Episode
22

Let's do the Math!

Watch this Built This Week episode on video
Subscribe on YouTubeA new AI build every week

Questions this episode answers

Can AI become a mathematician that proves and discovers new theorems?

0:00Carina, founder and CEO of Axiom Math, says Axiom is building an AI mathematician that can prove theorems, formulate new problems and discover new mathematical objects. Jordan Metzner built an LLM math roaster that scores each model's answer.

How does an LLM math roaster compare Gemini, GPT-5, Claude and Grok?

2:19Jordan Metzner says it sends a problem to Gemini 2.5 Pro, GPT-5, Claude Sonnet 4.5 and Grok 4 Fast, which write Lean proofs, then ChatGPT judges them. He also built an API so Axiom's team can run their own questions.

Which AI model proved Fermat's little theorem best in Lean?

5:27Jordan Metzner's leaderboard gave Gemini 98 and ChatGPT 70. Carina notes one model proved it for natural numbers instead of integers, and says compiling the Lean proof should be more painless than an LLM judge.

What is Axiom Math building with its AI mathematician?

9:26Carina says Axiom is building a prover and a conjecturer that form a self-play loop, plus auto-formalization that turns math into Lean, a programming language, so results are verifiable like code.

Why is Lean training data so scarce for AI math models?

11:14Carina says compute is not the bottleneck; data is. There are over 1 trillion tokens of Python code but only about 10 million of Lean, a 100,000 times gap, so Axiom generates synthetic data and auto-formalizes existing math.

Which universities teach the Lean theorem prover to students?

13:05Carina names the University of Washington, CMU, Stanford and UK universities. She says Mathlib began as a teaching effort by Kevin Buzzard at Imperial College London, and two or three of its early contributors now work with Axiom.

How is a formal AI math prover different from ChatGPT doing math?

15:18Carina says LLMs write natural-language proofs that are hard to verify, while Axiom's output is an executable Lean program, so no LLM or human judge is needed. She expects formal systems to scale better on harder problems.

How good is Gemini 3 at coding and math benchmarks?

18:01Jordan Metzner says Gemini 3 impressed him for coding and design taste despite throttling in Antigravity. Carina says it is cheaper to run than GPT, scored 100% on AIME 2025, and Axiom's model beat it on one benchmark.

What is Jeff Bezos's new AI startup Project Prometheus?

21:22Jordan Metzner says Bezos will be co-CEO of Project Prometheus and sees it as Amazon building its own foundation lab. Carina says it appears focused on physical science and real-world testing of AI for science.

How much did Suno raise, and what is it used for?

23:03Jordan Metzner says Suno raised a $250 million Series C from Menlo at about a $2.5 billion valuation. Sam Nadler says Suno generates produced music from one prompt, and the Built This Week theme song was made with it.

Read the full write-up

AI Mathematician in Lean: How Axiom Math Proves Theorems: the key questions from this episode, answered with quotes and timestamps.

Mentioned in this episode

Transcript

Jordan Metzner [0:00]: I built an LLM math roaster. You put in the math problem. It'll score it, roast it, and we'll go through that in just a second. You can actually submit a custom problem. So if you have your own problem, you can simply do that. It's awesome.

Sam Nadler [0:25]: Hey, everyone, and welcome to built this week, the podcast where we share what we're building, how we're building it, and what it means for the world of AI and startups. I'm Sam Nadler, cofounder here at Ryz Labs. And each and every week, I'm joined by my friend and business partner cohost, Jordan Metzner. And this week, we have a special guest from Axiom Math dot ai, Carina. Hello, Carina, and welcome to the show. If you don't mind, give us a one minute intro about who you are and what Axiom Math does.

Carina [0:57]: Hi, Sam and Jordan. Hi, everyone here. I'm Carina, founder and CEO of Axiom. At Axiom, we are building a self improving super intelligent listener starting with an AI mathematician. AI that can do really good math. It can prove theorems. It can formulate new problems, and it can discover new mathematical objects like graphs and fancy functions that show up in important partial differential equations, etcetera. Yeah. Great to be here.

Sam Nadler [1:27]: Super exciting topic. We're gonna jump in just to cover the high level docket for today. We're gonna go into a cool tool that Jordan built to really put the current LLMs up against each other, for math proofs. We're also just gonna dive into Axiom Math and your mission and hear directly from the source itself, you, about what you guys do and how it's all coming together. And then lastly, we're gonna cover some of the latest and greatest in AI news. I think some big fundraises as always, Bezos' new opportunity, and, yeah, just what's happening in the last couple days. So with that, Jordan, I'd love for you to walk us through what you built with Axiom in mind.

Jordan Metzner [2:18]: Yeah. So, hey, Carina. Welcome to the show. Hey, Sam. Another great episode. Another crazy week in AI, obviously, with the news of Gemini three dropping this week and a bunch of other things. So, it's almost never a dull moment, in the AI world. When we first spoke with Carina, we talked about some ideas of just building some kind of vibe coding applications that could be cool for math and could be even cool for Axiom in general. So I built an LLM Math roaster. Carina, I hope you like it, but I wanna show you how it works. And it's it's productionalized, so it works like pretty well. Okay. Cool. So I have it in light mode and dark mode. Pretty cool. Right? Alright. I have some style. Alright. So dark mode is better for math. Right? I feel like that's like a little on mass.

Carina [3:02]: No. Well Light mode?

Jordan Metzner [3:04]: Light mode? Okay. Light mode for math. Alright. So here's how it works. So I collected a bunch of different problems of different levels of difficulty. And then I have different models. I have Gemini 2.5 pro, GPT five, Claude Sonnet 4.5, and Grok 4 Fast. Now I wanted to add Grok 4.1 and Gemini three, but these models just came out like yesterday, and I don't have API access yet. So and even 5.1 is out, but I just didn't get it to like put it in time. But before I run it, me just show you a little bit about what the application does. So you put in the math problem, it'll score it, roast it, and we'll go through that in just a second. You can actually submit a custom problem. So if you have your own problem, you can simply do that. That's awesome. We have the history. So if all the maths problems that have run-in the past, we can see how well they performed. And then I thought that'd be fun for your team, but I did a little extra and I built a little API. What your team can do is generate their own API key and using my API link here, they can pass in a request of a question and then what they can do is have in the background it run, have all the models go do their own results and then they can compare them. Let's jump into it.

Jordan Metzner [4:19]: So first is, I'm okay at math but I'm certainly not your level. So the first thing I wanted to do was just build something really easy to prove whether or not my model works. So I did something, let's just you know two plus two equals four and at this type of math is you know, probably at my level and I think I can solve it. So what I have all these models doing is I have Gemini, they're correcting, they're writing kind of a lean proof. You can here see the response times from each of the models.

Carina [4:44]: Wow.

Jordan Metzner [4:45]: We can compare the results of each of the models And then, obviously, you have this problem which no model knows which model is smartest. So I chose ChatGPT. So ChatGPT will then evaluate the responses from all of the models. Let's just get this finished with two plus two, and then we can go into a more complicated question and see how well it does.

Carina [5:03]: Yeah. That's great. Oh, evaluating.

Jordan Metzner [5:05]: It has to get processed each one of these against, like, the core source. So, ChatGPT's feedback is that all of them are correct. Okay. Great job. So fantastic. Two plus two equals four. All models know that. I think we're on good shape. So so far, the basis of truth. Right, Carina? I'm not a perfect scientist, but you know, I know a little bit. I have a few different problems. Maybe you wanna choose which one? I have a

Carina [5:27]: Let's do Fermat Little Theorem.

Jordan Metzner [5:29]: Okay. Fantastic. So that's considered an intermediate problem here. And here's the problem. For a prime number, p in any integer, a non divisible by p, we have a to the p minus one equals one mod p

Carina [5:41]: That's right.

Jordan Metzner [5:42]: Provide a formal proof in Lean four syntax. So I just read that out loud just for the audience, you know. So first, let's roast the LLMs. So now we'll have the LLMs. This is gonna take a little bit longer, so we can maybe chat in the meantime.

Carina [5:53]: It's fascinating. There are so many Fermat theorems. I think like when I selected it, I was actually having something else in mind. But yes, I think this one is the Fermat little theorem.

Jordan Metzner [6:01]: But ChatGPT told me that it is when I built the app. So as I vibe coded this thing, I'm pretty sure it is. But the good part is is that you can kind of submit, whatever formula you want. What I tried to do is get a collection of about 10 problems of different difficulty so that it could test the application and see kind of For some how well it does. The easiest one was Pythagorean theorem, then I felt like, that's even like too difficult just to check, basis of truth. That's why I built the Okay. Mathematic one. Just to check, if everything's working essentially.

Carina [6:31]: Yeah. And that's for lean? So it's generating all

Jordan Metzner [6:34]: Yeah. It's gonna generate lean response. Wow. -huh. Yeah.

Carina [6:36]: Yeah. Yeah. We're not seeing the lean.

Jordan Metzner [6:37]: Okay. Cool. Alright. So here we go. So here's Gemini Here's the response. Here's the theorem. Here it just gives the oh, here we'll provide both versions of Lean. Okay? Here's GPT five.

Carina [6:50]: No. That is Lean. I haven't seen Lean in the Gemini Pro one yet. If you scroll down, the first one.

Jordan Metzner [6:58]: It says it's below. Let's keep going. Right here.

Carina [7:00]: Yeah. Got

Jordan Metzner [7:00]: It. Right here. Cool. Alright. So we got import Mathlib. Right? So we've got like these different ones. What we can do, first, we can compare the results. So we can just review them all side by side. And then we can judge the proofs. I think that's the way to do it. We have two ways to do it, actually. This should score it. Yeah. So then it'll judge all the proofs. Mhmm.

Carina [7:20]: We could also, right, like take that lean proof and then put it in like lean land and like, and see if it compiles, which should be hopefully be pain more painless than having LLM judge. Yeah.

Jordan Metzner [7:34]: Sure. So we can take like I don't know which answer we want as

Carina [7:37]: Probably wouldn't want to take the lean you know, just start with import Mathlib.

Jordan Metzner [7:41]: Yeah. Yeah. I got it. I But I'm saying we could just pick which one of these answers we want and we can go into a lean editor.

Carina [7:48]: Entire thing? Yeah.

Jordan Metzner [7:49]: Yeah. Okay. Let's just let the judging finish and let's see how well that does. It's just a really cool way to compare any type of multi level LLM results against any dataset. Right? And like in this case, I chose lean and math. But, know, this could be a lawyer writing a contract and sending it out, amongst all four and asking them all to bring back, which contract is the best. So it could be applicable in many businesses, even ones that are outside the scope of mathematics. Fascinating. Cool. So I have a leaderboard. It gave Gemini the best score. ChatGPT is 70, and so on and so forth.

Carina [8:22]: So That that's weird. Don't you think? For two, it says it proves the theorem for natural numbers instead of for integers. Oh, I guess oh, it just didn't go with the negative numbers. That's fascinating. Just a close miss. Gemini is 98. Wow. Okay. It's great.

Jordan Metzner [8:40]: So I think what would be really interesting, Carina, would be is in this type of problem set would be to get like thousands. Right? And just iterate this over and over again and find out where these models truly fail. And if you do this at enough iterations, like, I don't know what, like, the right end number would be. But my guess is for each, like, major type of problem set, you'd be able to find the model's weakness pretty quickly and its ability to resolve those types of problems.

Carina [9:06]: And that's actually the first thing we did when the office is, still camper chairs and plastic foldable table. It's what we did.

Jordan Metzner [9:15]: That's awesome. Okay. So anyway, that's my math roaster. I hope you like it. It's great. And that's enough about me. Let's jump into Axiom.

Carina [9:24]: That was super cool.

Jordan Metzner [9:25]: Okay, Carina. So obviously, super young entrepreneur, super excited about your new round of investment, but let's start from scratch. Tell us, like, how did this whole thing come about? What is Axiom? And what are you guys doing every day?

Carina [9:38]: Axiom is, I think, the coolest AI for math company

Jordan Metzner [9:40]: Awesome.

Carina [9:41]: In my opinion. We are building an AI mathematician, a model that can not only do do really well on benchmark problems, those Olympiad math problems that we just saw, but also develops capabilities that are like a research mathematician, including the ability to conjecture, which is to propose new problems, unseen problems, hypothesis, and the same system can then try to prove and verify in addition to solving these problems. So a prover and a conjecture talking to each other, forming the self play loop like we talked about in our vision blog. Additionally, this system can also auto formalize, which is to convert the massive amount of math corpus data into lean, turning math into programming language, which, have a lot of great technical advantages because we have seen reinforcement learning, all verifiable domains like coding, having achieved incredible breakthroughs. So by combining AI, math, and programming language, all three pillars together, we believe to see the same sort of step function jump in math capabilities, especially real mathematics, serious mathematics beyond the benchmark that a lot of models have seen.

Jordan Metzner [10:58]: So that's obviously incredibly interesting. Math, obviously, historically was run on CPUs. Right? So the movement of running math equations onto GPUs is really this big jump. Right? And the ability to essentially kind of find new opportunities within the mathematical field. Is that a good way to say it?

Carina [11:14]: I think it's a it's it's it's close. Well, I think we use, a lot of both GPU and CPU in our engineering effort. There's, obviously, the large language models part run on the GPU and the LIMPod, currently compiles through CPU. And there's interesting engineering problem as to how to maximize utilization because there is some sort of dragging it down, in fact, because CPU generally, could work a little bit challenging with the GPU. But I wouldn't say that the compute part is kind of the bottleneck. I think the difficult part is the data scarcity, which is there isn't there that much lean. There just isn't that much lean. And there are more than 1,000,000,000,000 tokens of Python code, only about, like, 10,000,000 tokens of lean code. That's a 100,000 times data gap. So that's, I think, what is really, really hot.

Jordan Metzner [12:08]: Yeah. So, speaking of that, how I guess, like, artificial data becomes much more important in generating artificial lean problems

Carina [12:16]: 100%.

Jordan Metzner [12:16]: If that becomes, more critical in sourcing the data because you can't just go to a library and buy, a nineteen twenties book on lean. Right?

Carina [12:24]: Well, I guess a lot of the companies I know, especially some Chinese companies working on this, are having a massive number of, like, lean data labelers, lean programmers to try to generate human data. Of course, that's very expensive. Doesn't scale as well. We have where both database own synthetic data generation, both by converting the informal data that already exist, scrape them, and, really augment them in a way that makes sense to convert to lean, auto formalization. We also have other efforts. So given formal data, formal math data already in lean and that's your seed data, how do you make that 101,000 times Williams larger?

Jordan Metzner [13:05]: Yeah. Okay. So speaking of lean, now that we have everyone has AI, and obviously it's it's almost like for mathematics kind of the jump of like having a calculator versus not having a calculator. Is lean now being taught in these mathematic, educational programs? And are students like writing their math, theorems in lean now? Or is that still too early and we haven't gotten there yet?

Carina [13:27]: That's a great question. I think a lot of universities are teaching Lean. I know a couple of universities in The States, and I know university of Washington, professor Joe Alper in the math department is teaching students Lean. At CMU, there's a really great Lean community. Professor Jeremy Avigad, professor Sean Volick, and others are teaching students Lean. Stanford has an automated reasoning lab by professor Clark Barrett and other folks, and they have TAs that are grad students teaching students Lean. There are many universities in Europe, in The UK that are teaching students Lean as well. In fact, Lean started I mean, not Lean, but Mathlib, the Math Library started as a teaching effort at Imperial College London by professor Kevin Buzzard. He wanted to teach his students who are enrolled in his introductory level, freshman level proofs class to write better proofs and to train them to think rigorously. So he gave these students who might, be a little bit behind on proof writing the exercise of formalizing everything in lean.

Carina [14:34]: What he found is actually it's not those students as his audience, but the students who already don't need the class that, they are very much advanced grad classes takers. And these students, because they are bored and they have nothing better to do, would love to join the effort of formalizing the undergrad corpus of math in Mathlib. And two or three of them are actually currently working with Axiom. Some of Them are, like, my closest friends over, like, the last five years that I met, like, via, like, MIT Imperial College London exchange program. So really sort of great to have these lean native students, and now, like, they're PhD students, some of them have graduated from PhD. But that was, like, 2019, very early on.

Jordan Metzner [15:18]: Awesome. How these, like, LLMs compare to, like, figuring out math versus, like, what you guys are doing? Because I think that's, like you know, this is the whole clip of, like, what's exciting. Right? Like, if anybody doesn't know about math and they have no idea what you're doing and they're just like a layman who's into tech and AI, and they say, okay, what is this what's the difference between this and ChatGPT? Like, what's the difference between like an LLM and what you guys are trying to do?

Carina [15:40]: Large language models are doing math in the informal space. They produce proofs in natural language that is English, and they will give you a multistep reasoning traces if they're a deep sea, but they will only give you, say, like, numerical answer if you're, change your beauty. And the numerical answer is a verifiable output, which is something that you can, grade. Like, 971 is 971. The problem is without the sort of very detailed step by step deduction, it's hard to verify all these intermediate reasoning traces. So it's very difficult for an expert or a layman to know whether there might be a hidden bug among, like, a 3,000 line math proof. On the other hand, what Axiom, the informal formal hybrid prover system we are building is to make sure that the output we give are programmatically verified. Verified. There is a Lean program underneath it, and the Lean program is executable. So in a way, we do not need an LLM judge or a human judge.

Carina [16:45]: We just run it like you run a Python computer program. I think that's the biggest difference between these formal models and the large language models. In the formal model states, we know that Google DeepMind AlphaProof system, the system that got Silver Medal, actually, one score below the gold cutoff is a formal system. This year, they have the Gemini system, and also OpenAI has the strawberry team's IMO team. These are informal system that got really good scores on IMO. Difficulty is IMO and other Olympiad math benchmarks sort of half a curriculum, a set sort of syllabus of things that they're testing all, which limits their search space quite a bit. When the proof gets very complex and multistep, requires really hard math capability, and we believe that formal system gonna be extremely helpful in scaling, continuing to scale on those harder problems.

Jordan Metzner [17:43]: That's that's so so cool. Obviously, math's the backbone of kind of all technology, so it seems like there's some, mathematical breakthroughs on the edge here that, once these things really get their power, they can really turn out some new opportunities. That's super cool. Alright, Carina. Well, thank you for telling us about Axiom. Thanks for joining us. Let's talk a little bit about the news for this week as it's been another crazy week. Gemini three just dropped. I don't know if you've tried it yet. I downloaded Antigravity, the new Google code editor. Lots to tell you guys, but I'm being throttled everywhere. So Cursor, I can't get Gemini three to work. I can't get Gemini three to work in Antigravity. I burned all my tokens. So, I'm I'm munching tokens all night long pushing Gemini three, but I've been incredibly impressed with its performance for coding and design taste, also much nicer.

Carina [18:33]: We like Gemini three. It's also, like, so much cheaper to run compared to, like, GPT. One thing that's very interesting is we you know, on a certain benchmark, I can tell, which one, and our model actually beats Gemini three

Jordan Metzner [18:47]: Oh, wow.

Carina [18:48]: In math improves yesterday.

Sam Nadler [18:50]: I know Gemini three has been outperforming almost every LLM on the market in terms of test scores. I tried to use it quickly this morning to build a personal meditation app, and I bumped into some hiccups, but maybe it was user error and not the model.

Carina [19:08]: It got 100% on AIME 2025, which is the high school level. So it's three levels before the IMO. So if you win AIME, you will go to US AMO, and then you'll go to MOP, and then you will eventually go to IMO. But it got 100% on Yeah. Yeah. That's fascinating. But 100% does code execution shows how important the

Jordan Metzner [19:29]: Code is needed. Yeah.

Carina [19:30]: Yeah. That's the tool is important.

Jordan Metzner [19:32]: Well, It says without tools, it got 95%. So, obviously, that's a significant improvement.

Carina [19:38]: Odd because it has what? The it has 20 well, guess that's odd because it has, like the number of AIME problems is 25 problems?

Jordan Metzner [19:49]: Well, if you compare it to Gemini, looks like to

Carina [19:51]: Two Fifteen. Point 15 problems. So 15 problems on the AIME exam, so 95% is, like you know, got one wrong.

Jordan Metzner [20:00]: Yeah. So they got a 88 last time, so they probably got two wrong without the tool. You know? Yeah. Mhmm. Pretty cool. But maybe it's calculated differently because Sonic got a 80 If it got a 88.

Carina [20:15]: I guess it's like, past Yeah. Probably. Yeah. Past k.

Jordan Metzner [20:20]: Okay. But anyway, yeah, Gemini. Super cool. So, I just think this is interesting. The Gemini model for a lot of reasons. I mean, one, this is the first, real big model coming out of, one of the type three hyperscalers, know, the Amazon, Google, Microsoft. So far, all those models have been behind, pretty much Claude and Anthropic and OpenAI historically, and this is a big leap. Google has a lot of money and a lot of servers and a lot of warehouses and a lot of products to inseminate, Gemini three Pro into their products from, Google Suite to search to YouTube to ads. I mean

Carina [20:54]: Yeah.

Jordan Metzner [20:55]: I don't know. Big opportunity.

Sam Nadler [20:57]: Yeah. 650,000,000 monthly active users across search, the Gemini app. I mean, that's an insane amount.

Jordan Metzner [21:05]: Yeah. Insane amount of users. Obviously, we saw this week Warren Buffett made a massive investment in Google. And I think if you saw the videos of I don't know if you guys saw the videos from Antigravity, the launch of the code editor, Sergey was front and center, you know. So yeah. Good. I mean, this is about CEOs getting back into the driver's seat. So why don't we jump over to story number two? Because that's another CEO getting back into the driver's seat. So Jeff Bezos is starting a new AI startup called Project Prometheus. He's gonna be the co CEO. To me, honestly, this just seems like Amazon doesn't really have access to, a foundational laboratory like Microsoft does with OpenAI, and they're trying to build their own. I mean, it seems like Google has DeepMind, and Microsoft has a relationship with OpenAI, and Amazon doesn't really have a stake in the ground. I don't know. What do you guys think about this?

Sam Nadler [21:59]: Yeah. I don't know. To me, it's exciting that Jeff Bezos is, coming out of semi retirement and, taking an operational role. I would argue that, he was the best CEO of the last couple decades. So to get him back into a driver's seat, I think, is super

Carina [22:18]: Yeah. I think this is doing, like, physical science space, so kind of, like, a lot of real world testing AI for science. I'm quite excited about that part. This is seem like, a OpenAI style, like, foundation model lab, but more like applying the theoretical findings and try to figure out how to, deal with some material or data.

Jordan Metzner [22:39]: Exactly. Hard to say what they're gonna do. Obviously, they brought over Bajaj from Verily, obviously, who was in the biotech startup at Google or Alphabet per se. I think overall, the trend is that you're getting, these billionaire CEOs who, could be on a beach, or executives are retired per se, could be on a beach or whatnot, but they're coming back to build because, we're in a new build era, that's exciting, I Yeah. Okay. Last story of the day, real quick. Major funding news from Suno. I don't know if you've used Suno, Carina, but I love to use Suno. I find it to be so fun. I think it's a great party trick. But, yeah, Suno raised a $250,000,000 series c from Menlo at something like a $2,500,000,000 valuation. I know we've talked about them a few times on here, Sam, but, yeah, curious who's thoughts.

Sam Nadler [23:27]: Suno allows you to quickly generate, like, highly produced music from a single prompt. And maybe to end out the episode, we'll we'll have a Axiom theme song that we can, layer on But it's a really fun tool. We with a quick prompt about Carina and Axiom, we could have a pop song, a reggae song. Oh, no. Who's talking about that? An idiom song. You name it. We could have, Axiom, prove out its, math problems in song, theoretically. No. I'm just joking here. But it's it's a fun tool that we like talking about. And in fact, like, the song of Built This Week, our podcast we created with Suno.

Carina [24:12]: Yeah. I remember playing with Suno. It's like, it's amazing that, like, I don't know anything about composition, but maybe there's some melody I want to turn it into reality, which, at one point, I feel like when the AI gets really, really good and, people who are hidden Ramanujans, who have mathematical creativity but having never sort of been trained to do formal proofs could probably, use the Axiom tool and get a, actual theorem just like music and artists creators using Suno.

Jordan Metzner [24:46]: Yeah. Totally. We covered on a previous episode, there's a new programming language where you can program music. And obviously, music at the end of the day is is incredibly mathematical. So it'll be interesting how, maybe with some new math inventions, we can invent some new styles of music.

Carina [25:03]: Most of the double major as in or, like, the humanities social science classes, the math majors that MIT take are music, actually, It's music

Jordan Metzner [25:12]: It's incredibly mathematical. And, it doesn't really matter, like, what instrument you play. The more you learn about the instrument, the more you get into the, learning about the triads and the triplicates and, how the notes and chords are created. Alright, Carina. Well, this was a great episode. Thank you so much for joining us. Sam, this was awesome. Love to learn about Axiom, talk about math, build some new tools this week. Obviously, Gemini three's kept me up all night. I don't know about you guys, but I'm gonna continue to work on it and play with some new stuff. But, yeah, this was really fun.

Sam Nadler [25:44]: Carina, thank you. It was a pleasure. This is a pretty big pivot from our normal routine episode, so it's been extremely informative and really appreciate you coming on.

Carina [25:54]: Thank you so much. Yeah. Was a lot of fun.

Jordan Metzner [25:56]: See you all next week. Bye.

Hosted by
Sam
Hosted by
Jordan

More podcast