the comments in the video that Metapost is like, this is what my sleep paralysis demon would sound like. the, like, it's not the best, but

I think overall it's something that met a ship that people can use and it is interesting in its own regard and it is open source. This one, it doesn't allow commercial use, but that's good enough. I mean, open sourcing the community and letting people play with it and figure out the best way to do stuff. You get a lot more feedback when you do some.

Okay, so Meta's robotics advancements. I think before I talk about stuff relating to this, I think the best thing to do is to share my screen and watch a two minute video.

Dalton Anderson (23:47.022)
This is it right here. Cool. So I've already watched it cause I wanted to test the video and thank goodness I did because originally it was coming in so loud. Like I wanted to make sure when I played this video that the audio was coming through and pretty sure it did, but I couldn't hurt to test. So when I was doing it, I was like listening to the after the video, after the video recording test and my,

It was so loud. So I turned it down and made it a little bit less loud. So hopefully that is not too loud, but let's watch the video and it will give us a pretty good understanding of what this is. And then I could talk about it.

Dalton Anderson (24:36.014)
Maybe make it full screen.

Dalton Anderson (27:09.636)
Yeah. Insane, right? I was like the same thing. Crazy. One thing I think is more I would say.

think it's hard to understand that these independent teams launched all these things in the last five weeks or so. Crazy that they, maybe not five, eight weeks, say eight weeks, they've launched all this stuff so soon within each other and they're all.

I would say...

incredible projects and they're all coming with a 90 page research paper, which I'll need to read them and I'll talk about them in the episode. So the next couple of weeks, while I'm working on some special episodes with guests to get that all squared away, I'll be talking about Meta's research papers and I'll probably start with the robotics one because digitizing touch seems very interesting and

Overall, super cool, super cool. Stop sharing.

Dalton Anderson (28:28.004)
I don't know, how are they shipping this much stuff is what I'm having a hard time understanding. This whole meta robotics advancement and the just different integrations with the digitizing the touch with the sensors and having the 460,000 images and then having a 95 % improvement to or

Did they say 95 or 90 %?

think that they said, we literally just watched it together.

Dalton Anderson (29:11.137)
Let's see.

Dalton Anderson (29:16.26)
I think it's 90. 90.

Dalton Anderson (29:23.556)
That's, I know, I just, we literally just watched it. 95. All right. All right. So yeah, I was right. I was doubting myself. just, I, sometimes I doubt myself with these numbers because it's such a high number to say to state out, but we found that Sparsh outperforms task and sensor specific models by an average of over 95 % by this benchmark. So.

not only are they shipping all this stuff, they are absolutely just dominating in the things that they're releasing. Like they're dominating with the Code Tracker 3, they're dominating with Sparsh and these other things. And it's just not even close. I 95 % better than the other models.

And then the movie gin thing, like the movie gin thing looks just flabberg, I'm flabbergasted with all the stuff that they're, that they're launching. I'm really excited to read these papers and see what knowledge I can gleam and share with the audience and everyone that listens to the episodes every week. Appreciate you. And I hope that you find this stuff interesting because it improves me quite a bit. And my understanding of technology and

hopefully a mix of insurance and finance and hopefully in the future, all these things intertwine and become one and allow me to elevate myself and others. But anyways, so that was metasparsh. Sparsh and sparsh means touch in a language called like Sanskrit, Sanskrit, which is a language back in the bronze age and

I don't think many people speak it today, but that's what that sparse means. It means touch, but it sounds pretty cool though. It's like, wow, that's all nifty, but really it literally means touch. So maybe that's something to pull out of the product rule book or roadmap is when next time I come out with a product or X, Y, Z, you just pull up your, your foreign language index and just, okay, what is this? All right, perfect.

Dalton Anderson (31:39.18)
Okay. That's what that means. All right, let's call it that. It's easy to say, it's easy to spell. Let's go. Let's do it.

Dalton Anderson (31:51.513)
And I didn't mention it earlier, but the combination of this Sparsh and the stuff that they're doing with that, the Digi360, the DigiPlex, all these things and creating not only the technology, open sourcing to the community, but then also creating a way for it to be.

easily integrated with having a platform for these sensor connections and also partnering with these other companies to help build out these little digits that they're going to be used for the fingers and the sensors and all that stuff.

think that it's...

it's going to change the game like five years from now. It might be the standard. Like I don't, I don't know other, how, how else someone else would compete with unless they came out with a superior product, but is it, is it open source? Like when you open source a superior product, then everyone else, I don't know how someone can get away with not open sourcing. Like that's like saying,

Okay.

Dalton Anderson (33:10.528)
you can buy my hot dogs, right? And you could also make them yourself. Here's the recipe if you like it a lot. And then there's someone else selling hot dogs, but not only do you have to sell, you have to buy the hot dog. You also have some kind of membership fee like to get, to get your, your hot dog. You've got to have Sam's hot dog membership and then you've got to buy the hot dog. When

This open source hot dog is so much better and you can make it yourself at home and you have all the knowledge of what goes in it. Like why would you use the other one?

So it really burns the alternative. The alternative is just done. And that's really the goal of Mark Zuckerberg and Metta. He is really pushing for these generational technologies that are gonna transform this, not only the industry, but society in general. The demand is open source. He wants it to be open source.

He doesn't want to have a closed closed system model like phones or computers. He wants it to be open source and he wants open source to win. So he's like, yeah, I'm fine. We're just open sourcing everything. Like who cares if it makes any money. We don't need, we don't need the money. We don't need the product. We need to invest in these things to become advanced and to protect ourselves against.

know, sophisticated nations attacking our systems. So we're going to have to have a really advanced technology. And this, in this incident, I'm talking about LLMs and AI. And then this other stuff with advanced robotics and the CoTracker, the original adaptation of these things possibly wasn't from VR, but a lot of these applications are related to VR. And it was something that Mark talked about before with when he was getting a lot of crap,

Dalton Anderson (35:14.756)
for pushing into VR and really leaning into the metaverse and all this stuff was the technologies that we will create from investing and optimizing this technology are going to be incredible. And if you guys can't see that, then I can't help you. But otherwise we're going to be moving forward with this. And you can just see, you can just see some of these things that

A lot of these research projects fold over to VR or fold over to the other things that they're doing. Like the CoTracker 3, I didn't talk about it. I think I forgot to, but gaming, like your gaming, like for VR gaming, tracking your hands, maybe other players in the room, other things like that. Huge, huge. And for this thing right here, the Sparsh and the Digiplex and the

the Touch 360 or MetaDigit 360, those items would help in VR. You could scan in textures and then have these sensors. You could scan in the textures in VR and then simulate these textures back to the human with sensors.

I mean, you get pretty wild pretty quick with all that stuff, like scanning in textures and then allowing people to feel the textures in VR. Before you know it, the Skynet's here, I don't know. Pretty cool, and I'm always excited when people are shipping stuff and it's open source. I really like Meta's approach. I think it's very admirable.

And overall their stuff is great. Like, and they ship it with a paper, like everything they're shipping comes with a paper. And I think that it's such a different approach than Google or open AI. Google, Google is more open source, but like open AI is really open, right? Like they're not very open.

Dalton Anderson (37:42.852)
So the only two big open source folks is X with XII, which is AI on, guess Gronk is what their product is called, but the company is called XAI. And it's worth like 50 billion recently. It was evaluated or something like that. And then there is Meta.

Open AI doesn't open source. Anthropic isn't open source.

Microsoft's AI is an open source. So there's very few folks that are open sourcing, but Meta's stuff is really good. Not only is there AI, but there are other research and it comes with a paper and they disclose so much stuff in the papers that I've read from them. They're very interesting. I really don't know if...

If they keep shipping at this rate, I'm not sure that there is a closed source available. I think everything just eventually becomes open source, which would be great for everyone. I mean, it's a negative for closed source, but if open source and free is maybe 90 % there, why would you use something else? If you get 90 % of your use cases for free and maybe paying 20 bucks or 40 bucks a month,

gives you the other 10%. Like you're those people, the majority of the population are not going to search for the extra 10. They're going to be filed with a 90, which is fine. So let me know what you thought about this episode. Maybe, maybe you felt my state of delirium, maybe not so much. I felt like sometimes I was all over the place, but that's just the nature of, having a Nick Centric hosts, I guess.

Dalton Anderson (39:44.952)
What do you think about some of the things I talked about? I thought the Co-Tracker three demo was pretty cool. Metas Mugen was something else entirely. this sparse, sparse robotics and all of those things that come with it are incredible and be really cool for robotic surgeries or manufacturing or

caught him blanking on it.

Dalton Anderson (40:22.574)
prosthetics. was like, what? Yeah. Prosthetics, prosthetics would be really cool for prosthetics. Like maybe advanced hand sensing for prosthetics and be able to grip things with, I don't know. It's just going to be cool. Everything's going to be really cool in like 10, five years. Like the future is bright. It's brighter than people, people believe. And, and I'd always, always lean into the favorable outcome and being positive and, and, and looking, looking for the best in people.

and not searching for the bad. There's a lot of things that happen to you, but a lot of times those things are intentional from others. So when something happens and you're like, all that person's in not so nice or blah, blah, they probably didn't intentionally do that. Just throwing it out there. Just lean into the brightness of the world and feel the delirium. But in the next,

Coming weeks, I've been trying to-

Dalton Anderson (41:26.532)
gather some guests on the show and I had some guests lined up and then I was out of country for five or so weeks and that kind of fell off and they're a bit annoyed with me. So I try to get them back on the show and then I have a special series, an insurance series. I want to have some insurance vendors on the show. When I was at ITC, I met some founders that would be interested in coming on the show for some of the problems that they're solving.

And with that comes the responsibility of explaining what really is going on in insurance, what's happening in these catastrophic areas and why is it so difficult to get insurance? And then in general explaining on like what, what is insurance like in ins and outs? Like how is insurance created? What is reinsurance? How do you price insurance? All those things and more. And then I want to have some vendors on the show.

talking about some of the problems that they're solving for either governmental agencies, homeowners or companies. But I want to do those things and do it right. So you have the proper background. You're like, wow, this is pretty incredible. Without that, it's going to fall flat. So bear with me. I'm trying my best. COVID doesn't help. So, but as always, I appreciate you and I hope that you tune in next week.

And I hope I'm around next week as well. I'm sure it will be just being dramatic, but of course, wherever you are in this world, have a good afternoon, good evening, good morning and overall have a great day. Goodbye.