Podcasts about minify

Join Kyle, Nader, Vibhu, and swyx live at NVIDIA GTC next week!Now that AIE Europe tix are ~sold out, our attention turns to Miami and World's Fair!The definitive AI Accelerator chip company has more than 10xed this AI Summer:And is now a $4.4 trillion megacorp… that is somehow still moving like a startup. We are blessed to have a unique relationship with our first ever NVIDIA guests: Kyle Kranen who gave a great inference keynote at the first World's Fair and is one of the leading architects of NVIDIA Dynamo (a Datacenter scale inference framework supporting SGLang, TRT-LLM, vLLM), and Nader Khalil, a friend of swyx from our days in Celo in The Arena, who has been drawing developers at GTC since before they were even a glimmer in the eye of NVIDIA:Nader discusses how NVIDIA Brev has drastically reduced the barriers to entry for developers to get a top of the line GPU up and running, and Kyle explains NVIDIA Dynamo as a data center scale inference engine that optimizes serving by scaling out, leveraging techniques like prefill/decode disaggregation, scheduling, and Kubernetes-based orchestration, framed around cost, latency, and quality tradeoffs. We also dive into Jensen's “SOL” (Speed of Light) first-principles urgency concept, long-context limits and model/hardware co-design, internal model APIs (https://build.nvidia.com), and upcoming Dynamo and agent sessions at GTC.Full Video pod on YouTubeTimestamps00:00 Agent Security Basics00:39 Podcast Welcome and Guests07:19 Acquisition and DevEx Shift13:48 SOL Culture and Dynamo Setup27:38 Why Scale Out Wins29:02 Scale Up Limits Explained30:24 From Laptop to Multi Node33:07 Cost Quality Latency Tradeoffs38:42 Disaggregation Prefill vs Decode41:05 Kubernetes Scaling with Grove43:20 Context Length and Co Design57:34 Security Meets Agents58:01 Agent Permissions Model59:10 Build Nvidia Inference Gateway01:01:52 Hackathons And Autonomy Dreams01:10:26 Local GPUs And Scaling Inference01:15:31 Long Running Agents And SF ReflectionsTranscriptAgent Security BasicsNader: Agents can do three things. They can access your files, they can access the internet, and then now they can write custom code and execute it. You literally only let an agent do two of those three things. If you can access your files and you can write custom code, you don't want internet access because that's one to see full vulnerability, right?If you have access to internet and your file system, you should know the full scope of what that agent's capable of doing. Otherwise, now we can get injected or something that can happen. And so that's a lot of what we've been thinking about is like, you know, how do we both enable this because it's clearly the future.But then also, you know, what, what are these enforcement points that we can start to like protect?swyx: All right.Podcast Welcome and Guestsswyx: Welcome to the Lean Space podcast in the Chromo studio. Welcome to all the guests here. Uh, we are back with our guest host Viu. Welcome. Good to have you back. And our friends, uh, Netter and Kyle from Nvidia. Welcome.Kyle: Yeah, thanks for having us.swyx: Yeah, thank you. Actually, I don't even know your titles.Uh, I know you're like architect something of Dynamo.Kyle: Yeah. I, I'm one of the engineering leaders [00:01:00] and a architects of Dynamo.swyx: And you're director of something and developers, developer tech.Nader: Yeah.swyx: You're the developers, developers, developers guy at nvidia,Nader: open source agent marketing, brev,swyx: and likeNader: Devrel tools and stuff.swyx: Yeah. BeenNader: the focus.swyx: And we're, we're kind of recording this ahead of Nvidia, GTC, which is coming to town, uh, again, uh, or taking over town, uh, which, uh, which we'll all be at. Um, and we'll talk a little bit about your sessions and stuff. Yeah.Nader: We're super excited for it.GTC Booth Stunt Storiesswyx: One of my favorite memories for Nader, like you always do like marketing stunts and like while you were at Rev, you like had this surfboard that you like, went down to GTC with and like, NA Nvidia apparently, like did so much that they bought you.Like what, what was that like? What was that?Nader: Yeah. Yeah, we, we, um. Our logo was a chaka. We, we, uh, we were always just kind of like trying to keep true to who we were. I think, you know, some stuff, startups, you're like trying to pretend that you're a bigger, more mature company than you are. And it was actually Evan Conrad from SF Compute who was just like, you guys are like previousswyx: guest.Yeah.Nader: Amazing. Oh, really? Amazing. Yeah. He was just like, guys, you're two dudes in the room. Why are you [00:02:00] pretending that you're not? Uh, and so then we were like, okay, let's make the logo a shaka. We brought surfboards to our booth to GTC and the energy was great. Yeah. Some palm trees too. They,Kyle: they actually poked out over like the, the walls so you could, you could see the bread booth.Oh, that's so funny. AndNader: no one else,Kyle: just from very far away.Nader: Oh, so you remember it backKyle: then? Yeah I remember it pre-acquisition. I was like, oh, those guys look cool,Nader: dude. That makes sense. ‘cause uh, we, so we signed up really last minute, and so we had the last booth. It was all the way in the corner. And so I was, I was worried that no one was gonna come.So that's why we had like the palm trees. We really came in with the surfboards. We even had one of our investors bring her dog and then she was just like walking the dog around to try to like, bring energy towards our booth. Yeah.swyx: Steph.Kyle: Yeah. Yeah, she's the best,swyx: you know, as a conference organizer, I love that.Right? Like, it's like everyone who sponsors a conference comes, does their booth. They're like, we are changing the future of ai or something, some generic b******t and like, no, like actually try to stand out, make it fun, right? And people still remember it after three years.Nader: Yeah. Yeah. You know what's so funny?I'll, I'll send, I'll give you this clip if you wanna, if you wanna add it [00:03:00] in, but, uh, my wife was at the time fiance, she was in medical school and she came to help us. ‘cause it was like a big moment for us. And so we, we bought this cricket, it's like a vinyl, like a vinyl, uh, printer. ‘cause like, how else are we gonna label the surfboard?So, we got a surfboard, luckily was able to purchase that on the company card. We got a cricket and it was just like fine tuning for enterprises or something like that, that we put on the. On the surfboard and it's 1:00 AM the day before we go to GTC. She's helping me put these like vinyl stickers on.And she goes, you son of, she's like, if you pull this off, you son of a b***h. And so, uh, right. Pretty much after the acquisition, I stitched that with the mag music acquisition. I sent it to our family group chat. Ohswyx: Yeah. No, well, she, she made a good choice there. Was that like basically the origin story for Launchable is that we, it was, and maybe we should explain what Brev is andNader: Yeah.Yeah. Uh, I mean, brev is just, it's a developer tool that makes it really easy to get a GPU. So we connect a bunch of different GPU sources. So the basics of it is like, how quickly can we SSH you into a G, into a GPU and whenever we would talk to users, they wanted A GPU. They wanted an A 100. And if you go to like any cloud [00:04:00] provisioning page, usually it's like three pages of forms or in the forms somewhere there's a dropdown.And in the dropdown there's some weird code that you know to translate to an A 100. And I remember just thinking like. Every time someone says they want an A 100, like the piece of text that they're telling me that they want is like, stuffed away in the corner. Yeah. And so we were like, what if the biggest piece of text was what the user's asking for?And so when you go to Brev, it's just big GPU chips with the type that you want withswyx: beautiful animations that you worked on pre, like pre you can, like, now you can just prompt it. But back in the day. Yeah. Yeah. Those were handcraft, handcrafted artisanal code.Nader: Yeah. I was actually really proud of that because, uh, it was an, i I made it in Figma.Yeah. And then I found, I was like really struggling to figure out how to turn it from like Figma to react. So what it actually is, is just an SVG and I, I have all the styles and so when you change the chip, whether it's like active or not it changes the SVG code and that somehow like renders like, looks like it's animating, but it, we just had the transition slow, but it's just like the, a JavaScript function to change the like underlying SVG.Yeah. And that was how I ended up like figuring out how to move it from from Figma. But yeah, that's Art Artisan. [00:05:00]Kyle: Speaking of marketing stunts though, he actually used those SVGs. Or kind of use those SVGs to make these cards.Nader: Oh yeah. LikeKyle: a GPU gift card Yes. That he handed out everywhere. That was actually my first impression of thatNader: one.Yeah,swyx: yeah, yeah.Nader: Yeah.swyx: I think I still have one of them.Nader: They look great.Kyle: Yeah.Nader: I have a ton of them still actually in our garage, which just, they don't have labels. We should honestly like bring, bring them back. But, um, I found this old printing press here, actually just around the corner on Ven ness. And it's a third generation San Francisco shop.And so I come in an excited startup founder trying to like, and they just have this crazy old machinery and I'm in awe. ‘cause the the whole building is so physical. Like you're seeing these machines, they have like pedals to like move these saws and whatever. I don't know what this machinery is, but I saw all three generations.Like there's like the grandpa, the father and the son, and the son was like, around my age. Well,swyx: it's like a holy, holy trinity.Nader: It's funny because we, so I just took the same SVG and we just like printed it and it's foil printing, so they make a a, a mold. That's like an inverse of like the A 100 and then they put the foil on it [00:06:00] and then they press it into the paper.And I remember once we got them, he was like, Hey, don't forget about us. You know, I guess like early Apple and Cisco's first business cards were all made there. And so he was like, yeah, we, we get like the startup businesses but then as they mature, they kind of go somewhere else. And so I actually, I think we were talking with marketing about like using them for some, we should go back and make some cards.swyx: Yeah, yeah, yeah. You know, I remember, you know, as a very, very small breadth investor, I was like, why are we spending time like, doing these like stunts for GPUs? Like, you know, I think like as a, you know, typical like cloud hard hardware person, you go into an AWS you pick like T five X xl, whatever, and it's just like from a list and you look at the specs like, why animate this GP?And, and I, I do think like it just shows the level of care that goes throughout birth and Yeah. And now, and also the, and,Nader: and Nvidia. I think that's what the, the thing that struck me most when we first came in was like the amount of passion that everyone has. Like, I think, um, you know, you talk to, you talk to Kyle, you talk to, like, every VP that I've met at Nvidia goes so close to the metal.Like, I remember it was almost a year ago, and like my VP asked me, he's like, Hey, [00:07:00] what's cursor? And like, are you using it? And if so, why? Surprised at this, and he downloaded Cursor and he was asking me to help him like, use it. And I thought that was, uh, or like, just show him what he, you know, why we were using it.And so, the amount of care that I think everyone has and the passion, appreciate, passion and appreciation for the moment. Right. This is a very unique time. So it's really cool to see everyone really like, uh, appreciate that.swyx: Yeah.Acquisition and DevEx Shiftswyx: One thing I wanted to do before we move over to sort of like research topics and, uh, the, the stuff that Kyle's working on is just tell the story of the acquisition, right?Like, not many people have been, been through an acquisition with Nvidia. What's it like? Uh, what, yeah, just anything you'd like to say.Nader: It's a crazy experience. I think, uh, you know, we were the thing that was the most exciting for us was. Our goal was just to make it easier for developers.We wanted to find access to GPUs, make it easier to do that. And then all, oh, actually your question about launchable. So launchable was just make one click exper, like one click deploys for any software on top of the GPU. Mm-hmm. And so what we really liked about Nvidia was that it felt like we just got a lot more resources to do all of that.I think, uh, you [00:08:00] know, NVIDIA's goal is to make things as easy for developers as possible. So there was a really nice like synergy there. I think that, you know, when it comes to like an acquisition, I think the amount that the soul of the products align, I think is gonna be. Is going speak to the success of the acquisition.Yeah. And so it in many ways feels like we're home. This is a really great outcome for us. Like we you know, I love brev.nvidia.com. Like you should, you should use it's, it's theKyle: front page for GPUs.Nader: Yeah. Yeah. If you want GP views,Kyle: you go there, getswyx: it there, and it's like internally is growing very quickly.I, I don't remember You said some stats there.Nader: Yeah, yeah, yeah. It's, uh, I, I wish I had the exact numbers, but like internally, externally, it's been growing really quickly. We've been working with a bunch of partners with a bunch of different customers and ISVs, if you have a solution that you want someone that runs on the GPU and you want people to use it quickly, we can bundle it up, uh, in a launchable and make it a one click run.If you're doing things and you want just like a sandbox or something to run on, right. Like open claw. Huge moment. Super exciting. Our, uh, and we'll talk into it more, but. You know, internally, people wanna run this, and you, we know we have to be really careful from the security implications. Do we let this run on the corporate network?Security's guidance was, Hey, [00:09:00] run this on breath, it's in, you know, it's, it's, it's a vm, it's sitting in the cloud, it's off the corporate network. It's isolated. And so that's been our stance internally and externally about how to even run something like open call while we figure out how to run these things securely.But yeah,swyx: I think there's also like, you almost like we're the right team at the right time when Nvidia is starting to invest a lot more in developer experience or whatever you call it. Yeah. Uh, UX or I don't know what you call it, like software. Like obviously NVIDIA is always invested in software, but like, there's like, this is like a different audience.Yeah. It's aNader: widerKyle: developer base.swyx: Yeah. Right.Nader: Yeah. Yeah. You know, it's funny, it's like, it's not, uh,swyx: so like, what, what is it called internally? What, what is this that people should be aware that is going on there?Nader: Uh, what, like developer experienceswyx: or, yeah, yeah. Is it's called just developer experience or is there like a broader strategy hereNader: in Nvidia?Um, Nvidia always wants to make a good developer experience. The thing is and a lot of the technology is just really complicated. Like, it's not, it's uh, you know, I think, um. The thing that's been really growing or the AI's growing is having a huge moment, not [00:10:00] because like, let's say data scientists in 2018, were quiet then and are much louder now.The pie is com, right? There's a whole bunch of new audiences. My mom's wondering what she's doing. My sister's learned, like taught herself how to code. Like the, um, you know, I, I actually think just generally AI's a big equalizer and you're seeing a more like technologically literate society, I guess.Like everyone's, everyone's learning how to code. Uh, there isn't really an excuse for that. And so building a good UX means that you really understand who your end user is. And when your end user becomes such a wide, uh, variety of people, then you have to almost like reinvent the practice, right? Yeah. You haveKyle: to, and actually build more developer ux, right?Because the, there are tiers of developer base that were added. You know, the, the hackers that are building on top of open claw, right? For example, have never used gpu. They don't know what kuda is. They, they, they just want to run something.Nader: Yeah.Kyle: You need new UX that is not just. Hey, you know, how do you program something in Cuda and run it?And then, and then we built, you know, like when Deep Learning was getting big, we built, we built Torch and, and, but so recently the amount of like [00:11:00] layers that are added to that developer stack has just exploded because AI has become ubiquitous. Everyone's using it in different ways. Yeah. It'sNader: moving fast in every direction.Vertical, horizontal.Vibhu: Yeah. You guys, you even take it down to hardware, like the DGX Spark, you know, it's, it's basically the same system as just throwing it up on big GPU cluster.Nader: Yeah, yeah, yeah. It's amazing. Blackwell.swyx: Yeah. Uh, we saw the preview at the last year's GTC and that was one of the better performing, uh, videos so far, and video coverage so far.Awesome. This will beat it. Um,Nader: that wasswyx: actually, we have fingersNader: crossed. Yeah.DGX Spark and Remote AccessNader: Even when Grace Blackwell or when, um, uh, DGX Spark was first coming out getting to be involved in that from the beginning of the developer experience. And it just comes back to what youswyx: were involved.Nader: Yeah. St. St.swyx: Mars.Nader: Yeah. Yeah. I mean from, it was just like, I, I got an email, we just got thrown into the loop and suddenly yeah, I, it was actually really funny ‘cause I'm still pretty fresh from the acquisition and I'm, I'm getting an email from a bunch of the engineering VPs about like, the new hardware, GPU chip, like we're, or not chip, but just GPU system that we're putting out.And I'm like, okay, cool. Matters. Now involved with this for the ux, I'm like. What am I gonna do [00:12:00] here? So, I remember the first meeting, I was just like kind of quiet as I was hearing engineering VPs talk about what this box could be, what it could do, how we should use it. And I remember, uh, one of the first ideas that people were idea was like, oh, the first thing that it was like, I think a quote was like, the first thing someone's gonna wanna do with this is get two of them and run a Kubernetes cluster on top of them.And I was like, oh, I think I know why I'm here. I was like, the first thing we're doing is easy. SSH into the machine. And then, and you know, just kind of like scoping it down of like, once you can do that every, you, like the person who wants to run a Kubernetes cluster onto Sparks has a higher propensity for pain, then, then you know someone who buys it and wants to run open Claw right now, right?If you can make sure that that's as effortless as possible, then the rest becomes easy. So there's a tool called Nvidia Sync. It just makes the SSH connection really simple. So, you know, if you think about it like. If you have a Mac, uh, or a PC or whatever, if you have a laptop and you buy this GPU and you want to use it, you should be able to use it like it's A-A-G-P-U in the cloud, right?Um, but there's all this friction of like, how do you actually get into that? That's part of [00:13:00] Revs value proposition is just, you know, there's a CLI that wraps SSH and makes it simple. And so our goal is just get you into that machine really easily. And one thing we just launched at CES, it's in, it's still in like early access.We're ironing out some kinks, but it should be ready by GTC. You can register your spark on Brev. And so now if youswyx: like remote managed yeah, local hardware. Single pane of glass. Yeah. Yeah. Because Brev can already manage other clouds anyway, right?Vibhu: Yeah, yeah. And you use the spark on Brev as well, right?Nader: Yeah. But yeah, exactly. So, so you, you, so you, you set it up at home you can run the command on it, and then it gets it's essentially it'll appear in your Brev account, and then you can take your laptop to a Starbucks or to a cafe, and you'll continue to use your, you can continue use your spark just like any other cloud node on Brev.Yeah. Yeah. And it's just like a pre-provisioned centerswyx: in yourNader: home. Yeah, exactly.swyx: Yeah. Yeah.Vibhu: Tiny little data center.Nader: Tiny little, the size ofVibhu: your phone.SOL Culture and Dynamo Setupswyx: One more thing before we move on to Kyle. Just have so many Jensen stories and I just love, love mining Jensen stories. Uh, my favorite so far is SOL. Uh, what is, yeah, what is S-O-L-S-O-LNader: is actually, i, I think [00:14:00] of all the lessons I've learned, that one's definitely my favorite.Kyle: It'll always stick with you.Nader: Yeah. Yeah. I, you know, in your startup, everything's existential, right? Like we've, we've run out of money. We were like, on the risk of, of losing payroll, we've had to contract our team because we l ran outta money. And so like, um, because of that you're really always forcing yourself to I to like understand the root cause of everything.If you get a date, if you get a timeline, you know exactly why that date or timeline is there. You're, you're pushing every boundary and like, you're not just say, you're not just accepting like a, a no. Just because. And so as you start to introduce more layers, as you start to become a much larger organization, SOL is is essentially like what is the physics, right?The speed of light moves at a certain speed. So if flight's moving some slower, then you know something's in the way. So before trying to like layer reality back in of like, why can't this be delivered at some date? Let's just understand the physics. What is the theoretical limit to like, uh, how fast this can go?And then start to tell me why. ‘cause otherwise people will start telling you why something can't be done. But actually I think any great leader's goal is just to create urgency. Yeah. [00:15:00] There's an infiniteKyle: create compelling events, right?Nader: Yeah.Kyle: Yeah. So l is a term video is used to instigate a compelling event.You say this is done. How do we get there? What is the minimum? As much as necessary, as little as possible thing that it takes for us to get exactly here and. It helps you just break through a bunch of noise.swyx: Yeah.Kyle: Instantly.swyx: One thing I'm unclear about is, can only Jensen use the SOL card? Like, oh, no, no, no.Not everyone get the b******t out because obviously it's Jensen, but like, can someone else be like, no, likeKyle: frontline engineers use it.Nader: Yeah. Every, I think it's not so much about like, get the b******t out. It's like, it's like, give me the root understanding, right? Like, if you tell me something takes three weeks, it like, well, what's the first principles?Yeah, the first principles. It's like, what's the, what? Like why is it three weeks? What is the actual yeah. What's the actual limit of why this is gonna take three weeks? If you're gonna, if you, if let's say you wanted to buy a new computer and someone told you it's gonna be here in five days, what's the SOL?Well, like the SOL is like, I could walk into a Best Buy and pick it up for you. Right? So then anything that's like beyond that is, and is that practical? Is that how we're gonna, you know, let's say give everyone in the [00:16:00] company a laptop, like obviously not. So then like that's the SOL and then it's like, okay, well if we have to get more than 10, suddenly there might be some, right?And so now we can kind of piece the reality back.swyx: So, so this is the. Paul Graham do things that don't scale. Yeah. And this is also the, what people would now call behi agency. Yeah.Kyle: It's actually really interesting because there's a, there's a second hardware angle to SOL that like doesn't come up for all the org sol is used like culturally at aswyx: media for everything.I'm also mining for like, I think that can be annoying sometimes. And like someone keeps going IOO you and you're like, guys, like we have to be stable. We have to, we to f*****g plan. Yeah.Kyle: It's an interesting balance.Nader: Yeah. I encounter that with like, actually just with, with Alec, right? ‘cause we, we have a new conference so we need to launch, we have, we have goals of what we wanna launch by, uh, by the conference and like, yeah.At the end of the day, where isswyx: this GTC?Nader: Um, well this is like, so we, I mean we did it for CES, we did for GT CDC before that we're doing it for GTC San Jose. So I mean, like every, you know, we have a new moment. Um, and we want to launch something. Yeah. And we want to do so at SOL and that does mean that some, there's some level of prioritization that needs [00:17:00] to happen.And so it, it is difficult, right? I think, um, you have to be careful with what you're pushing. You know, stability is important and that should be factored into S-O-L-S-O-L isn't just like, build everything and let it break, you know, that, that's part of the conversation. So as you're laying, layering in all the details, one of them might be, Hey, we could build this, but then it's not gonna be stable for X, y, z reasons.And so that was like, one of our conversations for CES was, you know, hey, like we, we can get this into early access registering your spark with brev. But there are a lot of things that we need to do in order to feel really comfortable from a security perspective, right? There's a lot of networking involved before we deliver that to users.So it's like, okay. Let's get this to a point where we can at least let people experiment with it. We had it in a booth, we had it in Jensen's keynote, and then let's go iron out all the networking kinks. And that's not easy. And so, uh, that can come later. And so that was the way that we layered that back in.Yeah. ButKyle: It's not really about saying like, you don't have to do the, the maintenance or operational work. It's more about saying, you know, it's kind of like [00:18:00] highlights how progress is incremental, right? Like, what is the minimum thing that we can get to. And then there's SOL for like every component after that.But there's the SOL to get you, get you to the, the starting line. And that, that's usually how it's asked. Yeah. On the other side, you know, like SOL came out of like hardware at Nvidia. Right. So SOL is like literally if we ran the accelerator or the GPU with like at basically full speed with like no other constraints, like how FAST would be able to make a program go.swyx: Yeah. Yeah. Right.Kyle: Soswyx: in, in training that like, you know, then you work back to like some percentage of like MFU for example.Kyle: Yeah, that's a, that's a great example. So like, there's an, there's an S-O-L-M-F-U, and then there's like, you know, what's practically achievable.swyx: Cool. Should we move on to sort of, uh, Kyle's side?Uh, Kyle, you're coming more from the data science world. And, uh, I, I mean I always, whenever, whenever I meet someone who's done working in tabular stuff, graph neural networks, time series, these are basically when I go to new reps, I go to ICML, I walk the back halls. There's always like a small group of graph people.Yes. Absolute small group of tabular people. [00:19:00] And like, there's no one there. And like, it's very like, you know what I mean? Like, yeah, no, like it's, it's important interesting work if you care about solving the problems that they solve.Kyle: Yeah.swyx: But everyone else is just LMS all the time.Kyle: Yeah. I mean it's like, it's like the black hole, right?Has the event horizon reached this yet in nerves? Um,swyx: but like, you know, those are, those are transformers too. Yeah. And, and those are also like interesting things. Anyway, uh, I just wanted to spend a little bit of time on, on those, that background before we go into Dynamo, uh, proper.Kyle: Yeah, sure. I took a different path to Nvidia than that, or I joined six years ago, seven, if you count, when I was an intern.So I joined Nvidia, like right outta college. And the first thing I jumped into was not what I'd done in, during internship, which was like, you know, like some stuff for autonomous vehicles, like heavyweight object detection. I jumped into like, you know, something, I'm like, recommenders, this is popular. Andswyx: yeah, he did RexiKyle: as well.Yeah, Rexi. Yeah. I mean that, that was the taboo data at the time, right? You have tables of like, audience qualities and item qualities, and you're trying to figure out like which member of [00:20:00] the audience matches which item or, or more practically which item matches which member of the audience. And at the time, really it was like we were trying to enable.Uh, recommender, which had historically been like a little bit of a CP based workflow into something that like, ran really well in GPUs. And it's since been done. Like there are a bunch of libraries for Axis that run on GPUs. Uh, the common models like Deeplearning recommendation model, which came outta meta and the wide and deep model, which was used or was released by Google were very accelerated by GPUs using, you know, the fast HBM on the chips, especially to do, you know, vector lookups.But it was very interesting at the time and super, super relevant because like we were starting to get like. This explosion of feeds and things that required rec recommenders to just actively be on all the time. And sort of transitioned that a little bit towards graph neural networks when I discovered them because I was like, okay, you can actually use graphical neural networks to represent like, relationships between people, items, concepts, and that, that interested me.So I jumped into that at [00:21:00] Nvidia and, and got really involved for like two-ish years.swyx: Yeah. Uh, and something I learned from Brian Zaro Yeah. Is that you can just kind of choose your own path in Nvidia.Kyle: Oh my God. Yeah.swyx: Which is not a normal big Corp thing. Yeah. Like you, you have a lane, you stay in your lane.Nader: I think probably the reason why I enjoy being in a, a big company, the mission is the boss probably from a startup guy. Yeah. The missionswyx: is the boss.Nader: Yeah. Uh, it feels like a big game of pickup basketball. Like, you know, if you play one, if you wanna play basketball, you just go up to the court and you're like, Hey look, we're gonna play this game and we need three.Yeah. And you just like find your three. That's honestly for every new initiative that's what it feels like. Yeah.Vibhu: It also like shows, right? Like Nvidia. Just releasing state-of-the-art stuff in every domain. Yeah. Like, okay, you expect foundation models with Nemo tron voice just randomly parakeet.Call parakeet just comes out another one, uh, voice. TheKyle: video voice team has always been producing.Vibhu: Yeah. There's always just every other domain of paper that comes out, dataset that comes out. It's like, I mean, it also stems back to what Nvidia has to do, right? You have to make chips years before they're actually produced.Right? So you need to know, you need to really [00:22:00] focus. TheKyle: design process starts likeVibhu: exactlyKyle: three to five years before the chip gets to the market.Vibhu: Yeah. I, I'm curious more about what that's like, right? So like, you have specialist teams. Is it just like, you know, people find an interest, you go in, you go deep on whatever, and that kind of feeds back into, you know, okay, we, we expect predictions.Like the internals at Nvidia must be crazy. Right? You know? Yeah. Yeah. You know, you, you must. Not even without selling to people, you have your own predictions of where things are going. Yeah. And they're very based, very grounded. Right?Kyle: Yeah. It, it, it's really interesting. So there's like two things that I think that Amed does, which are quite interesting.Uh, one is like, we really index into passion. There's a big. Sort of organizational top sound push to like ensure that people are working on the things that they're passionate about. So if someone proposes something that's interesting, many times they can just email someone like way up the chain that they would find this relevant and say like, Hey, can I go work on this?Nader: It's actually like I worked at a, a big company for a couple years before, uh, starting on my startup journey and like, it felt very weird if you were to like email out of chain, if that makes [00:23:00] sense. Yeah. The emails at Nvidia are like mosh pitsswyx: shoot,Nader: and it's just like 60 people, just whatever. And like they're, there's this,swyx: they got messy like, reply all you,Nader: oh, it's in, it's insane.It's insane. They justKyle: help. You know, Maxim,Nader: the context. But, but that's actually like, I've actually, so this is a weird thing where I used to be like, why would we send emails? We have Slack. I am the entire, I'm the exact opposite. I feel so bad for anyone who's like messaging me on Slack ‘cause I'm so unresponsive.swyx: Your emailNader: Maxi, email Maxim. I'm email maxing Now email is a different, email is perfect because man, we can't work together. I'm email is great, right? Because important threads get bumped back up, right? Yeah, yeah. Um, and so Slack doesn't do that. So I just have like this casino going off on the right or on the left and like, I don't know which thread was from where or what, but like the threads get And then also just like the subject, so you can have like working threads.I think what's difficult is like when you're small, if you're just not 40,000 people I think Slack will work fine, but there's, I don't know what the inflection point is. There is gonna be a point where that becomes really messy and you'll actually prefer having email. ‘cause you can have working threads.You can cc more than nine people in a thread.Kyle: You can fork stuff.Nader: You can [00:24:00] fork stuff, which is super nice and just like y Yeah. And so, but that is part of where you can propose a plan. You can also just. Start, honestly, momentum's the only authority, right? So like, if you can just start, start to make a little bit of progress and show someone something, and then they can try it.That's, I think what's been, you know, I think the most effective way to push anything for forward. And that's both at Nvidia and I think just generally.Kyle: Yeah, there's, there's the other concept that like is explored a lot at Nvidia, which is this idea of a zero billion dollar business. Like market creation is a big thing at Nvidia.Like,swyx: oh, you want to go and start a zero billion dollar business?Kyle: Jensen says, we are completely happy investing in zero billion dollar markets. We don't care if this creates revenue. It's important for us to know about this market. We think it will be important in the future. It can be zero billion dollars for a while.I'm probably minging as words here for, but like, you know, like, I'll give an example. NVIDIA's been working on autonomous driving for a a long time,swyx: like an Nvidia car.Kyle: No, they, they'veVibhu: used the Mercedes, right? They're around the HQ and I think it finally just got licensed out. Now they're starting to be used quite a [00:25:00] bit.For 10 years you've been seeing Mercedes with Nvidia logos driving.Kyle: If you're in like the South San Santa Clara, it's, it's actually from South. Yeah. So, um. Zero billion dollar markets are, are a thing like, you know, Jensen,swyx: I mean, okay, look, cars are not a zero billion dollar market. But yeah, that's a bad example.Nader: I think, I think he's, he's messaging, uh, zero today, but, or even like internally, right? Like, like it's like, uh, an org doesn't have to ruthlessly find revenue very quickly to justify their existence. Right. Like a lot of the important research, a lot of the important technology being developed that, that's kind ofKyle: where research, research is very ide ideologically free at Nvidia.Yeah. Like they can pursue things that they wereswyx: Were you research officially?Kyle: I was never in research. Officially. I was always in engineering. Yeah. We in, I'm in an org called Deep Warning Algorithms, which is basically just how do we make things that are relevant to deep warning go fast.swyx: That sounds freaking cool.Vibhu: And I think a lot of that is underappreciated, right? Like time series. This week Google put out time. FF paper. Yeah. A new time series, paper res. Uh, Symantec, ID [00:26:00] started applying Transformers LMS to Yes. Rec system. Yes. And when you think the scale of companies deploying these right. Amazon recommendations, Google web search, it's like, it's huge scale andKyle: Yeah.Vibhu: You want fast?Kyle: Yeah. Yeah. Yeah. Actually it's, it, I, there's a fun moment that brought me like full circle. Like, uh, Amazon Ads recently gave a talk where they talked about using Dynamo for generative recommendation, which was like super, like weirdly cathartic for me. I'm like, oh my God. I've, I've supplanted what I was working on.Like, I, you're using LMS now to do what I was doing five years ago.swyx: Yeah. Amazing. And let's go right into Dynamo. Uh, maybe introduce Yeah, sure. To the top down and Yeah.Kyle: I think at this point a lot of people are familiar with the term of inference. Like funnily enough, like I went from, you know, inference being like a really niche topic to being something that's like discussed on like normal people's Twitter feeds.It's,Nader: it's on billboardsKyle: here now. Yeah. Very, very strange. Driving, driving, seeing just an inference ad on 1 0 1 inference at scale is becoming a lot more important. Uh, we have these moments like, you know, open claw where you have these [00:27:00] agents that take lots and lots of tokens, but produce, incredible results.There are many different aspects of test time scaling so that, you know, you can use more inference to generate a better result than if you were to use like a short amount of inference. There's reasoning, there's quiring, there's, adding agency to the model, allowing it to call tools and use skills.Dyno sort came about at Nvidia. Because myself and a couple others were, were sort of talking about the, these concepts that like, you know, you have inference engines like VLMS, shelan, tenor, TLM and they have like one single copy. They, they, they sort of think about like things as like one single copy, like one replica, right?Why Scale Out WinsKyle: Like one version of the model. But when you're actually serving things at scale, you can't just scale up that replica because you end up with like performance problems. There's a scaling limit to scaling up replicas. So you actually have to scale out to use a, maybe some Kubernetes type terminology.We kind of realized that there was like. A lot of potential optimization that we could do in scaling out and building systems for data [00:28:00] center scale inference. So Dynamo is this data center scale inference engine that sits on top of the frameworks like VLM Shilling and 10 T lm and just makes things go faster because you can leverage the economy of scale.The fact that you have KV cash, which we can define a little bit later, uh, in all these machines that is like unique and you wanna figure out like the ways to maximize your cash hits or you want to employ new techniques in inference like disaggregation, which Dynamo had introduced to the world in, in, in March, not introduced, it was a academic talk, but beforehand.But we are, you know, one of the first frameworks to start, supporting it. And we wanna like, sort of combine all these techniques into sort of a modular framework that allows you to. Accelerate your inference at scale.Nader: By the way, Kyle and I became friends on my first date, Nvidia, and I always loved, ‘cause like he always teaches meswyx: new things.Yeah. By the way, this is why I wanted to put two of you together. I was like, yeah, this is, this is gonna beKyle: good. It's very, it's very different, you know, like we've, we, we've, we've talked to each other a bunch [00:29:00] actually, you asked like, why, why can't we scale up?Nader: Yeah.Scale Up Limits ExplainedNader: model, you said model replicas.Kyle: Yeah. So you, so scale up means assigning moreswyx: heavier?Kyle: Yeah, heavier. Like making things heavier. Yeah, adding more GPUs. Adding more CPUs. Scale out is just like having a barrier saying, I'm gonna duplicate my representation of the model or a representation of this microservice or something, and I'm gonna like, replicate it Many times.Handle, load. And the reason that you can't scale, scale up, uh, past some points is like, you know, there, there, there are sort of hardware bounds and algorithmic bounds on, on that type of scaling. So I'll give you a good example that's like very trivial. Let's say you're on an H 100. The Maxim ENV link domain for H 100, for most Ds H one hundreds is heus, right?So if you scaled up past that, you're gonna have to figure out ways to handle the fact that now for the GPUs to communicate, you have to do it over Infin band, which is still very fast, but is not as fast as ENV link.swyx: Is it like one order of magnitude, like hundreds or,Kyle: it's about an order of magnitude?Yeah. Okay. Um, soswyx: not terrible.Kyle: [00:30:00] Yeah. I, I need to, I need to remember the, the data sheet here, like, I think it's like about 500 gigabytes. Uh, a second unidirectional for ENV link, and about 50 gigabytes a second unidirectional for Infin Band. I, it, it depends on the, the generation.swyx: I just wanna set this up for people who are not familiar with these kinds of like layers and the trash speedVibhu: and all that.Of course.From Laptop to Multi NodeVibhu: Also, maybe even just going like a few steps back before that, like most people are very familiar with. You see a, you know, you can use on your laptop, whatever these steel viol, lm you can just run inference there. All, there's all, you can, youcan run it on thatVibhu: laptop. You can run on laptop.Then you get to, okay, uh, models got pretty big, right? JLM five, they doubled the size, so mm-hmm. Uh, what do you do when you have to go from, okay, I can get 128 gigs of memory. I can run it on a spark. Then you have to go multi GPU. Yeah. Okay. Multi GPU, there's some support there. Now, if I'm a company and I don't have like.I'm not hiring the best researchers for this. Right. But I need to go [00:31:00] multi-node, right? I have a lot of servers. Okay, now there's efficiency problems, right? You can have multiple eight H 100 nodes, but, you know, is that as a, like, how do you do that efficiently?Kyle: Yeah. How do you like represent them? How do you choose how to represent the model?Yeah, exactly right. That's a, that's like a hard question. Everyone asks, how do you size oh, I wanna run GLM five, which just came out new model. There have been like four of them in the past week, by the way, like a bunch of new models.swyx: You know why? Right? Deep seek.Kyle: No comment. Oh. Yeah, but Ggl, LM five, right?We, we have this, new model. It's, it's like a large size, and you have to figure out how to both scale up and scale out, right? Because you have to find the right representation that you care about. Everyone does this differently. Let's be very clear. Everyone figures this out in their own path.Nader: I feel like a lot of AI or ML even is like, is like this. I think people think, you know, I, I was, there was some tweet a few months ago that was like, why hasn't fine tuning as a service taken off? You know, that might be me. It might have been you. Yeah. But people want it to be such an easy recipe to follow.But even like if you look at an ML model and specificKyle: to you Yeah,Nader: yeah.Kyle: And the [00:32:00] model,Nader: the situation, and there's just so much tinkering, right? Like when you see a model that has however many experts in the ME model, it's like, why that many experts? I don't, they, you know, they tried a bunch of things and that one seemed to do better.I think when it comes to how you're serving inference, you know, you have a bunch of decisions to make and there you can always argue that you can take something and make it more optimal. But I think it's this internal calibration and appetite for continued calibration.Vibhu: Yeah. And that doesn't mean like, you know, people aren't taking a shot at this, like tinker from thinking machines, you know?Yeah. RL as a service. Yeah, totally. It's, it also gets even harder when you try to do big model training, right? We're not the best at training Moes, uh, when they're pre-trained. Like we saw this with LAMA three, right? They're trained in such a sparse way that meta knows there's gonna be a bunch of inference done on these, right?They'll open source it, but it's very trained for what meta infrastructure wants, right? They wanna, they wanna inference it a lot. Now the question to basically think about is, okay, say you wanna serve a chat application, a coding copilot, right? You're doing a layer of rl, you're serving a model for X amount of people.Is it a chat model, a coding model? Dynamo, you know, back to that,Kyle: it's [00:33:00] like, yeah, sorry. So you we, we sort of like jumped off of, you know, jumped, uh, on that topic. Everyone has like, their own, own journey.Cost Quality Latency TradeoffsKyle: And I, I like to think of it as defined by like, what is the model you need? What is the accuracy you need?Actually I talked to NA about this earlier. There's three axes you care about. What is the quality that you're able to produce? So like, are you accurate enough or can you complete the task with enough, performance, high enough performance. Yeah, yeah. Uh, there's cost. Can you serve the model or serve your workflow?Because it's not just the model anymore, it's the workflow. It's the multi turn with an agent cheaply enough. And then can you serve it fast enough? And we're seeing all three of these, like, play out, like we saw, we saw new models from OpenAI that you know, are faster. You have like these new fast versions of models.You can change the amount of thinking to change the amount of quality, right? Produce more tokens, but at a higher cost in a, in a higher latency. And really like when you start this journey of like trying to figure out how you wanna host a model, you, you, you think about three things. What is the model I need to serve?How many times do I need to call it? What is the input sequence link was [00:34:00] the, what does the workflow look like on top of it? What is the SLA, what is the latency SLA that I need to achieve? Because there's usually some, this is usually like a constant, you, you know, the SLA that you need to hit and then like you try and find the lowest cost version that hits all of these constraints.Usually, you know, you, you start with those things and you say you, you kind of do like a bit of experimentation across some common configurations. You change the tensor parallel size, which is a form of parallelismVibhu: I take, it goes even deeper first. Gotta think what model.Kyle: Yes, course,ofKyle: course. It's like, it's like a multi-step design process because as you said, you can, you can choose a smaller model and then do more test time scaling and it'll equate the quality of a larger model because you're doing the test time scaling or you're adding a harness or something.So yes, it, it goes way deeper than that. But from the performance perspective, like once you get to the model you need, you need to host, you look at that and you say, Hey. I have this model, I need to serve it at the speed. What is the right configuration for that?Nader: You guys see the recent, uh, there was a paper I just saw like a few days ago that, uh, if you run [00:35:00] the same prompt twice, you're getting like double Just try itagain.Nader: Yeah, exactly.Vibhu: And you get a lot. Yeah. But the, the key thing there is you give the context of the failed try, right? Yeah. So it takes a shot. And this has been like, you know, basic guidance for quite a while. Just try again. ‘cause you know, trying, just try again. Did you try again? All adviceNader: in life.Vibhu: Just, it's a paper from Google, if I'm not mistaken, right?Yeah,Vibhu: yeah. I think it, it's like a seven bas little short paper. Yeah. Yeah. The title's very cute. And it's just like, yeah, just try again. Give it ask context,Kyle: multi-shot. You just like, say like, hey, like, you know, like take, take a little bit more, take a little bit more information, try and fail. Fail.Vibhu: And that basic concept has gone pretty deep.There's like, um, self distillation, rl where you, you do self distillation, you do rl and you have past failure and you know, that gives some signal so people take, try it again. Not strong enough.swyx: Uh, for, for listeners, uh, who listen to here, uh, vivo actually, and I, and we run a second YouTube channel for our paper club where, oh, that's awesome.Vivo just covered this. Yeah. Awesome. Self desolation and all that's, that's why he, to speed [00:36:00] on it.Nader: I'll to check it out.swyx: Yeah. It, it's just a good practice, like everyone needs, like a paper club where like you just read papers together and the social pressure just kind of forces you to just,Nader: we, we,there'sNader: like a big inference.Kyle: ReadingNader: group at a video. I feel so bad every time. I I, he put it on like, on our, he shared it.swyx: One, one ofNader: your guys,swyx: uh, is, is big in that, I forget es han Yeah, yeah,Kyle: es Han's on my team. Actually. Funny. There's a, there's a, there's a employee transfer between us. Han worked for Nater at Brev, and now he, he's on my team.He wasNader: our head of ai. And then, yeah, once we got in, andswyx: because I'm always looking for like, okay, can, can I start at another podcast that only does that thing? Yeah. And, uh, Esan was like, I was trying to like nudge Esan into like, is there something here? I mean, I don't think there's, there's new infant techniques every day.So it's like, it's likeKyle: you would, you would actually be surprised, um, the amount of blog posts you see. And ifswyx: there's a period where it was like, Medusa hydra, what Eagle, like, youKyle: know, now we have new forms of decode, uh, we have new forms of specula, of decoding or new,swyx: what,Kyle: what are youVibhu: excited? And it's exciting when you guys put out something like Tron.‘cause I remember the paper on this Tron three, [00:37:00] uh, the amount of like post train, the on tokens that the GPU rich can just train on. And it, it was a hybrid state space model, right? Yeah.Kyle: It's co-designed for the hardware.Vibhu: Yeah, go design for the hardware. And one of the things was always, you know, the state space models don't scale as well when you do a conversion or whatever the performance.And you guys are like, no, just keep draining. And Nitron shows a lot of that. Yeah.Nader: Also, something cool about Nitron it was released in layers, if you will, very similar to Dynamo. It's, it's, it's essentially it was released as you can, the pre-training, post-training data sets are released. Yeah. The recipes on how to do it are released.The model itself is released. It's full model. You just benefit from us turning on the GPUs. But there are companies like, uh, ServiceNow took the dataset and they trained their own model and we were super excited and like, you know, celebrated that work.ZoomVibhu: different. Zoom is, zoom is CGI, I think, uh, you know, also just to add like a lot of models don't put out based models and if there's that, why is fine tuning not taken off?You know, you can do your own training. Yeah,Kyle: sure.Vibhu: You guys put out based model, I think you put out everything.Nader: I believe I know [00:38:00]swyx: about base. BasicallyVibhu: without baseswyx: basic can be cancelable.Vibhu: Yeah. Base can be cancelable.swyx: Yeah.Vibhu: Safety training.swyx: Did we get a full picture of dymo? I, I don't know if we, what,Nader: what I'd love is you, you mentioned the three axes like break it down of like, you know, what's prefilled decode and like what are the optimizations that we can get with Dynamo?Kyle: Yeah. That, that's, that's, that's a great point. So to summarize on that three axis problem, right, there are three things that determine whether or not something can be done with inference, cost, quality, latency, right? Dynamo is supposed to be there to provide you like the runtime that allows you to pull levers to, you know, mix it up and move around the parade of frontier or the preto surface that determines is this actually possible with inference And AI todayNader: gives you the knobs.Kyle: Yeah, exactly. It gives you the knobs.Disaggregation Prefill vs DecodeKyle: Uh, and one thing that like we, we use a lot in contemporary inference and is, you know, starting to like pick up from, you know, in, in general knowledge is this co concept of disaggregation. So historically. Models would be hosted with a single inference engine. And that inference engine [00:39:00] would ping pong between two phases.There's prefill where you're reading the sequence generating KV cache, which is basically just a set of vectors that represent the sequence. And then using that KV cache to generate new tokens, which is called Decode. And some brilliant researchers across multiple different papers essentially made the realization that if you separate these two phases, you actually gain some benefits.Those benefits are basically a you don't have to worry about step synchronous scheduling. So the way that an inference engine works is you do one step and then you finish it, and then you schedule, you start scheduling the next step there. It's not like fully asynchronous. And the problem with that is you would have, uh, essentially pre-fill and decode are, are actually very different in terms of both their resource requirements and their sometimes their runtime.So you would have like prefill that would like block decode steps because you, you'd still be pre-filing and you couldn't schedule because you know the step has to end. So you remove that scheduling issue and then you also allow you, or you yourself, to like [00:40:00] split the work into two different ki types of pools.So pre-fill typically, and, and this changes as, as model architecture changes. Pre-fill is, right now, compute bound most of the time with the sequence is sufficiently long. It's compute bound. On the decode side because you're doing a full Passover, all the weights and the entire sequence, every time you do a decode step and you're, you don't have the quadratic computation of KV cache, it's usually memory bound because you're retrieving a linear amount of memory and you're doing a linear amount of compute as opposed to prefill where you retrieve a linear amount of memory and then use a quadratic.You know,Nader: it's funny, someone exo Labs did a really cool demo where for the DGX Spark, which has a lot more compute, you can do the pre the compute hungry prefill on a DG X spark and then do the decode on a, on a Mac. Yeah. And soVibhu: that's faster.Nader: Yeah. Yeah.Kyle: So you could, you can do that. You can do machine strat stratification.Nader: Yeah.Kyle: And like with our future generation generations of hardware, we actually announced, like with Reuben, this [00:41:00] new accelerator that is prefilled specific. It's called Reuben, CPX. SoKubernetes Scaling with GroveNader: I have a question when you do the scale out. Yeah. Is scaling out easier with Dynamo? Because when you need a new node, you can dedicate it to either the Prefill or, uh, decode.Kyle: Yeah. So Dynamo actually has like a, a Kubernetes component in it called Grove that allows you to, to do this like crazy scaling specialization. It has like this hot, it's a representation that, I don't wanna go too deep into Kubernetes here, but there was a previous way that you would like launch multi-node work.Uh, it's called Leader Worker Set. It's in the Kubernetes standard, and Leader worker set is great. It served a lot of people super well for a long period of time. But one of the things that it's struggles with is representing a set of cases where you have a multi-node replica that has a pair, right?You know, prefill and decode, or it's not paired, but it has like a second stage that has a ratio that changes over time. And prefill and decode are like two different things as your workload changes, right? The amount of prefill you'll need to do may change. [00:42:00] The amount of decode that you, you'll need to do might change, right?Like, let's say you start getting like insanely long queries, right? That probably means that your prefill scales like harder because you're hitting these, this quadratic scaling growth.swyx: Yeah.And then for listeners, like prefill will be long input. Decode would be long output, for example, right?Kyle: Yeah. So like decode, decode scale. I mean, decode is funny because the amount of tokens that you produce scales with the output length, but the amount of work that you do per step scales with the amount of tokens in the context.swyx: Yes.Kyle: So both scales with the input and the output.swyx: That's true.Kyle: But on the pre-fold view code side, like if.Suddenly, like the amount of work you're doing on the decode side stays about the same or like scales a little bit, and then the prefilled side like jumps up a lot. You actually don't want that ratio to be the same. You want it to change over time. So Dynamo has a set of components that A, tell you how to scale.It tells you how many prefilled workers and decoded workers you, it thinks you should have, and also provides a scheduling API for Kubernetes that allows you to actually represent and affect this scheduling on, on, on your actual [00:43:00] hardware, on your compute infrastructure.Nader: Not gonna lie. I feel a little embarrassed for being proud of my SVG function earlier.swyx: No, itNader: wasreallyKyle: cute. I, Iswyx: likeNader: it's all,swyx: it's all engineering. It's all engineering. Um, that's where I'mKyle: technical.swyx: One thing I'm, I'm kind of just curious about with all with you see at a systems level, everything going on here. Mm-hmm. And we, you know, we're scaling it up in, in multi, in distributed systems.Context Length and Co Designswyx: Um, I think one thing that's like kind of, of the moment right now is people are asking, is there any SOL sort of upper bounds. In terms of like, let's call, just call it context length for one for of a better word, but you can break it down however you like.Nader: Yeah.swyx: I just think like, well, yeah, I mean, like clearly you can engage in hybrid architectures and throw in some state space models in there.All, all you want, but it looks, still looks very attention heavy.Kyle: Yes. Uh, yeah. Long context is attention heavy. I mean, we have these hybrid models, um,swyx: to take and most, most models like cap out at a million contexts and that's it. Yeah. Like for the last two years has been it.Kyle: Yeah. The model hardware context co-design thing that we're seeing these days is actually super [00:44:00] interesting.It's like my, my passion, like my secret side passion. We see models like Kimmy or G-P-T-O-S-S. I'm use these because I, I know specific things about these models. So Kimmy two comes out, right? And it's an interesting model. It's like, like a deep seek style architecture is MLA. It's basically deep seek, scaled like a little bit differently, um, and obviously trained differently as well.But they, they talked about, why they made the design choices for context. Kimmy has more experts, but fewer attention heads, and I believe a slightly smaller attention, uh, like dimension. But I need to remember, I need to check that. Uh, it doesn't matter. But they discussed this actually at length in a blog post on ji, which is like our pu which is like credit puswyx: Yeah.Kyle: Um, in, in China. Chinese red.swyx: Yeah.Kyle: It's, yeah. So it, it's, it's actually an incredible blog post. Uh, like all the mls people in, in, in that, I've seen that on GPU are like very brilliant, but they, they talk about like the creators of Kimi K two [00:45:00] actually like, talked about it on, on, on there in the blog post.And they say, we, we actually did an experiment, right? Attention scales with the number of heads, obviously. Like if you have 64 heads versus 32 heads, you do half the work of attention. You still scale quadratic, but you do half the work. And they made a, a very specific like. Sort of barter in their system, in their architecture, they basically said, Hey, what if we gave it more experts, so we're gonna use more memory capacity.But we keep the amount of activated experts the same. We increase the expert sparsity, so we have fewer experts act. The ratio to of experts activated to number of experts is smaller, and we decrease the number of attention heads.Vibhu: And kind of for context, what the, what we had been seeing was you make models sparser instead.So no one was really touching heads. You're just having, uh,Kyle: well, they, they did, they implicitly made it sparser.Vibhu: Yeah, yeah. For, for Kimmy. They did,Kyle: yes.Vibhu: They also made it sparser. But basically what we were seeing was people were at the level of, okay, there's a sparsity ratio. You want more total parameters, less active, and that's sparsity.[00:46:00]But what you see from papers, like, the labs like moonshot deep seek, they go to the level of, okay, outside of just number of experts, you can also change how many attention heads and less attention layers. More attention. Layers. Layers, yeah. Yes, yes. So, and that's all basically coming back to, just tied together is like hardware model, co-design, which isKyle: hardware model, co model, context, co-design.Vibhu: Yeah.Kyle: Right. Like if you were training a, a model that was like. Really, really short context, uh, or like really is good at super short context tasks. You may like design it in a way such that like you don't care about attention scaling because it hasn't hit that, like the turning point where like the quadratic curve takes over.Nader: How do you consider attention or context as a separate part of the co-design? Like I would imagine hardware or just how I would've thought of it is like hardware model. Co-design would be hardware model context co-designKyle: because the harness and the context that is produced by the harness is a part of the model.Once it's trained in,Vibhu: like even though towards the end you'll do long context, you're not changing architecture through I see. Training. Yeah.Kyle: I mean you can try.swyx: You're saying [00:47:00] everyone's training the harness into the model.Kyle: I would say to some degree, orswyx: there's co-design for harness. I know there's a small amount, but I feel like not everyone has like gone full send on this.Kyle: I think, I think I think it's important to internalize the harness that you think the model will be running. Running into the model.swyx: Yeah. Interesting. Okay. Bash is like the universal harness,Kyle: right? Like I'll, I'll give. An example here, right? I mean, or just like a, like a, it's easy proof, right? If you can train against a harness and you're using that harness for everything, wouldn't you just train with the harness to ensure that you get the best possible quality out of,swyx: Well, the, uh, I, I can provide a counter argument.Yeah, sure. Which is what you wanna provide a generally useful model for other people to plug into their harnesses, right? So if youKyle: Yeah. Harnesses can be open, open source, right?swyx: Yeah. So I mean, that's, that's effectively what's happening with Codex.Kyle: Yeah.swyx: And, but like you may want like a different search tool and then you may have to name it differently or,Nader: I don't know how much people have pushed on this, but can you.Train a model, would it be, have you have people compared training a model for the for the harness versus [00:48:00] like post training forswyx: I think it's the same thing. It's the same thing. It's okay. Just extra post training. INader: see.swyx: And so, I mean, cognition does this course, it does this where you, you just have to like, if your tool is slightly different, um, either force your tool to be like the tool that they train for.Hmm. Or undo their training for their tool and then Oh, that's re retrain. Yeah. It's, it's really annoying and like,Kyle: I would hope that eventually we hit like a certain level of generality with respect to training newswyx: tools. This is not a GI like, it's, this is a really stupid like. Learn my tool b***h.Like, I don't know if, I don't know if I can say that, but like, you know, um, I think what my point kind of is, is that there's, like, I look at slopes of the scaling laws and like, this slope is not working, man. We, we are at a million token con

Javascript is a powerful tool, allowing you to add interactivity and functionality to your site. But did you know that there are certain things you can do to make your JavaScript load faster? You can do this by minifying your code! Minification simply means that you compress the code without changing its functionality. By default, this feature is enabled on all of our servers. Just make sure to enable it yourself if it turns off for some reason. It makes it faster for your visitors to download your script files, because their file sizes are smaller. If you're a WordPress developer, you probably know how important it is to be able to minify your JavaScript files. More info about website's performance, reduce load time and increase search engine ranking. : https://dev.co/minify-javascript/ Connect with us:  https://seo.co/ // https://link.build/ // https://dev.co/ // https://ppc.co/

https://twitter.com/kentcdodds/status/1394420201542668289?s=20 So the other day I tweeted about how I really want people to stop minifying and bundling what they send to NPM. And just to clarify I it's fine if you want to minify and bundle as one of the things you distribute as part of your package, but it shouldn't be the only thing and there are a couple of reasons and what I do for my packages is I actually do have a UMD module that is bundled and I have a minified version of that as well. So we have two of those and then I've got an ESM.R version which is like fake ESM right now eventually I'll get around to making a native VSM supported version. And then a common JS and those are the the four formats that I shipped to NPM. So the reason that I really really don't want people to exclusively ship minified code is even with source maps can it can be really difficult to debug and especially when we're talking about libraries that I'm interacting with well even even transitive dependencies. I like to be able to.Stick a console log in there or to step through with a debugger and it's just really difficult to do that if you've minified your code and in particular what motivated me to tweet this in the first place was I was working with a library that minified everything and it ended up minifying its implementation of an abort signal and so the constructor name was incorrect and node fetch actually checks the constructor name to know if what you've passed is an abort signal which we could argue about whether that's necessary or not, but the fact is that it does and becauseThey were minifying it totally is unusable which is a less super annoying. So that's notification then on the bundling side of things this can get to be a real problem like if for example your bundling a particular library and I'm already using that library in my project MPM can't dedupe that and do means it says, oh you're using this library in this other dependency uses that library too. So we'll just have them both use the same files and therefore we don't have to send.That code to the browser twice so we don't have to require that code and evaluate it in person all that stuff. And so there are arguments that people make about bundling as like performance improvement so like you could do that with some tools and and that could be useful but it could also be a big problem because then I can't like change the versions of the things that I'm using and I don't have any control over that. So there are a lot of issues there in general. So, please don't bundle don't minify it's better this way. Let meDo that.

Video. Here are 5 tips to improve your website’s speed (and boost revenues): Use Astra WordPress theme (lightweight and free) Compress images (use online tools like TinyPNG or TinyJPG) Optimize server (clean the MySQL database, contact web host for help) Minify code (CSS and HTML) Follow Google PageSpeed’s list of suggestions Controversial bonus tips: Don’t … 5 Ways to Improve Website Speed (+ Revenues) Read More »

After 49 Episodes, Mike and Larry get the chance to describe the F.I.R.E. movement and what it means to be financially independent.  They help you figure out your why of F.I. This is a must listen episode. Show transcription: Episode 29 Financial Independence, Retire Early.mp3   [00:00:00] Welcome to the Real Estate Marathon podcast. Your Guide in the Race to Financial Freedom. The Real Estate Investing and Sound Financial Practices. This podcast is for anyone interested in learning more about real estate, investing, personal finances and a new take on traditional retirement. Now here are your host, Larry B0 and Mike Moe.    [00:00:24] What's going on, everybody? Welcome to the Real Estate Marathon podcast. Your guide on the race to financial freedom through real estate investing in sound financial practices. My name is Mike Bell, one of the hosts of the show joined today, as always, Mr. Fisher.    [00:00:39] I'm doing well, Mike. I'm doing very well tonight.    [00:00:41] I know that you're extremely excited because this is an episode that you've been looking forward to for about forty nine episodes, I would think.    [00:00:50] Yes, I am super pumped for this episode. So what are we going to be talking about today, Mike? Well, man, after 50 plus episodes or so, we are finally going to dove deep into the financial independence. What is it? What does it mean? How do you get there? You know, when we started this, you know, we talked about, you know, obviously the name is a real estate marathon podcast for a reason. But when we started this, we talked a lot about, you know, having this be a really good blend of real estate investing and personal finance topics. You know, I think we've we've done a decent job, you know, going over the credit scores, going over a lot of that, you know, setting that strong financials, you know, foundation that we talk about and we delve deep into, you know, a handful of topics around real estate. And now after like I said, after almost 50 plus episodes, we're going to dove deep into financial independence.    [00:01:43] What it means, you know, we're doing five, one on one. So finding independence is one of the posts you put earlier in the podcast on social media was your Wi-Fi.    Larry [00:01:54] Yeah, I like that. And everybody has to have a reason for why they want financial independence. And once you discover that reason, it gives you the motivation to pursue it actively.    Larry [00:02:04] And that's what we're here to do. We're going to define it. And really deep dove into it. So I am surprised you can even sleep last night. We absolutely did.    [00:02:14] I'm omgpop man, and I'm glad we're finally getting around to this. You know, and it's it's a subject that we've we've touched on or it's a term, I should say, that we've used in a ton of episodes.    [00:02:23] So I'm glad we're finally getting to it being given it's a given it the justice it deserves. You really kind of dove deep. So we're going to you know, we're we're going to cover the definition. Obviously, we're in a covered the history of, you know, fights. The basic principle is how did she do it and resources to us to explore more and dove deeper on your own. So it's it's going to be a good episode. And I'm fun. And it's the first time that you and I have gotten to a riff. You're on our own. You know, we've had a ton of interviews, last handful of episodes.    [00:02:50] We haven't that. We've had a solo Soad an hour. It's just us on a topic. So be good to get back to that as well.    [00:02:56] Yeah. Yeah, I enjoy that a lot because I think we we offer a lot of good information, a lot of good material to the listeners and it's great to have the interviewers.    [00:03:06] But one of the things I enjoy hearing the most is my own voice and they have not heard enough of it lately.    [00:03:14] I like hear my own joke. So we'll see if I can throw a few of those in here.    [00:03:17] Oh, yeah, yeah. I loved some bad jokes myself. So. Yes, well, you want to start with the warm up so we can get Guiteau limber and loose ready to run this marathon.    [00:03:27] Let's do it, man. And this is going to be a marathon. It's going to be a get up. So here it is.    [00:03:31] It is. We're talking about the fire movement and fire stands for financial independence.    [00:03:36] Retire early. And the fight the fire movement is essentially the goal of planning for financial independence. So you have the option to retire early or at any time you would like to.    [00:03:48] Yeah. Yeah. It sits exactly what we're talking about today. And, you know, some people get to it kind of thrown off by the R E on that term, you know.    [00:03:58] So people some people like just the they don't like to retire early. Sometimes they retire term gives kind of a negative connotation or you're just gonna be, you know, sitting on the beach and sipping mai tais, which isn't necessarily the case for most people who reach financial independence. But either way, it's exactly, exactly what we're talking about today.    [00:04:18] And I've been known to take some liberties with the army of fire. You know, it could be a financial independence. Retiring is excellent. You know, any any of that kind of thing. Real estate. You know, I take liberties. What it actually does mean the retire early.    [00:04:33] So you know what? Where do you want to start? You know, we're we get really deep dove into it. You want to cover some of the history. Maybe the basic principles of it.    [00:04:43] Well, you know, so let's just expand a little bit more on on fire. So there's a couple of different terms that it can be referred to on a pretty regular basis.    [00:04:51] So fire is probably one of the most common ones which you already defined as that financial independence. Retire early fi or F5, financial independence, financial freedom, the hundred percenters, which is basically means 100 percent of your expenses is covered by passive income. But essentially all these things mean that saying that all mean that you can hundred ten, 11 percent cover your living expenses is with the income that is coming in off your passive portfolio, a passive investments, whatever. Maybe whether it's real estate, whether it's stocks, bonds, whatever your investments is. They all mean the same thing that you made such a cover, your living expenses and your main expenses for life.    [00:05:33] And I'm actually in this position right now with my passive income portfolio, with being able to cover all my expenses.    [00:05:41] I could retire right now and and not lose any ground in my financial livelihood. I guess you could say and this is very freeing. It gives you options. And that's one of the things that people seek is freedom, freedom, freedom. And the FI gives you that freedom. And when we actually in the last few episodes, we've been talking a lot about the financial retirement number, and the number is in an age which we defined in one of the last episodes. It's just a number of how much how many dollars you need to have monthly coming in. So you don't have to work that eight to five or nine to five full time grind the rat race, if you will.    [00:06:24] Yeah. And there you're probably the prime example of why that already doesn't necessarily always apply. So you got that fi- and it's almost like financial independence work optional.    [00:06:33] You're still working. But tomorrow you don't have to. Like that's kind of the options that this gives you. You know, it's kind of like I said, I think a handful of times on this, you know, this this show, I got a you know, a nine-to-five today that they currently enjoy. And I get to do some on energy. And, you know, I'm not one of those people that hates their job day in and day out. Right. But, you know, in five years, I don't know what's going to happen in five years. I think I use this exact term before, you know, my boss could come to me tomorrow and say, you're scrubbing toilets for the next week. You know, obviously in I.T. this could happen, but they could. And I you know, not being at financial independence, what do I do? I guess Guptill is right because I'm dependent on that paycheck right now. So financial independence work optional. You don't have to retire. You don't have to stop working. You don't have to go sit on the beach. But it gives you options. You know, I'm talking to one of these young guys at one of these investment events. The handful of months ago. And he kind of said the same thing is like, I love my job. So why do I care about financial independence?    [00:07:34] Don't care about, you know, that whole movement. It's like, man, things change real quick. And, you know, I think we're in a position right now currently in our current situation that we got going on here, mid 20s, Tony, where a lot of people would be better off. Have they had some, you know, passive income coming in?    [00:07:51] Yeah. Yeah. And you bring up a good point where we are with my my financial independence is it is work optional. And part of the reason, you know, people are saying, why?    [00:08:02] Why should I care about financial independence? I enjoy my 9 to 5. Well, financial independence. What that allows you to do it. It allows you to build wealth twice as fast, because if you've got dual income, you've got the the portfolio income, which is equal to or higher than what your regular paycheck is. And then you got that weekly paycheck coming in. You can actually get to, well, wealthy. You're rich even faster if you take that money and use it is as in investments or however you choose to use it. We choose real estate. But if you have that financial independence. No. On top of your regular income, that's just it's brings a lot of a lot of wealth to bear at your situation.    [00:08:49] So, yeah, it it's it's just a numbers game and it's just taken the numbers and extrapolating. I know, you know, I used to always hear, you know, one of the best things to do was, you know, you know, if you're married, you get two incomes. You should save 100 percent of one person's income and just live off the other one.    [00:09:04] Well, in essence, if you are five or if you build up a portfolio of, you know, whether it be rentals or whether it be stocks or bonds, that provides you enough pass, it could provide, you know, passive income to live on. Well, essentially, you have two incomes. You're just one hundred cent investing one and then you're living off the other. So it's almost doing the same thing, but better because you're building this investment portfolio.    [00:09:26] Yeah. Yeah. And like you said, if if my boss came to me today and said you've got a you've got to clean those toilets, I have the option of saying I really decided I didn't want to do that today.    [00:09:37] Yeah, that's. We'll get to that in the basic principles of fi. That's what we like to lovingly referred to as F-U money.    [00:09:44] F-U money, the toilet principle. And I'm still reeling over you quoting your own term, that thewall Wauchula theWall Financial. Linda Pence's financial independence work optional.    [00:09:56] I like Eminem. Yeah. His trademark that themwho coined to fuel this is a new thewall movement. There's some other other variations of FYE that I want to touch on real quick.    [00:10:08] And that's fact fire and lehne fire. And essentially these are just the, you know, lean fire is you have enough passive income coming in to cover your basic basic basic living expenses. So you can eat. You can. You could. Your mortgage, but you're not living the life you want to. It's not like you're going oh, it's not like you're traveling. You're not living the life even that you're living. Right now, you would have to make some significant cutbacks. But you wouldn't make it right. So that's lean fire. That fire is kind of the opposite. That where it's, you know, you have more than enough to do it. You know, I wouldn't say extravagantly, but you can travel. You can, you know, live above your means that you're even doing now. I'm completely on your passive income. So I moved in last year living large. Right. So I thought fire.    [00:10:53] Fire. I like it. That's that's the way to be. Get enough of that passive income. And there's not really much you you don't necessarily have to live large way. You could if the if the mood struck you.    [00:11:05] Yeah. Exactly. There's a kid. You can take trips or travel or you know, do whatever you wherever you may be. But you're not you're not living like pinching pennies.    [00:11:14] Right.    [00:11:14] So these are as you see with the pictures of the Lamborghinis and the private jets out there, they're definitely fat firing that straight away.    [00:11:21] And it's straight wealth, man. That's that's wealthy for sure. But yeah.    [00:11:26] So we actually move on or you want to dove in and anything else on those, you know, the FatFighters, when I think I think a lot of people are trying to get to the lean fire is when you first achieve financial independence, you have lean fire.    [00:11:40] You don't necessarily have to retire. But you can. And just get by. But like you said, that fat fires, what dual income that I'm working towards right now is.    [00:11:50] Yeah. Yes. But I'll give you a I guess I'll give you an example right now. So, you know, if you're somebody who on a regular day to day basis is living off about, say, let's say six grand a month and you take a look at all your expenses and you realize you can cut out, you know, you can cut your grocery bill, you cut gas down if you know, if you had to.    [00:12:08] And then you could you could live at, say, forty two hundred bucks a month. Your lean fire would be forty two hundred bucks a month. I mean, you could live. You could pay your bills. You wouldn't be you know, you wouldn't be going hungry, yoga, losing your house or going bankrupt.    [00:12:20] So it's very nice in that same example. You know, let's say 10 grand a month. Is that advice? You know, it's well, but beyond that, you know, that six grand that you're accustomed to, you can splurge a little bit on travel alert. You know, what have you per month and you're good to go there.    [00:12:37] And the fat fire, my goal, just so everybody knows, is that taken that month or two off and just just traveling for an entire couple months, you know, that's serious.    [00:12:47] Well, my hope is that fires.    [00:12:50] But we got to go. We've got to get a handful of these people. Oh, there's so many people that take these many retirements that I've listened to where, you know, that worked for three or five years.    [00:12:59] And they'll take six months out because they can because it built this this this machine. And that is their portfolio that can that can, you know, sustain them for more than six months.    [00:13:11] But they'll just do that as a mini retirement so they don't wait until they're, you know, fifty or fifty five years old. And you only need to wait till you're fully, you know, that fire. You can just do it. If you have a if you union fire and you have a little bit of an essay that you're comfortable with it, you take them in your retirement and MBNA.    [00:13:27] Yeah. And one of the terms and I think it was Jack Bosch on his episode said, was that forever cash? You know, it's an excellent concept. I love that forever cash flow out, you know. So you want to jump into the history and file. But where did the word that term get coined?    [00:13:45] Yeah. And we weren't willing to spend too much time here, man. But it did start better. It is known to have started right around in the mid 80s by a couple, Vicki, Robin and Joe Domínguez. They wrote a book.    [00:13:57] They wrote a book, not a bike, pirates' and bikes, but they wrote a book called Your Money Your Life. And the core concepts of this book is that most people go through life unknowingly trading their time for money. So essentially, you guys, everybody, most of the people here, they show up at a job every day and you spend eight, nine, 10 hours at that job and you're essentially trading now or you realize for certain things in your life. Basically, it's a trade off, right?    [00:14:24] Yeah. Yeah. And that's I mean, a lot of people when they and this is how I run my finances, you actually think to yourself when when you're looking to splurge on something or you're trying to decide whether something is in need or want.    [00:14:38] I generally calculate how much time I would have to spend to make the money to pay for that.    [00:14:45] So which is it? That's a great thing to do, man, because when you look at it like that, when you kind of put that that on its head as far as well that 400 at our and that's easy.    [00:14:54] I can I can handle that. I can make those payments. But when you kind of put that on its head and say, well, how many hours your life are you trading for that hour payment, well, then it kind of becomes real. There's a little bit more personal. And I wrote an example here and see if I can get it straight. This is a week or so ago. But so if you think about that 400 car payment, which is not I mean, that's pretty average for people these days, I'd say maybe that's even a little bit on the low end. But 400 bucks a month is your car. If been making bread around the national average of $50000 a year, you know, after taxes, you always gotta come. You know, factory taxes, because when you think about it, you make 50 grand a year. Sure. But you are paying in taxes and all that money. And then when you are buying something like this car, you're also paying taxes on it. So how much you truly walking away with? So let's say after taxes, you are going to forty three hundred bucks a year. So a 40 hour work week say that you work out of 40 hour work week, you're averaging 20 bucks an hour or twenty dollars and 70 cents an hour you're walking away with. It would take you 19 hours. Nineteen point three hours a month to trade for that car. So essentially, you think you work Monday, Tuesday and half of Wednesday and the first week of every month. That is your time that you traded for that car. And when you think about it like that, especially when you start thinking about, you know, this mortgage payment of two, three, four, five thousand dollars a month, you're trading how many hours or weeks or days year your life for that essentially every month. And when it adds up, you want to make sure that you're trading your time for things that actually mattered and helps put things in perspective a little bit.    [00:16:29] It does. It does. In one of the things I kind of throw a little bit of a subjective part of that as well. You know, I look at it like, do I buy a car that gives me nineteen point three, two hours worth of enjoyment for that?    [00:16:43] Because it's it's a input output kind of thing. So I'm putting my nineteen point three, two hours. But if I get 50 hours worth of enjoyment on my will, say like a Corbat or whatever I decided to buy, it becomes worth it. But if if you're buying, you know, I don't know what kind of little tiny, you know, card doesn't go very fast and you get maybe an hour and a half of enjoyment. And it's just for getting you back and forth to work. Then, you know, it might not be a tradeoff, but you definitely do need a car.    [00:17:16] So, yeah. But so you bring up a good point that in the whole I think the whole reasoning behind looking at it like this is it's looking at what am I spending money on? And does it truly bring value to be it like I am not a frugal person. So that's why I went at a time when we talk about budgeting, when we talk about debt. Like I see those cars. I'm like, yeah, I want that. So, like, I have to look at that and say, does that. Is that worth trading my time for it? And some of it does splurging on those nice things. It's worth it to me. And some of it isn't. And that's that's why looking at it and taking a true look at your expenses and you're spending. I was able to cut a bunch of expenses just by, you know, in hindsight thinking of how much value I got out of those expenses and shift those into the things that I actually got value. I think that's the power I find that really makes you look at where's your money going and does it align with your values and what you find beneficial and you like you enjoy, you know, getting time and spending time on those things that you spend your money on.    [00:18:17] And I think this is a good time for the credit score. KING To jump on a different side note, you know that that example you had would cost you nineteen point three, two hours a month.    [00:18:28] Imagine if you had like a four hundred credit score that could number could easily jump to 30 hours or 30 hours a month and you're paying more for your credit. So, you know, the higher your credit score, the lower the amount of hours that you have to cover purchases. So, yeah.    [00:18:46] And you know what I like about the credit score. And you know that I don't like the credit score very much. But I do like the credit score.    [00:18:52] The fact that you can you can maintain and you can you can get a good credit score without spending a lot of money. Like I always feel people and you know, you've heard my complaints about the credit score that I don't think it's a very good indication of how financial savvy you charge because you're able to borrow a bunch of money and pay it back. And that doesn't mean you're good with your money, but you can do it without spending money. And you can you can build that up without going and racking it into debt. Like like we talked about, you can get a credit card and you can put your you know, if you're smart about it, you can just put your next year and your money that you would have spent anyways on that card to get those points into build up that credit and not go into more debt than you weren't expecting to. Yeah.    [00:19:35] And that's definitely another benefit. So but it looks like you have listed a few few different resources to help people deal with FI. I mean, the first one you've got listed here is the Mr. Money Mustache Blog 2011 net. Yeah. Yeah.    [00:19:51] So we went we went a little off track of the history. You know, it started with Vicki Robin and Joe Dominguez with that book, Your Money, Your Life. And then it really exploded. 2011/2012 with with the blog that you you mentioned, Mr. Money Mustache. It's a lot of people's kind of first foray into, you know, financial independence or what it might actually mean to, you know, go this unconventional route and be able to retire early. So there's an article that was one of his most famous one that's called The Shockingly Simple Math Behind Early Retirement, which we linked to here and we can link to in the show notes. It breaks down in a unbelievably easy way to understand how you can retire at 30, at 35, at 40 if you truly want to. It kind of breaks down that it is just a numbers game and makes it super easy for people to comprehend.    [00:20:45] Retirement just. Well, math problem. And yeah, you know, math and realize it tells you exactly what you need how to get there.    [00:20:53] And once you get there, the numbers work out. It's it's glorious. People lie.    [00:20:58] Numbers don't lie.    [00:21:01] That's how it goes. So, yeah.    [00:21:03] If you guys haven't heard Mr. Money Mustache, you know, he bragged he was one of the really the pioneers of bringing, you know, the financial independence, financial freedom fighter or whatever the heck you want to call it to a little bit more of a mainstream with his blog. And then there's a handful of other ones that choose F choose F, I guess, which is phenomenal podcasts. They also got a book I A Blueprint to Financial Independence. Remember correctly. And then the bigger pockets, money, podcasts. All of these are really the core players in the financial independence education sector. I would say, you know, out there and have done a ton of bringing all these principles and these concepts to the mainstream.    [00:21:44] Yeah. And the nice thing about all these blogs and podcasts is they basically put a put a term and a face on what I was already doing.    [00:21:54] It took me 15 years to get to the point where I was financially secure and and had my credit score and everything fixed. And I started listening to these guys. I'm like, you know, why are you do that? And I didn't realize there was a rule to cover it.    [00:22:08] This is what, you know, you'll be even before where obviously this guy really popular in 2011, 2012 started to take off. You know, obviously there are people doing it and practicing this. But I think what you know, what that goes to say is there are still ways that you can even improve even further. There's not a lot of these are just minor, minor tweaks that over the long run really, really, really make a difference to these different like tax strategies that these different savings tactics and things like air investment strategies that really they seem I knew in the in the in the real time here, but, you know, expand that over a five or seven or eight year investing term. And the numbers show how much of a difference this can make. And it is really tactical ways about going about your finances.    [00:22:59] And once you start getting getting a handle on everything, it generally falls into place. You have to you have to get this stuff set the the basics before you can run, you know, when and where you can run.    [00:23:12] Yeah, 100 percent.    [00:23:13] And there is there's almost these different levels of as you kind of dove down into the financial independence rabbit hole, there's these different levels of, I guess, educate educators and a levels of education. So if you think about, you know, Dave Ramsey is one that I know a lot of people mention in is a is one that I started out with. You know, I started out listening to it. You know, it kind of led me to the next one, the next one to the next one. And Dave Ramsey, you'll see a lot of people in the financial independence community, starting with Dave Ramsey. He's got super good principles. He teaches a lot of the basic money concepts. But when you look at it, some of it is just too black-And-White. Like he's got this like, you know, you hate debt. Right. Like, he just absolutely can can't stand debt and says you shouldn't buy real estate unless unless you can buy a cash, which I mean, and leverage is one of the amazing tools of real estate and amazing tools and investments if done right. So I think you'll find people start with like the Dave Ramsey or some of the other basics and then graduate once they learn those. They kind of. They graduate to some other concepts of different educators and the financial independence world.    [00:24:25] Now, I see Dave Ramsey as being the person that gives you a healthy respect for the power that the negative aspects of debt. And then once you learn to have a healthy respect for debt and you use it wisely, then a debt can be a huge tool in your tool belt.    [00:24:41] Yeah. And let's be honest, like you think about like you listen to the Dave Ramsey podcast and you listen to the people that call in. You know, he's got these millionaires that call in and it'll work.    [00:24:51] If you want to. And believe me, I was on this train at first. You know, when I when I started listening to this and when I started getting into this movement, you know, worked twenty five years and spend your super frugal and don't spend a lot of money and save as much as you can into mutual funds. And in twenty five years, you'll be a millionaire.    [00:25:09] That will work. One hundred percent that will work. The problem is, I don't want to do it in twenty five years. I don't want to do it in like five years. So there are others tactics and other strategies for it. You know, those goals. So it all comes back to that. So it's a it's a good start. But then I think people kind of graduate from there.    [00:25:27] Yeah. Twenty five years is a very long time to get to be a millionaire. Bye bye. Yeah. Scrimping and saving pennies and things.    [00:25:35] Yeah. And it's like I don't want to pinch pennies or twenty five years.    [00:25:38] I just want to do the same page with that, Mike. You know, it's a lot of things I don't want to work for sixty five years. For ten years of fun before. That it has a way.    [00:25:48] So that's why we're here trying to help as many people as we can to get that. Get the heck. Yeah. 25 year millionaire do it.    [00:25:56] I mean, there's studies. I mean, obviously. So a lot of the financial independence blogs, podcasts, things like that. It all depends on your savings rate, which we'll talk about in a little bit here. But there are case studies, people doing it in two or three years as case studies of people doing it in nine or 10 years. I think on average, people can get to this five point anywhere from five to 10 years, depending on how much you make, depending on your savings rate and really depending on how crazy are about it. You know, some people don't mind being super, super frugal and cutting back down to the bare bone and saving, you know, 60 percent, 70 percent or 80 percent of income. Other people, you know, totally cool will do 20, 30 percent and just add a couple years under, you know, the time it take you to get there. And either approach is fine. It's just kind of what fits you type thing.    [00:26:43] I tell everybody, you took me forty nine years to get to financial independence. It was forty seven years of trial and error. And I wasn't doing that correctly.    [00:26:53] Yeah.    [00:26:53] And so if you can take that and if you can use some of that education that's out there, you know, just so much education out there, you might go to cut down that learning curve more.    [00:27:04] Yeah. I'm hoping to condense my forty seven years of trial and error and help these folks in in listening to the podcast do it in a couple years, so.    [00:27:12] Oh, my gosh. Yeah. Man, you. Yeah. I can't even tell you how many resources are out there, podcasts and books. And, you know, obviously that's that can be an issue, too, because it's almost overwhelming how much stuff is out there.    [00:27:25] And it's just it's like it's just like the health industry and some of the stuff contradict each other. Some of the you know, this this guru says X and Scooter says Y. And there's really no easy way to navigate that other than you've got a headache. Go out there and explore and take what works for you and discard the rest and keep keep going and figure out what works for you.    [00:27:45] So, you know, and you guys are all listening to my favorite podcast resource. So keep that up with that.    [00:27:54] The real estate marathon is my favorite resource. That's right. It's a dad joke. So a lot of people miss him.    [00:28:05] So you can jump into the basic five principles and rules of thumb.    [00:28:09] Yeah. Let's do it.    [00:28:10] So the 4 percent rule, the 4 percent rule is essentially you need a hammer. So essentially you 4 percent of your nest egg you can live on essentially forever. So if you have a million dollars, you take out 4 percent of that. That's what, $40000. Right. So you could essentially take out four percent of that million dollars. And there is a 97 percent chance, likelihood that that principle will last or that that nest egg will last forever. It's based on what the called the Trinity studies, which is this massive study of basically of what you can take out and with based on the returns in the whole other factors, the likelihood of it lasting forever, essentially. You never having it touch that principle. So based on that, the four percent rule, it's kind of been this rule of thumb being, you know, once you reach that's that 4 percent rule, you're essentially for. So my expenses are $40000 a year or, you know, adjusted for taxes. Then you're a little over a million dollars nest egg. If I'm doing stocks or bonds or whatever that it's that stock portfolio, then that would be your number.    [00:29:22] Yeah. And as everybody knows, it's one of the one of the fears of people that they're they're going to outlive their money. And that's not a good retirement. If you end up having enough money to cover five years and you live, you know, twenty five years of retirement, you're you're broke in five years. Then what do you do?    [00:29:40] Yeah. Right. Yep. The other way to do it is just take your expenses that you need. So if you need $40000 a year to live. Times it by twenty five. It's the same thing, but it's just like anything. It's a rule of thumb. So it does not. You know, there are there are more conservative folks out there who might who would say it's probably more like three and a half percent and would also say that it largely depends on what happens in the market. The first handful of years, if you were Tirina, because you you know, if you're a tired day one and you start drying on your portfolio in the market immediately takes a dove, say 20 percent, I don't know. Like it just didn't stop 25 percent, then that way you can't take that 4 percent off that original balance. You have to then adjust for what the principle is. Sorry. What's your your total portfolio is and take 4 percent off that new. Right. Right. So in sequence return risk essentially is what they refer to. That is what it is a good rule of thumb, at least while you're traveling on the road to fi and as you're trying to. The goal to shoot for is that 4 percent rule.    [00:30:49] Yep, yep. And then the next thing you've got there is the savings rate. Now, that's the amount of savings that you need to retire. Financial independence, is that what that means?    [00:31:00] No, it's it's essentially. What percentage of your income are you saving today? So if you're making said one hundred thousand dollars a year and you're saving ten thousand dollars a year, whether it be to invest in stocks or to invest in real estate, you know, your savings rate is 10 percent.    [00:31:17] We've talked on the show a few times where we think, you know, in normal in a society, you hear about somebody saving 10 percent of their income and they get that boy.    [00:31:26] And everybody is super pumped in the firewall world. You know, it's more like 40 or 50 percent. It is usually the average. People are saving upwards of 40, 50, 60, sometimes 70, 80 percent of their income just in investing that tire on it that they're saving and then just living on that 10 or 20 or 30 percent of their income. You know, that's a little bit extreme depending on how much money you make. But I think 50 percent is kind of that that nice balance, at least in my my perspective.    [00:31:55] To get to from a savings rate on the savings rate, like you said, if you can save 50 percent.    [00:32:00] That's where for me personally with the portfolio, that's where my portfolio comes in because I make as much in my portfolios as my wife and I do working full time. So we we live off of our full time income and then basically save 50 percent of our income, which is the portfolio income. We put that right in the savings. So that's going to help effectively get us to being millionaire status a lot sooner.    [00:32:25] So you're essentially saving a 100 percent and you're able to 100 percent of your working income. You were able to save because of that, because of that rental income that you had coming in.    [00:32:36] Yeah. And then once we get to a level where we can invest even more into another expanding their portfolio, another duplex or try to flekser multifamily, then that just keeps increasing the amount. So at some point we're going to be saving 200 percent of our of our income.    [00:32:54] Yeah. Yeah, exactly. And definitely powerful, powerful, powerful thing.    [00:32:59] Now, what's this next item on their mind? Inefficiencies in taxes, spending and investments wasn't necessarily like a rule of thumb.    [00:33:07] This is more of a kind of a general guiding principle.    [00:33:10] You know, when you get into it, like I said with earlier, with the Dave Ramsey is the world has got really super good basic basic financial literacy. Right. That's the foundation. And then financial the five principles, the fire principles typically are a level up from that.    [00:33:29] And they they a lot of times all kinds of shit like that on those minor, minor efficiency's that really make a big difference in the end. A lot of my around taxes.    [00:33:39] So how can you max out your tax tax deferred savings, things like your phone fallen case, things like HSA or MAX, maximize tax benefits, do things like real estate.    [00:33:51] And then on the I guess on the withdrawal, you know, maximizing your tax burden by doing things like Rothenberg's and Ladders. You make it backdoor Roth contributions and things like that.    [00:34:03] Now, these are kind of more advanced financial principles that you can look into and get details on, but it really comes down to expanding or making those those improvements on the margins. So, you know, you got your basics and then fight typically goes above and beyond. And it makes those minor adjustments, like you said, seem minor, but make a huge difference in the this category.    [00:34:28] Here is it reminds me of the saying that somebody I heard a long time ago and I don't remember where I heard it's from.    [00:34:34] Are we going to I'm probably gonna busher. It might have been Robert Kiyosaki and rich dad. Poor dad. But he said it's not about how much money you make, it's about how much money you keep. Yeah, and that actually plays right into the efficiency's in tax. And his taxes and spending because you you actually if you can reduce your spending and reduce your tax burden, you're going to be able to keep more of your money regardless of how much money you make. You can use that to get to be millionaire status or even, you know, even if you're just shooting for fi doesn't necessarily have to be millionaire status. But you know that personally is what I'm shooting for.    [00:35:08] Yeah. I mean, when you eat it makes it so, so worth it to dove into this and figure out how you can how you can truly make get the most bang for your buck. You know, somebody wants that. And again, it's kind of the same thing you just said as a quote there somewhere. I can't remember who said as I apologize, I'm not giving credit.    [00:35:25] But there's one line in the tax code that says you have to pay taxes on all your income. And then there's like thirty thousand lines in the tax code that gives you loopholes to not pay taxes on your income. So, you know, you say what you will about the wealth, the avoiding taxes, but they use the tax code to their benefit.    [00:35:43] You know, if you could do the same. Should so figure out where you can save or where you can reduce your tax burden. Get yourself educated so you can you can get your goals a lot faster and keep more of your money that you make.    [00:35:57] Yeah. Yeah, that's and that's actually a very powerful thing. Thirty thousand versus 1. So. Yeah, and how but when.    [00:36:03] And that's only one thing that says you got to pay out pay taxes.    [00:36:07] Every other line in the tax code is loopholes on how to not pay taxes. So why the heck once you take advantage of that as a real estate man, as you and I know the tax the tax benefits from owning real estate. Q Huge, huge. You know, there's there's doctors and lawyers who dumped some money into real estate, you know, not even caring about the performance just because it can completely simply wipe out a lot of their tax liability and all the income limit.    [00:36:33] So, yeah. And if you it's hard to tax season, you're now investing in real estate, right?    [00:36:40] Yeah. I don't look forward to tax season because of the paperwork, but I do. I'm with you.    [00:36:44] I'm a numbers guy. I'll sit there all day and add my wealth.    [00:36:48] That's probably a whole another whole topic around. Don't wait until last minute to do your tax paperwork, your expenses for your business and stuff like like I sometimes might have said that 48 hour I called the 48 hour tax marathon that you don't really know of.    [00:37:05] All right. Now, I'm curious, this one I I've heard the term before, but I've never really delved too far into it. What exactly are you meaning by stealth wealth, stealth wealth, mail.    [00:37:16] This is a millionaire next door and this is it. This is those people who can essentially buy your Tesla with cash if they wanted to. But don't they choose? Not that they choose to drive a five or six year old Camry or Kearl or whatever, you know, whatever your car choices. But the point is, is that they could spend a ton of money. And they're very, very wealthy, but they don't because they spend money on what they value and because they they've been able to get their wealth by not spending things on flashy things that don't make sense. So the stealth wealth community is one that that is they're they're interesting bunch, but essentially they're bunch of millionaires. You don't look like millionaires. They look like your average person who looks like your average working class person.    [00:38:00] So these are the folks that you see every now and then.    [00:38:03] You read an article about it where people say they were surprised that they were able to leave a 10 million dollar endowment fund to their college. Right. You know, they passed away. They left all this money and everybody's like they were just normal people. They cut coupons and they did, you know, they did whatever they had to do. And nobody knew that they were millionaires.    [00:38:22] Yeah. Yep, exactly. And I got to I mean, I got a I won't say I'm might with this camp, like I completely understand and respect the selfless community in a. Who's the guy who is a millionaire next door. Can't remember the name of that book. Yeah. Cameron. It's because I'm. I know I like my Teslas. I like my flashy stuff. But no, it's it's totally it's definitely a movement out there in a community out there that is very proud of what they do and the more power to them.    [00:38:53] And I clearly like my camper and my Corvette that I'm looking to try and have fun. Let me buy.    [00:39:00] Yeah, but it's the spending money on what makes it what makes you happy. It will make sense for you.    [00:39:05] Yeah. Well, and I was telling somebody that I'm trying to talk my way for.    [00:39:09] No, let me get a Corvette. Nice. We were playing a chess game of this, trying to get this Corvette out of the dealership and you'd be surprised if you start beating your wife in a chess game of getting the Corvette dealership, how quickly it turns into hardball playing hardball.    [00:39:25] So it was a firm. No, after that. So what you got to do, man, you just need to buy a pickup, one more property and half your tenants pay for your Corvette. One of the that thing and like five, six, seven hundred bucks a month, all you gotta do is find a couple of properties, a cash flow that ammo and go right there.    [00:39:42] I actually already I already started with that argument, had the properties all picked out and everything so nice to the network. But that's that my friend is is that is a principle.    [00:39:55] It wasn't a key Sakhi thing was that we're okay. So essentially have your your assets paid for your liabilities. Huge. Huge. Basic principle of investing. Right. So if you base if you want that Corvette, don't go work your 9 to 5 and use your your after tax dollars to buy that Corvette. And B car poor essentially. Right. Go buy an asset that pays you that amount of money and then that funds your fund, that buys your Corvette. You know what happens when that Corvette is paid off in five years? Your assets still paying you money and you still have that.    [00:40:33] So you go from having a Corvette bought for you to get in the race. Exactly. Or something else. Gomez, I got something else in mind. Let's say your assets paid for your liabilities when I had never. Have a lack of imagination. So I think of it. You. And the next term, they're the next principal, the F-U money. It's my fast favorite f you money, financial university money.    [00:41:00] That's why they say using your son. No, we won't. Because we we check that little box that says we're, you know, a clean, family friendly episode for our right as listeners. We want one explain this one too much and do so. But this is kind of the point before Lehne Fi that you have if enough money where if that boss comes in and says, look, you scrubbing toilets for the next six months because a sorry, that doesn't work for me. What a it changes the game. It changes the perspective that you can.    [00:41:28] You're in a position of power.    [00:41:29] You know, there's so many people who have written about this and about how they've enabled to, you know, after they got into this step, may have had the courage to go negotiate with their employer for a better work life balance or for more money for a better position, because just worried about where the employer says yesterday. Because you have that money that you can say, well, you know, that doesn't work for me. I respectfully decline and see you later because you have that money, whether it's six to eight to nine months expenses or, you know, the exact dollar amount is all personal. But it's whatever that that amount of money that you feel comfortable living off of for space with, you don't have a job.    [00:42:07] Yeah. I call this the forget your money because you get you and your money. Because when I leave work, I'm going to forget all about you because I can afford to live a mile.    [00:42:18] This is the type of money in the situations that we are in right now.    [00:42:22] Like I said, we're recording this March, April 20, when you get this little thing called COBRA 19 going on right now. And it's causing a lot of anxiety with people like we've talked about before, a lot of people don't have that for on their books that that stat that they say, you know, most Americans can't take a $400 expense without diving into credit or, you know, dip in it, you know, borrowing the money. What happens right now when hundreds and hundreds of millions of people are getting laid off from their job are now uncertain? You know, this isn't necessarily the F you money, but that same type of money that concept comes in where, you know, if you lose your job, can you survive for six, eight months with expenses? You have that rainy day fund built up. And I think, you know, I hope, you know, people who don't use this as an opportunity to realize how important it is and how much much stress that could take off. Yeah.    [00:43:16] Yeah. And it's times like this when I'm I'm glad we're able to save one hundred percent of our income through the portfolio, because that's just. Money will fall back on. So I can sit here and talk to you with the podcast without worrying. Yeah.    [00:43:32] Yeah. It's. That's that's a rare situation to be in.    [00:43:36] And I found I think it's a it's it's a good one man and I think this hopefully will well implore people to start looking at their finances and start looking at some alternative options, you know, saving the 10 percent. We'll get you there in 30 years, probably.    [00:43:52] But, you know, you really got to make some more aggressive moves in order to to get there any sooner. Really? To to put yourself in a better spot.    [00:44:01] Yeah. Well, next is the burning question that I have for you, Mike. How do you cheat, achieve my financial independence? How do you go about doing that?    [00:44:10] Well, this is kind of a loaded question, because it's it's it's a little tongue in cheek because it's kind of like, how do you be successful? There's a, I don't know, a million different ways that you could you could chuck an answer out for that. There's probably gonna be new ways invented every day and height, yet there is kind of the same thing as five, but the basics of fi are the same, which I think we've covered a couple times on this on this show in various episodes. Here's what you spend, you know, whatever you spend, and then here's what you make, whatever you makes it take, whatever you make, minus what you spend. And the point is, Tate, that needs to be as big as a number as possible and wisely invest the difference. So if I make $5000 a month and I spend $3000 a month, I get two thousand dollars surplus that I can invest in wisely with over a long period of time. The point is, the fastest way to achieve high is widening that gap, lowering those expenses, increasing that income, whichever you want to focus on, both want to focus on one either way, widening that gap and then wisely investing that difference over time consistently. So maybe you get A's and you go up to seven grand a month and maybe cut your expenses back a little bit more. But on twenty five months, it's just widening that gap and being smart with the difference.    [00:45:31] Yeah. And it's it's not rocket science. It's just a math problem. Yeah. You want to get there? The solution would be the biggest number you can and it's a subtraction problem.    [00:45:41] So you want the left side of it to be as big as possible. And the. Right side of it to be as little as possible.    [00:45:47] Yeah. And you know, it's comes down to it's not not sexy. There's a thousand different ways to do it. I mean, you could literally do that and just throw it in stocks that, you know, index funds, whatever you may.    [00:45:57] And you'll get there, you know, in the past. And the more you save the bad, you'll get there. You could put it in real estate and you can, in some people's opinion, get there faster. Like like what we think. But it's just making that that gap as big as possible and then investing in that that the difference. Wisely and then taking advantage of the margins or taking advantage of your tax.    [00:46:18] You're you're more strategic tax. Either ways to go about reducing your tax burden in reducing your fees on your at your best friend strategy and things like that. It's a bunch of different ways that you can you can kind of optimize at the margins, as I say, with with some of those more those higher rate, not higher those more advanced strategies.    [00:46:43] Yeah. Your your tax strategy planning is something that you really need to look at probably before you need it.    [00:46:53] I mean, you should start planning way early because if you get to tax season and you think to yourself, I could've used another three or four, ten thousand dollars and deductions all, it's too late at that point because every first or last years when you should have been planning that unless you're a corporation, then you may have may go a different calendar year.    [00:47:14] But for the most part, for you privately, the thirty first of December is the last time we get a chance to do it short of maybe investing in an I.R.A. and that's a..    [00:47:24] And even if you do it, it you know, even if you do it at the very end of the year, there's so much there's not as much as you can do.    [00:47:30] You want it like going to you with a really good tax strategists who will say, you know, throughout the year hear the different things, they should do it. Here's the investments you should do to reduce your tax burden. I guess taxes, I think there's a really daunting, early, intimidated people. And I know that I felt that same way when I started looking into it. But really, it's really amazing how you can use some of these strategies to reduce the taxes that you pay to you in the end.    [00:47:56] In the end of this, you know, especially some of these tax advantaged accounts that you can invest through. It's just it's really remarkable once you start diving into it.    [00:48:05] So as it is and I know investors that use their their portfolios to pay for every aspect of their life and a lot of it legally can be written off. You know, it's just the tax the tax advantages, real estate are just limitless.    [00:48:24] Yeah.    [00:48:24] And even if, you know, in real estate, you still want to be smart about your taxes and you still want to figure out, you know, what can you invest in that reduces your taxable income? What are different ways that you reduce your taxable income? So you're you're keeping most your money now.    [00:48:39] Now, if I want to learn more than then, just as a podcast, what do you think we should do? I notice you got a list of some books here.    [00:48:48] Do it. Yeah. And there is no shortage of them. And I I didn't even know.    [00:48:52] I almost didn't want to make the list because I mean, you're inevitably going to leave some of the big hitters and the key ones off. But I think it give us it makes sense to to the people at least some place to start if they want to dig in more. So, I mean, we've got a bunch on the list now. We've got Rich Dad poured out of it by Robert Kiyosaki, which I think is I mean, bar none. It is one of the biggest ones that always gets brought up. When you talk to people about, you know, what changed your mind would change your life, your financial trajectory.    [00:49:21] And a lot of people refer back to the rich dad for that book from Robert Kiyosaki.    [00:49:25] And that changed my life when I read it, because it makes you look at a different way, your finances. What exactly an asset is.    [00:49:34] He's defines assets a lot differently than we've been taught through school and through our parents. And it's definitely worth a read. And I've noticed like I bought twenty five thirty copies of Rich and Poor that they were they were on sale going on and I'll hand it out to people one. And the funny thing is I say it either resonates with you and you go and buy every one of his books and read read voraciously or you just don't get. You just don't like it or doesn't. Does that strike a chord with you? So, I mean, it's it's 50 50. You know, you can either be something that's going to change your life or you just go, what's the what's the all the hype about?    [00:50:13] And I think more often than not, people are all right. It's definitely on the former of those two because it's time and, you know, it's time tested. It's one of the most popular personal finance books ever written. When was it written? Early 90s. Maybe it's been off for lying is a long time and it's always been at the top of the list for personal finance. So it's definitely a time tested bestseller for sure. And then, you know, I'm going to skip around a little bit. Maybe a little maybe a little bit of a out there statement, but I think the rich and poor that of our generation is the book by Scott Trenchcoats set for your set for life.    [00:50:55] And this is one tenth of what you mentioned on buying 30 copies and given it out. I think this people need to buy these for any graduating senior from high school. Anybody graduate college? Any any young adult could benefit massively by the principles that are taught in this book. Set for life by a trash.    [00:51:17] Yeah, yeah, definitely. You know, your money or your life. Vicki, Robin and Joe, you you basically touched on that and started the fire more.    [00:51:26] My back in the 90s are back in the 80s, actually. So that was that was pre, you know, the kind of computer stuff we got going on now. Pre technology, man. No, everybody checks and everything back then.    [00:51:41] Yeah. Back in the ghetto there's the good old days.    [00:51:43] The good old days. You know we were riding around in horse and buggy easier, you know, the wagon trains.    [00:51:51] But you know and J.L. Collins with the simple path to wealth. And one of my personal favorites is The Honeybee by Jake Stand's Piano and Geno Barbaro. We yeah. Podcast episode with those guys on that. And it just touched on basically how to create the multiple streams of income, which is so powerful in the world today.    [00:52:13] Yeah. You know, I love this one because it breaks down these principles in such the easy way, easy to understand way. So it's that's the honeybee. Baiji extends the unknown. You know, Barbara, we didn't like you said, we didn't interview with a handful of episodes back. Memorable what episode number that was. Twenty, twenty, episode 20. About creating multiple streams of income. Yeah. Easy, easy. Read another one that should definitely be handed out set to anybody who is interested in learning more about this. Definitely be a life changer. So yeah.    [00:52:45] And then we've got some some blogs and some podcasts.    [00:52:49] Yeah. Yeah. We'll just run down the list is what is we're getting kind along here. But from a podcast perspective, you know, choose f I mean those guys do a phenomenal job of going over.    [00:53:00] I mean they're on a couple hundred episodes now, but you can go back all the way to the beginnings and listen to a lot of the basics around financial independence and kind of follow along with their journey. Mad faintest. This guy is, if you like, numbers. This is the dude to talk to. Here he writes some of these articles. It's a little bit harder to follow. I would say. But it is numbers, numbers, numbers. He is a guy who's reading these thirty thousand lines, the tax code, figuring out how to best take advantage of it. And it gives these case studies of how he's done a lot of the things he's talked about. So Mad Scientist is a good podcast and blog to talk about as well. Bigger pockets, money, I guess, is another good one. And then Dave Ramsey, MINIFY podcast. It's got a lot of really, really good basic financial literacy.    [00:53:47] Yeah. You know, I started reading the tax code, too. I think I'm on line five or seven, something like that. You get a little bit of it. Yeah. Well we take it in fits and spurts. So they go on the blogs. Mr. Money Mustache.    [00:54:05] I follow his blog, The Financial Samurai. Those. Yeah. Yeah. That's a great one. I love that one. And the physician on fire. That's. Yup. You know, they're all great blogs. They give you a ton of information. So you should check those out.    [00:54:20] And this is just a starting point. Like I said, it was I was debating on whether or not we'd make a list here because, you know, this so many people in the space right now.    [00:54:27] So many people in this area that inevitably leave some of the really, really good ones out. But, you know, you're linked to you jump from one to the other to the other to the other other end by timing. I mean, we are one that you've never heard of before. But Scott, you know, they all got good information out there now.    [00:54:45] Yeah. And the last thing we got there is our Wi-Fi. Mike, that's what motivates you and I.    [00:54:53] Yeah. I think this is important.    [00:54:55] Not necessarily that anybody cares about our Wi-Fi, but it's important to have Wi-Fi in it. It's kind of fun to say, but like, why do you want financial independence? Why do you want freedom? What do you do in it for a nine? If you if you have that, then these some of these concepts, these things that you had to sacrifice, because let's be honest, it be a lot easier. Just go rack up credit card debt and go, you know, go, you know, live the life you want. Go travel and go party and buy the fancy cars when you can't afford it versus waiting, you know, a handful years till you can. But see, if you're making similar sacrifices now, it's it's easier to do so if you have a Y.    [00:55:38] Yeah. Yeah. And like you said, there are options and freedom. That's one of the big ones.    [00:55:44] Seems to be a running theme options, man. It's literally all about options, like when his options ever been a bad thing.    [00:55:52] Never. Never.    [00:55:53] You know, it's, you know, no idea what's what's going to happen in five to seven or eight years or even two years. So like you options and you can kind of control more of it.    [00:56:04] I do know one instance where option too many options are a bad thing. Let's hear it. Starbucks. I mean, I love Starbucks, but come on. You know that. Let's go back to decaf and regular.    [00:56:17] No, man, I like my fancy coffee mcare. But coffee, though, you know, being from Minnesota. That's kind of my my my thing there. But you know, Amanda. Yeah. We posted a while back on Instagram.    [00:56:30] And we're like, what's your Wi-Fi? And, you know, I originally because it was what I was doing at the time, as you know, because books and a/c and the deck was, you know, shouldn't just be for Saturday ability to do that. You know, any day that week. Right. Is we want to spend more time with you. You know, the people in you know, the things that you love to do. So, yeah, you know, I never was.    [00:56:52] Well, I mean, that's that short of doing the call to action. You know, I got the cool down.    [00:56:58] You want to do kind of a quick recap and I do.    [00:57:03] Let's see if we can if we can recap this. We covered a lot. I think we're we're a little over an hour, you know, some outlets yourself.    [00:57:09] Arsalan, final good byes today. I literally cannot wrap it up with my options. Options are good.    [00:57:21] Let's call that action that way. Issue we get the Wi-Fi like figure out what's your Wi-Fi has made sure that.    [00:57:26] Yeah, it's well understood and well documented. Why you're traveling down this path. That is a little bit unconventional. It might might be a little bit more difficult in your in your daily life than your average life.    [00:57:41] And I think you should write it down and put it like on your bathroom mirror or some place you're gonna see it every single day. And remind yourself what you're working so hard.    [00:57:48] George, techie Asian apps to keep that front center. Now, so while that's everything I got, all I got in my moments, I wrap her up. Thank you, guys. We've seen another episode of the Real Estate Marathon podcast and we'll see you next time. Take care, guys.    [00:58:07] Thanks for listening to the Real Estate Marathon podcast. If you found value in any of the content from this show, consider supporting us in the following ways. Subscribe to the Real Estate Marathon podcast. Leave a rating and review. Continue the conversation with like minded individuals on social media by heading over to the real estate marathon podcast Facebook Group or follow us on Instagram and Twitter at Real Estate Marathon podcast. 

Pete Shearer (aka Pete on Software) is building with React and Redux. Show Notes: Redux-synapse React SPA - Single Page Application XML literals in VB.NET StackOverflow thread about Virtual DOM & React Redux Redux has bindings for Angular, Vue, and Aurelia Flux MobX Ember, Backbone, Knockout, jQuery Some concepts you'll need to learn React: NPM, Webpack, Minify, Lint Create-react-app Web Bos - React for Beginners Steven Grider - Modern React with Redux Cory House - Pluralsight Pete mentioned underscore, but he meant to say lodash. I was on two episodes of Pete's podcast: Aspect Oriented Programming with Matthew Groves Matthew Groves on Couchbase Pete Shearer is on Twitter. Want to be on the next episode? You can! All you need is the willingness to talk about something technical. Theme music is "Crosscutting Concerns" by The Dirty Truckers, check out their music on Amazon or iTunes.

This weeks SEO and Social Media tips podcast is now live and I’ve spent quite a bit of time this week talking about page speed. With the big Google mobile update almost out in the wild having a fast loading website on mobile (and desktop) is really important so I hope you find the tips useful. Hit play on the Podcast above to get an in depth view on all the tips. You can see the tips first every day on my Twitter feed so give it a follow! Here’s the tips. Decide on a social media attitude for your business so everyone sings from the same hymn sheet. You can now DM anyone one Twitter. Great for customer service but be careful how you use it. Move non essential Javascript to the bottom of your page to speed things up for the visitor. Listen for your brand name on Twitter without the @ symbol. What are poeple saying about you? Minify you Javascript & CSS for better page loading speeds. The big Google mobile update is nearly done. Use Analytics & Webmaster Tools to see if you’ve been hit. Use the browser caching to help speed up your web pages load times. Share your content more than once on Twitter. Its a bit like radio, everyone’s not listening all the time. If you generate a lot of traffic think about using a Content Delivery Network to speed up your site. Do some A/B testing with your posts social media to see which format works best.

Tonight is a guest mix by James Landino, combining classic chiptunes with chiptune influenced EDM. soundcloud.com/jameslandino  For full tracklist and music links, ThisWeekinChiptune.com/064 Support TWiC and unlock bonus content, Patreon.com/DjCUTMAN

DIRETO de San Francisco, na ensolarada California, Zeno SanDiego e Ciro Nunes participam de mais um ZOFE.minify(); e Daniel de São Paulo. Forever alone. Falaremos de AngularJS, JSConfBR, MEANJS

Seguindo com nosso formato fechado totalmente aberto, resolvemos fazer episódios mais diretos, sem edição, direto e reto.

Schnelle Websites haben bessere Conversion Rates, weil die Besucher sich unbekümmerter auf der Seite bewegen. Die Navigation fällt einfacher. Auch Google will schnelle Websites in seinen Suchergebnissen bevorzugen. In dieser Conversion Clinic zeigen wir Tools und Methoden, die rasch zu schnelleren Seiten und somit höheren Conversion Rates führen können.