Podcasts about counterfactuals

Welcome to the History Guy Podcast: Counterfactuals. What is a counterfactual? At it's most basic, it is a ‘what if'. It's a way of understanding history as it is by discussing what it could have been.On today's episode, we talk about a little remembered campaign by the Allies to intervene in the Russian Civil War, at the tail-end and even after the end of WWI.

When we first dicsussed the Summer of Simulative AI in 2024 we knew it would be a brief summer, but it has recently come back with a vengeance with SimGym in April and now Simile AI's $2B Series B, backed by GreenOaks and Index Ventures with prominent backers like Fei-Fei Li and Andrej Karpathy, running tens of millions of simulations for Fortune 100 clients like CVS and 85–99% accuracy vs human focus groups. Time to catch up on why this Second Summer of simulation is working!From creating Smallville, the landmark 2023 paper on Generative Agents that showed AI characters could remember, plan, socialize, and develop emergent behaviors, to now building foundation models of human behavior, Joon Sung Park is trying to answer a much bigger question: what if we could simulate the world before making decisions in it? In this episode, the Simile co-founder and CEO joins us to unpack the path from generative agents to digital twins, why today's frontier models still fail to capture how humans actually behave, and what it would take to eventually simulate all 8 billion people on Earth.We go deep on Simile's approach to modeling human behavior: long-form interviews, observational and transaction data, randomized controlled trials, population-level and individual-level models, and post-training on the causal mechanisms behind why people make decisions. Joon explains how his research created digital twins that reproduced human behavior and attitudes 85% as accurately as people reproduced their own responses, why models optimized to be rational can be bad simulations of irrational humans, and why understanding “social physics” may require changing model weights rather than simply prompting frontier LLMs.We also explore the much larger ambition behind simulation: testing products and policies before deploying them, finding counterintuitive paths toward desired outcomes, modeling emergent behavior across entire societies, and potentially tackling problems like climate change, democratic instability, and UBI. Joon reflects on scaling laws for simulation, the economics of data-center-scale simulated worlds, the connection to Thomas Schelling and psychohistory, why simulation is surprisingly similar to painting, and whether we might already be living in one.We discuss:* How Smallville and Generative Agents led to Simile* Why Joon's team asked: “What if we can just recreate the world that we live in?”* Why useful personal agents require deep models of their users* Memory architectures, Markdown files, and the limits of prompting* “Social physics” and behavioral foundation models* Why web data captures what people say more than what they actually do* Interviews, transactions, observational data, and randomized controlled trials* Why predicting the future matters less than understanding how to shape it* How Simile creates representative simulated populations* Simulation versus prediction and the connection to Foundation's psychohistory* How to evaluate simulations instead of simply stacking LLM hallucinations* Creating digital twins of 1,000 real people and reaching 85% behavioral accuracy* Why frontier models can struggle to reproduce real human behavior* Why good simulations need to reproduce human biases and mistakes* Post-training models on randomized controlled trials* Population-level versus individual-level simulation* Scaling laws for human simulation* The long-term ambition to simulate all 8 billion people on Earth* Whether simulations could help solve climate change or detect collapsing democracy* Thomas Schelling and the history of agent-based modeling* Why future simulations could require an entire data center* Multi-agent simulations and what happens when simulated people interact* Replacing expensive human panels with synthetic populations* Why market research is only the starting point for simulation* Why Joon sees simulation as surprisingly similar to painting* Using simulation to study questions like UBI* Whether we are already living in a simulation* Why AGI and simulation may be the twin technologies of advanced civilizationsJoon Sung Park* LinkedIn: https://www.linkedin.com/in/joonspark* X: https://x.com/joon_s_pk* Website: https://www.joonsungpark.com* Simile: https://www.simile.comTimestamps00:00:00 Introduction and Joon's Path from Art to AI00:01:46 Smallville, Generative Agents, and the Origins of Simulation00:05:03 “Let's Just Create a World” and the Future of Personal Agents00:09:53 Social Physics and Behavioral Foundation Models00:14:08 Prediction vs. Simulation: How Do You Shape the Future?00:16:59 How Simile Models Real People and Populations00:25:35 Evaluating Simulations, Digital Twins, and 85% Accuracy00:30:23 Post-Training Models to Reproduce Human Behavior00:40:04 Scaling Laws and Simulating 8 Billion People00:43:10 From Schelling to Society-Scale Agent Simulations00:46:13 The Cost and Economics of Simulating the World00:52:05 Real-World Use Cases, Synthetic Populations, and the Market00:57:27 The Future of Simulation, Painting, and UBI01:04:23 Are We Already Living in a Simulation?01:06:08 Building Simile and HiringTranscriptIntroduction: Joon Sung Park, Simile, and the Story So FarVibhu [00:00:00]: Today, we have Joon in the podcast. Excited to kick this one off. Very exciting company. I wanna kick off and ask you the question, talk us through the story of your life. How have you gotten here?Joon [00:00:13]: Yeah, for sure. I'm really excited to be here. A story of my life. So I was born in Korea, and I lived there for a good 11 years or so of my life, and then my family moved to Boston. So we moved when I was 11, and my parents were doctors, so they were going through their postdoctoral studies. My dad was a surgeon, so he was doing his sabbatical years at the Boston Children's Hospital. So I grew up there, not too close to tech. I was very much a music and artsy, painting kind of guy.Vibhu [00:00:49]: Painting.Joon [00:00:49]: Exactly. I got into painting a little bit later, in high school, but that's what I used to do. And then I grew up mostly in the East Coast after Korea. So I lived a good number of years in New Hampshire, and then I went to college in Pennsylvania. And I got into more of this tech scene, in college. So I was originally trained to be an artist. I thought that would be my professional career. So it wasn't a hobby. It was like, “Hey, let's make a living out of this.” And then gradually, I got really interested in this idea of, hey, the greatest artist often creates their own medium, and the best medium that we had available today was in computation. So I decided to go deeper into that, and one thing led to another, and we can go deeper into this, but I decided that research was something that I gradually got interested in, and here I am.Smallville, Generative Agents, and the 2023 Breakout PaperSwyx [00:01:46]: So there's a lot that you packed into the research components. You had one of the best papers of 2023, which was the generative agents paper, commonly known as the Smallville paper.Swyx [00:01:58]: Feel free to call back to anything else that you mentioned, but most people would have heard of you from this. Do you have any statistics on how many people have, like, read it? arXiv gives you something, right? Some stats.Joon [00:02:10]: Yeah, it's a good question. How many people have read it, I'm not sure.Joon [00:02:14]: I know we do keep track of citations, and they are going up quite fast.Swyx [00:02:23]: Yeah, Google Scholar has 7,200 citations.Vibhu [00:02:25]: I feel like it made a bigger hit than that, and it was a pretty instrumental paper. It got cited so many times.Swyx [00:02:34]: It is frequently the answer when people ask, “What is the best paper you've read recently?” It's this one.Vibhu [00:02:39]: I thought the memory component was pretty underrated. It was a very good early memory system, and one of the biggest papers.Foundation Models and the Search for Killer ApplicationsJoon [00:02:47]: Yeah, so maybe I can talk a little bit about how this particular paper came together. So when I got into research, it was back in 2020 when I started my PhD program at Stanford, and that was the year, when we were about to get GPT-3 to be available. So we already had GPT-2, and you could sense that there was this new class of models that was just becoming available in the market, and the team got very intrigued. And the general consensus was, “Well, is this model going to be useful for anything?” “It's really strange that these models are not trained to do any particular task.” But we decided to take a bet. So a large group of scholars at Stanford, and it was led by one of my co-founders, Percy Liang, and we came togetherSwyx [00:03:35]: Who coined foundation models.Joon [00:03:36]: Who coined the term foundation models. We wrote this paper, where that term came from called Opportunities and Risks of Foundation Models. And during that process, really the thing that I started to think deeply about was, here is a model that is fundamentally new in our ecosystem. The reason why this was new was it wasn't, again, trained to do anything in particular, but its premise was it could do anything and everything. It was like a stem cell, if you were to take a biology analogy. And I got really interested in this idea that, well, if we were to really think about what are the killer applications that this particular technology would enable, what would that be? Many of my colleagues were using this for simple classification, simple generations. Interesting that these models can do that, but from an interaction perspective, not that interesting. We've known how to do that for many decades. And what we came down to was these models are trained on this very broad data from the web, right? So these are human behavioral data. It's social media, Wikipedia, all these data. So if you poke at the right angle, then you could see human behavior that would just pop out that's quite realistic, and we've never seen that before.The Time Machine Game and Recreating the WorldJoon [00:04:45]: So that got us really interested. The exercise that we decided to do, with this particular group of colleagues, Michael Bernstein, Percy Liang, and myself, who ended up becoming my co-founder at Simile, we sat down and we played this game that we call the time machine game.Joon [00:05:03]: Imagine we were to get on a time machine and fast-forward 10 years and look back. What would have been the single application that will have mattered that would be the most interesting and inspiring? And when we thought, “Well, what if we can just recreate the world that we live in?” it's really hard to get more ambitious than that. Like, let's just create a world.Joon [00:05:24]: And that's where we started. And initially, we had this paper that was a precursor to the generative agents paper called Social Simulacra.Swyx [00:05:32]: Before you go further, were there other candidates for the most ambitious thing in the time machine exercise? What was number two or number three?Personal Agents, User Models, and Why Simulation Came FirstJoon [00:05:44]: There is a close second that we were considering, which ended up becoming more of these automation tools, especially the vision around really personalized agents that would do things for you.Swyx [00:05:59]: That's also happening.Joon [00:06:00]: It's also happening. But it was interesting for us, right, in that the reason why, we decided to go with the idea of simulation, one, I was a huge science fiction nerd, and this idea of creating simulation, I was personally really just fascinated. I loved the idea. It's really cool to see, like, a game town like this and just see these agents live in it. But at the same time, my bet was if you were to create a really amazing personal assistant out of this technology, what you need first is an amazing model of your users. So I told a model, “Hey, can you go buy late dinner for me?” And it orders Hawaiian pizza, and I do not like pineapples on my pizza. Then it totally failed. The way for it to not make that mistake is only by having a deep understanding of who I am. And I gave a very simple and dumb example here, but you can imagine how this core understanding of people is instrumental. This is how, if we have our family and closest friends, they have a good mental model of who we are. That's the basis of our social connection. So our bet also was this technology around simulation, creating accurate representation of people ought to precede the more complex agents that would automate the world that we live in. So that was the bet. But that was a very close second, and I'm still very much fascinated by it. I think there's a lot of interesting work that's going around. My hot take here, though, is I don't think we've seen a true personal assistant that's useful, in ways that meet the ambition of that particular line of work. I think there are early applications that are interesting, and if you talk to even ChatGPT nowadays or Claude, they know a lot about us. So a lot of the generation it's doing, I do think it's much more tailored, but I think the ambition is quite large in that field, and I don't think we quite have all the right ingredients just yet.Swyx [00:08:01]: So OpenClaw and these personal agents, what do you want to see from them that they don't currently have?Memory, Markdown, and the Limits of PromptingJoon [00:08:09]: I do think it's slowly getting there, but I do generally want them to have much deeper understanding of the person. Right now, you look at the models. OpenClaw, what it's leveraging is a Markdown file, and I think it's quite clever, right? So if you look at the generative agents paper, this was the same intuition that we had, where initially when we were creating the memory architecture for the generative agents, and, like, this is, like, back in 2022, so we didn't really quite have the idea of even agentive architecture or the term agent. But the intuition that we shared with some of the work that's coming out today was we initially thought, “Well, do we want to make the memory into, let's say, knowledge graph? Do we want to train a bespoke model?” All of these things. And what we decided to do was, “No. Just forget about all this.” These language models are quite good at modeling text and understanding and reasoning about text. So just put everything in a Markdown file or a text file. You're done. I thought that was quite interesting that we could do that, and there's a lot of strength in doing that. But also, there are limitations. It's the way you retrieve and make sense of data that's extremely large, it takes a lot of work. So I think that technology is getting better. I also do, however, think, there are certain things you just cannot shape just by prompting the model. So to some degree, you do need to touch the parameters of the model itself. So there is this work that I do think does need to happen, and it is happening. The question is, how far can we take it? How do we source data, and how do you also create an ecosystem where people are continuously feeding data to this model so it's learning about you?Vibhu [00:09:50]: What's the intuition between why you need to do it in the model?Social Physics and Behavior Foundation ModelsJoon [00:09:53]: My intuition behind the actual when do you train or even post-train a model versus just prompt a model is if the model has to learn the underlying physics of the world that it's operating in. So it has to learn new social physics. The places where it doesn't have to train are the places where it already has the physics. We trust the physics. It already has the base statistics, but it's just trying to react to an environment. Then I think you can just prompt your way into getting the actions out of it. I don't think the models that are out in the open have yet learned the complete mapping of social physics of humanity. This is one of the core theses of Simile, right? And one of the core reasons why that is the case is if you look at the data that the model was trained on, these models were trained on the web data, like, whatever was available on the web. And these are really interesting data sets, but they are fundamentally the self-exposed attitudinal data with some behavior data that's sprinkled around here and there. And it has yet to learn the really deep behavioral nature of people, not just what people say they do online, but what they do in real life. And this is one of what I would consider to be the dark knowledge of humanity that we haven't quite captured. And it's these data that would also need to get factored into the model creation.Vibhu [00:11:21]: You call it behavior foundation model.Vibhu [00:11:23]: There's a good one-liner here, but outside of that, what type of data do you need? What are you changing on the model level? How do you go about modeling, doing a behavior foundation model?The Three Data Buckets: Interviews, Behavior, and CausalityJoon [00:11:35]: We think about data in three buckets. So one bucket is interview data. It's quite interesting. Rich qualitative data is interesting. It's not behavioral, but we would literally ask people, “Hey, tell me the story of your life.”Vibhu [00:11:53]: It's just what we're doing here exactly.Joon [00:11:54]: The question that you all asked at the beginning of this interview literally is the question we also ask. And we ask our participants to go a little bit deeper, than how far I went. Maybe I can give more of my life story in lieu of this. But the reason why that data is interesting is by learning about this very long-tail information about people, you get a lot of texture around this model, like, this person as a model. So even understanding their childhood memory or even their trauma, their first love, these things, quite informative in ways that's really hard to predict. So that's one. Then there are two tranches of what I would consider to be the behavioral data. One kind of behavioral data is observational. So these might be like transaction data, or these might be data that you can get by scraping the web, right? So you can imagine why these data sets would be interesting, right, because they give you the base statistics of people's behavior.Joon [00:12:55]: But then there is the last category of data, that I personally think is perhaps the most important, which is the data that describes the causal mechanism, the whys of people. Some of this is covered by the interview data, the qualitative, because people talk about why they made certain decisions. But really, where you get to see the most behavioral aspect of this is in randomized controlled trials, like RCTs. Imagine you have the same setup, but you have a few different variables that you are trying to tweak. Can you get realistic human behavior out of it in ways where, imagine you had this particular option. Imagine you're even trying to choose whether you're going to drink coffee or not. The day you drink coffee versus the day you didn't drink coffee, does your behavior change? That's a data set that describes a causal mechanism. This is quite important in modeling people. The reason why this is important is oftentimes when people come to us, or not just to us, but the reason why people are interested in simulation isn't because they want to predict the future. If you're trying to win against the stock market, predicting the future is interesting.Prediction vs. Simulation: Shaping the FutureJoon [00:14:08]: But most people, most decision-makers, what they want to know is, how can we shape the future? It doesn't really help you to hear that your sales are going to tank in two quarters. They're just gonna say, “Wow, that sucks.” What they want to know is, well, what do we need to do now to avoid that future? That's the causal mechanism. And this is also very hard data to come by, right, because the world is our ground truth, but it happens once. So in a very controlled setup where everything is equal except for one variable, this kind of data set rarely happens. So this is a reason why this data set is both hard to come by and quite important if you're trying to model human behavior.Swyx [00:14:50]: So behavior, I think, is the hardest data set to acquire. What is out there? What is even possible? You're not going to know a lot of details about my life. I don't even have data for myself on my own health or habits, and I just don't log everything. So how can you have that data?Joon [00:15:14]: So we run a lot of randomized controlled trials.Swyx [00:15:17]: But you put people in the lab, they watch them sleep, or what?Joon [00:15:20]: We do care a lot about the consent process. People know that we invite them to be a member of this community to both share data and have themselves represented in different forms. But we bring a lot of people to the lab, or virtual lab, where we design experiments that would pose them real behavioral decisions. And often in these experimental setups, what makes the difference between what is attitudinal versus behavioral is whether the stake in your decision is real. That's ultimately what makes it behavioral. So in these setups, we are inspired by our colleagues in social sciences, psychology, and so forth. So when they run studies, the techniques they utilize is imagine there's an online store that you're inviting people to come by. Then whatever they purchase in this experiment, they actually get that item delivered. Like, these are the things that make the stakes real. So we run a lot of these experiments, and we also do partner with firms. Right now, we also have customers who are quite excited to at least give us a glimpse of the behaviors that their users exhibit so that we can get a little bit deeper understanding of how people behave in these different platforms.How Customers Use Simile: Populations, Queries, and ExperimentsVibhu [00:16:39]: I think on the customer side, they have a lot of data about their users, who has bought. They have the action data.Vibhu [00:16:47]: Can you walk us through an example of what someone comes to you for? What questions would they want solved? Do you customize a model for them? Do you have something off the shelf? What does that look like?Joon [00:16:59]: Today, when people leverage our models, it's often to better understand the population of their interest. So usually, the start of the relationship, we come together and hear about what population they want us to model, right? So it might be that if you're a CPG company that's selling to all of the US, then maybe it's fairly straightforward. You want to model the gen pop of the US. But at the same time, if there is a vertical or if there's a market that they're trying to go into, imagine, they want to better understand, let's say, people in their 20s and 30s living in California. That's a much more specific population. So we hear about this population, and we go recruit these people, with consent, and with incentives, and we collect some of their data and create a model of these people. Then what our product allows you to do is query them. So it can take as input a filter that is a description of the population that you want to talk to, just like the one I just mentioned, and an environment. The environment can literally be survey questions, behavioral experiments, It can be A/B testing. Oftentimes, the core use cases are things like concept testing, to start with. But also, people sometimes want to do focus groups or one of the fun use cases that we also serve is even modeling things like earnings calls for public companies.Joon [00:18:21]: So these are the use cases that we often start with.Swyx [00:18:23]: Concept testing, is that an established term? I've never heard of concept testing.Concept Testing, Gallup, and PoliticsJoon [00:18:27]: Yeah. So it has to do with they have, let's say, different messaging, different products, different ideas.Swyx [00:18:32]: It's like a marketing exercise.Swyx [00:18:33]: Okay, got it. Got it. Politics?Joon [00:18:36]: We do, have a strategic partnership with Gallup, and of course, Gallup is deep into policy space and so forth. Right now, we have not worked deeply with politics, like that area just yet, however.Swyx [00:18:49]: I'm curious if there is demand or if they really would have different needs that somehow fundamentally don't mix with your existing, users or people.Joon [00:19:00]: I think there's certainly demand.Joon [00:19:02]: But we are very much mindful of how this technology gets adopted and the societal impact that we'll end up having with this technology. And I do see politics as an area where a company has to be particularly thoughtful about the way they operate and make impact. So this is where we also want to make sure that we form enough of guardrail and perspective on how to leverage this technology before we go on to serve markets like the politics.Swyx [00:19:29]: I'll give people an example. one of my favorite shows is The West Wing. I don't know if people have watched.Swyx [00:19:34]: One of the key storylines is, like, the president has, multiple sclerosis, but they haven't. they need to figure out how to disclose it. So they run a poll with a fake governor and ask people to respond on the poll,Counterfactuals, Polling, and When Simulation Is UsefulSwyx [00:19:47]: They try to make decisions based on the results of that poll on, like, how well they'll be received, like where, how should we play this?Swyx [00:19:54]: And I'm like, well, I think those counterfactual things, I would use a simulation for this if I could trust it.Joon [00:20:01]: For sure.Joon [00:20:02]: In that show, how'd it go?Swyx [00:20:04]: In that show, it was, like a foregone conclusion. They were like, “We know it's bad. We just don't know how bad.” And then the poll came back. It was like, “It's really bad.” And then they just did it anyway.Joon [00:20:14]: Part of it is to show, right? So you're, you're looking at the ideaSwyx [00:20:17]: Maximizing drama.Joon [00:20:18]: How bad could it be? Oh, it's horrible.Swyx [00:20:20]: And to some extent, I think that is part of the trick of the, or the challenge or with being a customer of yours, which is that if I know it's. if I roughly know and can intuitSwyx [00:20:35]: What the effect is going to be, do I need you? What sensitivity of it, of effect do I need in order to make a decision, right? So for example, if I, my approval rating is 50%Swyx [00:20:48]: And I, they have this negative piece, news item comes out, and it drops to 30.Swyx [00:20:52]: If it drops to 20, if it drops to 40, do I care? No. It, I know it drops. It's negative. So when do I care about simulations?Joon [00:21:01]: You do something that's clearly bad, that's not popular, and people don't like you, like, yeah, it's likeSwyx [00:21:05]: You don't need a simulation.Joon [00:21:07]: Yeah. Well, so there are a couple of things. one is, there are use cases where, like every day, developers, designers, policymakers, marketers, every single day, they create assets. They create new products. And turns out, it's many of the decisions in hindsight is obvious. Yes, of course this is bad, but we still run those studies because understanding the magnitude and understanding how acute something is quite difficult, even if, we feel like, of course, like this makes sense. this is the reason why we make so many mistakes. Like, every time somebody goes online and say something that has huge backlash, you look at that and like, “What an idiot.” However, it's tough. That's one. There's also another aspect here, which is, again, this is the reason why simulation is different from prediction. In simulation, in the ideal case scenario. So what simulation is trying to show is it's trying to show each step of the way or each step that we need to take to get to a certain outcome, right? So in the most advanced simulations, sometimes the next step that we're suggesting might be quite counterintuitive. The analogy that I sometimes give, and I ground it in a more realistic example, but, I, as I mentioned, I'm a huge fan of science fiction, and I don't know how, many of the audience members have read, like, things like the Foundation series by Asimov.Simulation as a Path, Not Just a PredictionSwyx [00:22:37]: Oh, yeah. We've mentioned psychohistory a number of times.Joon [00:22:39]: Okay, fantastic. So I might be, talking to the right crew. If you read Foundation series, literally the first act is there's a group of scientists who have found out that, “Oh, our galactic empire is going to collapse, and we're going to have 30,000 years of unrest.” And they run psychohistory, the simulator that tries to teach them, “Okay, how can we keep this unrest to a 1,000 years?” And they plan this out, and the first step of that plan is to get the scientists who say, “Okay, this is coming,” exiled into this random place in this, galax- galaxy.Swyx [00:23:18]: Terminus.Joon [00:23:19]: Exactly. And that's so counterintuitive. Like, what a strange move that you literally sent the group of scientists who was raising voice around this potential collapse of galactic empire into nowhere. How is that the right first move? Well, it turns out in this particular simulation, that was the move.Joon [00:23:40]: It's these things, right? And the reason why these reasoning is possible is because you're showing the step function or each step that results in a particular outcome. So really what simulation allows you to do in its highest form is you give it not a problem or question, like what would people answer to the survey? That's not what we do. What we tell it is, “Here is a goal that we have. In the context of foundation, we want to keep the unrest to a 1,000 years. What is the path that we need to take now to get to that particular future?” And that's what simulation allows you to do. Now, translating that into real market, imagine you're a automobile company and you're about to release a, EV, and you're trying to understand, well, how do we market EV, to make sure that our stock price goes up? But what if the answer comes down that, well, you can market your EV in XYZ way, but that might change people's perception around the cars that's not EV and make your overall sales to go down. Not very intuitive, especially all you're trying to optimize is EV salesss, and that's the only thing that you're tracking, then that might result in a completely wrong solution, or at least different solution than what you would have expected, whether it's right or wrong.Joon [00:24:57]: That's the power of simulation.Swyx [00:24:58]: For listeners, we covered a similar topic with Mikhail Parakhin from Shopify, where they are working on SimGym. I don't know if he ever talked to you about it. it's very similar.Joon [00:25:07]: ISwyx [00:25:07]: The goal is increased conversion, but then the journey is very unusual.Joon [00:25:12]: Journey is unusual.Swyx [00:25:12]: Yeah. The-- He's trying to look for interventions on a shopping trajectory, which is similar to what you're saying. Like, it's not about the attitudinal, is your word for it.Swyx [00:25:24]: It's about behavior.Joon [00:25:25]: It's about behavior.Swyx [00:25:25]: And that's exactly the difference, right? It's, like, not about the near-term direction about-- but it's more about, like, how do you affect multiple turns of interactions.Vibhu [00:25:35]: You had a good quote at the start about this as well. It's not about people wanting to know the outcome. It's about how they can change it, change the way to get there, something like that. But I wanna take it back to how do we know this is grounded? LikeGrounding and Evaluating Digital TwinsVibhu [00:25:47]: How do you run evals? How do you test that simulations come through? if I was to do the same thing that you described with, say, your favorite LLM, Opus, GPT-5.6, have some agent to map out these thingsVibhu [00:26:02]: How different are the answers we would get if I give it the same goal, the same objective, make a decent system? You're saying that you need to change the model weight. You have your own solution to this. But how far off are we, and how do you check if it's grounded? you have some interesting stuff on your site that points to how you run real evals, but if you could take us through that side. I think that's one of the big concerns that people have. They're like, “LLMs hallucinate.”Vibhu [00:26:27]: “You're just hallucinating layer after layer,” right?Joon [00:26:30]: The way we do this, and this is the paper that we worked on after the generative agents paper that really became the, at least for Simile and also the field of simulation and synthetic panels, really became the foundation. Yeah, this is the paper. the paper is called Generative Agent Simulations of 1000 People. Here's what we've done. For this paper, we brought 1,000 people that's representatively sampled from the US to a virtual lab. And what we have done was we spent two hours collecting fairly wide-ranging data. In this particular study, we focused a lot on this interview data, that was, whose script was taken from this project called American Voices Project. And then we would also pair that with a lot of behavior data and so forth, whatever we can collect within two hours. And then we would send these people away for a couple of weeks. And during that time, I would use this data to create their digital twins. And I would bring the humans, participants back after 2 weeks and have them complete a battery of surveys, experiments, behavior studies. So we have the list here, which included things like behavioral economics games. We would run literally, like, Big Five personality test, General Social Survey. We would also go ahead and run the randomized controlled trials that were published on PNAS. And we would have their digital twins predict how the source individuals would have acted in these studies and surveys. And this is where we could replicate people's behaviors and attitudes 85 percent as accurately as people would replicate their own. So that was the first really paper that gave this validated results that we can model individuals in an accurate way. And what we ended up finding now, of course, in AI space, so this paper came out at the end of 2024. AI space, a year and a half, 2 years, that's a lifetime.85% Accuracy and Why Frontier Models Miss Human BehaviorSwyx [00:28:24]: Yeah. Just, for listeners who are not seeing the YouTube, I just wanna say, like, the headline figure is 85 percent accuracy, like, which is a big improvement over all the otherSwyx [00:28:34]: Methods that you showed.Joon [00:28:36]: But the part that was particularly striking to us, especially as we improved this technology even further, was the generative AI models like ChatGPT, Claude that's coming out, it does give you the right foundation. However, what they do not consider is the true attitudinal and behavioral aspect of people, especially in the population that you care about. So what these models are really good at today is they're trying to become the super rational, objective machines, right? So you go get their data from places like Mercor, Scale. You talk to professional programmers, scientists to create model that's amazing at reasoning. That's what they do. Simile doesn't care about any of this. The models that we're talking about here, what we're trying to create are models that are as dumb as I am, right? So if I make some mistakes, the model has to make the same mistake.Swyx [00:29:34]: Oh, that's very hard.Joon [00:29:35]: That's very hard.Swyx [00:29:36]: You're solving Murphy's paradox.Joon [00:29:37]: That's exactly. And this is a completely different data and training objective. This is also where we see quite a bit of discrepancy in the performance in human behavior prediction between the frontier models, Simile's model, and the models being created in this space, where in some cases, the model performance of frontier models go all the way down to 20, 30 percent, especially if you go into that more niche population on topics that our customers would care about. On more gen pop, it might be around 50 to 60 percent. So it's not very robust. Like, you wouldn't want to make your decision off of these and these findings. If you can bring that up to 85 percent, that is ultimately what people end up getting very excited about.Swyx [00:30:20]: Yeah. Do we wanna keep going on the paper, routes?Joon [00:30:23]: Yeah, for sure. So the last one, was an interesting one. So this, paper was the follow-up paper that we had, to the 1000 agents paper, where the idea was now can we augment the models even further and post-train a model based on a lot of randomized controlled trials? So this was an interesting one. The data is always the most interesting part of modeling in many ways. The data that we got here was there's this, there's this platform called Open Science Framework. So some, the audience might be familiar with this. And there has been, especially in the social sciences over the past 5 years or so, there has been this concern around replicability of studies. And so it was a bit of a crisis, the scientists acknowledged, where we rerun the study and we don't see the same finding.Post-Training on RCTs and Replication StudiesVibhu [00:31:12]: Oof.Joon [00:31:12]: It's tough. And the reason why it's there-- that was often the case was there's this survival bias where the papers that get published often need to maintain what we call the value of less than 0.05 in the experiments that we ran. That suggests that only-- there's only 5% chance that the results that we saw is false positive. But the tricky part was all the papers that were not published, and there's still a 5% chance that whatever we publish is totally just randomly generated. Like, there's a 5% chance that, hey, this effect is not real, but it just happened to be real because of the sampling bias. So because of that, what scientists started to do was they started to register their studies. So before running an experiment, they would go to this platform and say, “Here is the data. Here is the population that we're collecting, and here's the hypotheses.” And they would just say, “Here is our hypothesis.” Like, “This is what we believe.” And you cannot retroactively change those hypotheses. This is what gives us more scientific statistical confidence that whatever effect that you ended up seeing is true. So that ended up creating this really interesting platform where there's one platform that has now contains tens of thousands of real-world experiments and hypotheses. And a lot of these are really high-quality, like, professionally designed behavior studies and random- randomized controlled trials. So we got the data and the studies from this platform and used that to make a point. And this particular, model is not, something that we're serving commercially because this was a part of the open science. But this particular data set, helped us make a point that by collecting a lot of these randomized controlled trials, that are really well-designed, we can make significant improvement in model's capability to predict human behaviors. So that's what this paper was about.Vibhu [00:33:10]: Is this stuff done on a individual level? Like, do I need to tune the model per individual, per company? Is there foundation model changes and then some slight post-training? Anything you can share there?Population-Level vs. Individual-Level ModelsJoon [00:33:21]: So this particular model was trained. the data we had at the level of individuals, but this particular model was trained. We experimented with both. And this is what we end up doing at Simile too. We always train 2, distinct model. One is what we call the population-level model. The other is what we call the individual-level model. And both take very similar input, which is the description of a subpopulation or individual and a stimuli. In this particular work, we've done the same. Here, the results that we are reporting are much more geared towards individuals because we do think that is a harder task in many ways, but that's what we have done.Vibhu [00:34:02]: You seen anything on the questions that humans can solve that models can't solve? So likeHuman Biases, Mundane Choices, and What Models MissVibhu [00:34:09]: Currently, it's, I live 5 minutes walk away from a car wash. It's a 10-minute drive. Should I walk or drive?Joon [00:34:16]: Huh.Vibhu [00:34:16]: The model will say, “Oh, walk to the car wash.” And, you don't have your car.Vibhu [00:34:20]: Is anything like this a problem in simulation? You would assume, like, very simple for human to think about, but if the model is saying you should walk to the car wash, anything here?Joon [00:34:32]: It's less, what can we solve, but I think it's more about what biases or mistakes do people make that models miss. Like, imagine that you are, like the. When I was still at Stanford, I lived in Palo Alto. So it's about, I would say, 40-minute walk from the campus. You ask the model, “Okay, let's go home. What can I, what can I do?” It would likely call an Uber or, give me, the bus time. But for the longest time, I really liked walking back. And the reason why I wanted to do that was not for efficiency. It really helped me think. And I like to walk for, half an hour or 40 minutes or so a day, where I just get to, just think about ideas, research, just get lost in my thoughts. That's very human activity. Unless the model has seen that and understands the importance of that activity, it would miss these kinds of features. So that I think, is fundamentally what we're trying to model. Like, what is fundamentally human might not be the most efficient thing to do, might not be the right thing to do, but things that make us who we are.Swyx [00:35:43]: I'm curious if, there are some data sets that you really want that would materially help you. One version of this may be interesting, which is more valuable to you to acquire as a data set, all of LinkedIn, all of Twitter, all of Facebook?What Data Matters: Social Media, Transactions, and FacebookJoon [00:35:57]: It's a little bit hard to rank, in part because, there's, there's this product saying where no feedback is wrong because it teaches you something about your users. Doesn't matter what feedback.Joon [00:36:11]: I think it's a little bit like that.Swyx [00:36:12]: So just whatever is bigger.Vibhu [00:36:13]: What about a different domain? Say it was. What about all of Amazon data?Joon [00:36:17]: Oh, yeah.Vibhu [00:36:18]: Shopping data, right?Joon [00:36:18]: Shopping data. So Amazon data is interesting in that it's very much behavioral, although, like, what people do on social media, you could squint and say that is also behavioral. But the transaction data is always interesting. It is also most commonly available, however.Joon [00:36:33]: If we were to look at purely social media, like if you really, if I were, if I had to really pick, Facebook likely is interesting because I do think it is most a default version of people. Because you go to LinkedIn, it's very much professional environment. So people put up their, they have their guards up, right? And that still is interesting because that is true human attitude and behavior, but it is not your base state. you go to Twitter- Twitter, people have their own crazy personas, or depending on who you are. Like, my Twitter profile and, persona is very much, initially was I was very much an academic. “Hey, I'm here to share my studies.” Now, I share, things that's related to Simile. But Facebook is one of those more private space where people just connect with their friends. In that way, I do think it shows you a little bit more about who that person is. So if I had to pick, I'd likely pick, Facebook.Swyx [00:37:30]: Yeah. And you're interested in, like, the whole person and their background and philosophy. I, is it too clinical or too machine learning-oriented to just say this is just ways to inject variance and biases? The broad question, is, like, is this any better than a randomized, like, combinatorial explosion version? So we have a link to the TencentBillion Personas, Synthetic Demographics, and Bespoke DataSwyx [00:37:54]: Billion persona paper, where they did not do any of the groundwork that you are doing.Swyx [00:37:59]: They just did like a cross matrix of here's all the professions in the world, here's all the people, possible backgrounds in the world, do a dot product across all of them, and that's it. That's your prompt for a billion people.Swyx [00:38:12]: This will do something. I don't know if it'll do what you do, but it gets you some way, some percent of the way there.Joon [00:38:18]: So this was an interesting paper. Like, what I admired about this paper when it came out was the scale. And you do gradually want to be able to simulate really large societies and interactions. So the scale is definitely admirable. it is relying heavily on the known statistics that went into training the model. So to the extent that you believe that statistics is correct, this is not a bad way to go about this. But the thesis here, and this is something that we also have seen in the market, like if this works, then we have solved simulation.Joon [00:38:54]: It,Swyx [00:38:55]: Because I survey, like, okay, 5% of the US population is in construction.Swyx [00:39:01]: The other 5% is in medicine, whatever, right? And then you just keep going down the list, and then you do the other side. 5% has, like, the big 5 personalitySwyx [00:39:08]: Of, like, neurotic or whatever. That's it.Joon [00:39:11]: That's it. So if you believe that the underlying data set and the platform that we're leveraging has all the right statistics, then this will have solved it. you're at that point merely retrieving the knowledge that is already embedded in the model, in the model parameters. That's not, unfortunately, what we see, where there is such detailed and also niche knowledge about people that if you just take one example, it might feel very mundane, but it's quite rich when you put together, that you do need to do a lot of bespoke data collection to better understand people. And this is also, I think what makes this particular, job fun, which you want to deeply understand people, and the process of deeply understanding them requires a lot of attention to the details. And you do need to pay attention to and pay respect to the daily lives that people lead.Scaling Simulation: From Thousands to SocietiesVibhu [00:40:04]: I wanna talk about scaling simulation.Vibhu [00:40:07]: So what can't we simulate, what can we simulate, and how does scaling affect this? So how big are the models? What if we go from, 8B, like, couple 100 billionVibhu [00:40:18]: Like billion000 parameters, billion000? Do we get scaling? Any interesting emergence? Like, at a certain scale, at a certain amount of training, you uncover anything unusual and any learnings from that?Joon [00:40:31]: What we are seeing is at Simile, so we do post-train our own model. The thing that we're seeing is the early glimpse of scaling law in simulations. The more data about humans and more compute you ingest, you start to get predictive and predictable gains of the model performance in simulating it, simulating people.Vibhu [00:40:51]: Ooh. We need a scaling law curve.Joon [00:40:52]: It's scaling law. Whenever you find it's a beautiful thing. And we're starting to see the glimpse of it, which is quite exciting. But if you talk about the ambition of simulation as a whole, it's not merely about building a model. It's about building a model, then creating the agents that become the individuals in a much larger ecosystem. So they're creating this multi-agent simulation. Down the line, you want these multi-agent simulation to also live in a very rich environment, right? What we are really trying to get to at that point is, hey, can we create. All right, let's do a time machine game again, and 5 years, 10 years into the future, can we create a simulation of 8 billion people living on Earth? I think that's quite interesting. And that really is the vision. And once you get to that state, the questions that you can help answer for the society also start to change from my perspective. The answers are fundamentally about emergence of the emergent behavior of society and large groups of people.Joon [00:41:53]: So the questions that I get excited by, and maybe this is a stodgy- a bit. I have my, academic side of me.Joon [00:42:01]: And for me, it's questions like, can we help solve climate change? If you look at climate change as a problem space, this is what we, like social scientists would often call it the wicked problems, problem where you have many actors with competing incentives for trying to make a very complex decision and coordinating that coordination decision. Very difficult to really solve in real life, which is also the reason why we couldn't solve it. Can simulation help us solve that? Another one is, can we understand the signals for collapsing democracy, or can we understand or can we uncover the origin story of the monetary system? These are societal questions that we never really had a good way of answering. If we can create simulations of our society, you have to believe that these are the problems that we can solve. So that's really the ambition of this field. And, I also think, yes, I think there's a Nobel Prize to be won there, which wouldn't be surprising. And I think there's some amazing societal impact that we can have to help people make better decisions.Climate Change, Democracy, and Societal SimulationSwyx [00:43:04]: Nobel Prize in economics?Joon [00:43:06]: In economics.Swyx [00:43:06]: Oh, I see. I see. Rooting for you to write that paper.Joon [00:43:10]: One of these days. But, one of the scholars that I was deeply inspired by, When I was coming into the space of simulation, is this scholar, named Thomas Schelling.Schelling, Agent-Based Models, and the Nobel PrizeSwyx [00:43:23]: Schelling point?Joon [00:43:24]: So the canonical example of the work that he's done was he was one of the creators of agent-based modeling. So this was, like, in the 1970s and 80s. It's very early days, but this was truly one of the first exemplars of simulations. And one of the canonical model from that time, and of course many of these simulations are trying to tackle the societal problems that's most relevant for their era, it was called the model of segregation. So racial segregation was a big topic, that, we cared about. And what they've done was they created this grid world where they had red dots and blue dots. And these dots were, back in the day, like, they were the agents, and they had a simple rule that governed their behavior. If certain percentage of your neighbors are of different color and if that goes above certain threshold, then you move to a new location at random.Joon [00:44:21]: One of the striking finding of this paper or this agent-based model was for the longest time, people thought the segregation within society was caused by explicit and overt racism.Joon [00:44:34]: But if you look at this model, people's preference towards living with people of the same color, that preference can be very minute.Joon [00:44:42]: But the very small difference causes the society to segregate completely over time. This was very counterintuitive for a lot of people. And this particular work ended up informing housing policies. Mixed income housing, got really inspired by this work. And Thomas Schelling ends up winning the Nobel Prize for having laid the groundwork for very early versions of simulations. The opportunity that I do see here in the more scientific terms, is agent-based models for the longest, had impact in the 1980s, 90s, to some extent, early 2000s, but it has now gotten forgotten by the community a little bit. Because as you can imagine, red dots and blue dots is not really a rich description of people.Joon [00:45:31]: But with the emergence of things like generative AI and, in particular, generative agents, we do have an opportunity to create these agent-based models that are high fidelity enough to help us make really complex decisions. And that's the opportunity that I see. If that truly works, then yes, that is the work that will result in a Nobel Prize.Swyx [00:45:53]: Yeah. For what it's worth, and I grew up in Singapore. 80% of Singapore is in public housing, and public housing has, enforced racial quotas for exactly that reason, which is very interesting. okay, so we talk about scaling, we talk about all these, the agent possible applications.Cost, Reuse, and the Economics of SimulationSwyx [00:46:13]: I'm scared about the cost. if you even-- let's just keep it to the US, about 8 billion people.Swyx [00:46:21]: But, how much does it cost to model so many hundreds of millions of people?Joon [00:46:26]: Oftentimes today, we don't start at that scale, this stage of the, of industry and simulation as technology. But we can get our users extremely rich and meaningful insights even by modeling thousands, tens of thousands of people. And today what we do is every week we are collecting data on the scale of tens of thousands people's data, and we have panel partnerships that gets us to tens of millions of people globally. So that's what we do today.Swyx [00:46:55]: And just as a side note once you've collected one person for one studySwyx [00:46:59]: Can you reuse that same person for all the subsequent studies?Joon [00:47:03]: That's exactly right.Swyx [00:47:03]: Okay.Joon [00:47:04]: The beauty of this model and these agents is the fact that they are domain-agnostic.Joon [00:47:08]: That what you're really trying to understand is what is the fundamental nature of these people? What's their social physics? And there are a lot of, a lot of, people that does change over time. Like, even, like, even things like, how many times have you gone have you been to, like, CVS the past week? that will change. But there's so many traits about people that are also known to never change. Like, your risk tolerance doesn't really change over time. It's very consistent. So it's these things that we're trying to learn. But the scale we are operating is right now hundreds or, tens of thousands to hundreds of thousands. And in many of the core use cases that we are deployed in, and this is more than enough population, to cover those. Really, at that point, what you care about is less the number of people, but more do you have the right subpopulation of interest covered? And this is also the reason why people want a larger sample. It's not because they want, stronger statistical guarantees. It's more that can they filter down to any population of their interest. However, you can also imagine in 10 years, if we truly believe that the compute is going to scale, that we'll have much more availability for compute, and our ambition for simulation is also going to scale accordingly, there's definitely a reason for us to create an entire data center worth of simulations.Joon [00:48:35]: Or in my hunch here is I do think in the next some number of years, we will start creating simulations that will cost as much as training a foundation model. But perhaps it's going to be so valuable to the society that it would be a no-brainer. Right now, even today, like, we are training bunch of new foundation model just so we can say we trained one and we spent tens of millions. But if we can create a simulation at the level of society that would solve climate change, I would run that today. I would raise the money right now just to run that.Multi-Agent Simulation and Social InfluenceSwyx [00:49:10]: Amazing. the follow-up question is, does it also compound if you let the simulations talk to each other?Swyx [00:49:18]: Or do they already do that today? They don't, right, as far as I understand?Joon [00:49:22]: It depends on what simulation you're trying to run.Joon [00:49:24]: In the multi-agent simulation setup, the agents do talk to each other.Swyx [00:49:28]: Right, which is exactly Smallville, right?Joon [00:49:29]: That's right.Swyx [00:49:30]: But a lot of times, for example, in commerce, you're just by yourself, so there's no point talking. which is way cheaper.Vibhu [00:49:37]: But they use all these levels, right? Like, you decide what you will buy based on what other people around you buy and talk about, right?Swyx [00:49:43]: It depends.Vibhu [00:49:44]: It depends.Swyx [00:49:45]: Again, I'm, I'm coming at this from a cost point of view. I'm like, “Oh my God.” LikeVibhu [00:49:48]: I thinkSwyx [00:49:49]: If there is, like, some combinatorial thing of, like, thousands of people talking to thousands of people, then that one million X's might cost.Vibhu [00:49:56]: I have a very different view as the cost point aside. Like, running these studies in reality is a lot more expensive, right? Running any study like this is you gotta have people do it, you gotta sign people up. It's very expensive and sometimes, like, not feasible to run the study.Vibhu [00:50:14]: But the outcome or the decisions you make are very expensive on them, right? So spend X million on something that, the overall process costs 100 million might as well, right? There's, there's a lot of value to be had there. It's a small cost, but I'm excited on the cost side.Joon [00:50:33]: To some extent, and when you deploy technology, you often want to deploy in a way where you can replace existing budget or you can make things more efficient, and that is the best way to deploy. However, the way you capture the long-term value of the technology is making the argument that, no, it's the upside, that by making this better decision using simulation, you have saved yourself or made yourself hundreds of millions or even billions of dollars, and that's a case to be made.Vibhu [00:51:06]: Random tangent question. So if you're doing a lot of inference, a lot of model multi-agent stuff, are you at the point where it makes sense to, train a model that' very sparse? You're expecting to do multi-million dollar runs. Are you thinking about this in model architecture standpoint or inference efficiency, or, you're still at the research phase of it works, we're not super there yet?Joon [00:51:34]: Efficiency, we do think quite a bit about. this is technology that is deployed now in some of the largest enterprise companies in the world, and we do process significant number of queries, that are trying to, simulate the populations in the world. So efficiency is a consistent thing. we don't want to over-optimize too early, so I wouldn't say, like, this is the higher bid Right now, but this is definitely something that we think pretty carefully about.Swyx [00:52:05]: Yeah. Are there other case studies? So we, you talked about CVS, talked about Gallup, Deloitte, Wealthfront.Efficiency, Enterprise Use, and Real-World Case StudiesJoon [00:52:12]: Wealthfront is an interesting one, because one of the things they were trying to do, they were one of the first customers that wanted to do product testing that goes beyond just asking people what they think about, let's say, behavior experiments and so forth. So there, really what we had to do was reason about multimodal input, so images, but also you can also imagine, like, these agents traversing through Figma mockups or websites. So some of the things that our agents can also do is it can be given a domain, like, or, like, a website URL and go use it for a while. It's these things. And Wealthfront was one of the first, customers, that was very excited about this possibility.Vibhu [00:52:53]: What have people been asking? Like, is there any demand that we have not covered? Like, UI testing, right?Vibhu [00:52:59]: I wanna try a new. I wanna ship a new feature, test the UI, simulate how people will do it. Any interesting things that you're seeing demand for?Product Testing, Websites, and Synthetic PanelsJoon [00:53:08]: Today, a lot of the demand does come from like, the places where people have historically used human panels, we can now replace with agents, and these synthetic populations. And this is not replacing human panel. in many ways, the simulation that Simile is building is grounded. So the way that I think about this is we are trying to represent humanity at scale. And in that way, the use cases are what we would expect, but it's the scale of deployment that surprises me.Joon [00:53:44]: Turns out there are so many decisions that people make every day in these organizations, groups, and we want to be able to say, “We listen to people. We have consulted our users.” But in reality, that is rarely the case because getting to people and asking them many questions, it's difficult. It's both costly, time-consuming, but most importantly, people are just not available. If I had to answer 1000 survey questions for this one particular, vendor, even if I wanted to do that, like, I would never do it. And that's very much the case. What simulation can do is ensure that the voices of people are always represented in rooms where the decisions for them is made, right? So all the stakeholders of this particular product launch, ideally they're consulted. That's what this technology really is trying to enable.Market Size, TAM, and Human Decision-MakingSwyx [00:54:39]: In my mind, that means it skews towards more consumer focus, right? Like, anything with a wide enough customer base where you do benefit from the diversity that you represent. What are some rough statistics, just for people who are not familiar with this market in general, what's the market size that. I'm sure you have some, like, rough numbers. market size is, like, a vague questionSwyx [00:55:01]: But, like, how much do people spend?Joon [00:55:03]: So market research is a $100 billion industry.Joon [00:55:06]: But the thing about simulation is not a tool for market research. Simulation is a tool for human decision-making. So the question around what is a TAM here is quite tricky, right? Because it's easy to say, “Well, market research TAM is roughly 100 million or 100 billion.” so is it a TAM? And not really, right? Because in many ways, you're trying to inform all human decision-making. You're trying to inform every decision that are made about humans for humans. What is a TAM for that? It's really unclear. And I'll be honest. Like, I have a scientific background, I have a research background, so I didn't come into the field calculating, oh, what is the TAM for human decision-making? But I just had to assume, well, if we can inform every decision that is made about human for human, that has to be big.Swyx [00:55:58]: Some- something valuable.Joon [00:55:59]: Exactly.Swyx [00:55:59]: To some extent, you are a unicorn founder now, and you have to care as a CEO. But, like, I do think, like, yeah, when you go into these boardrooms with people that you're quoting millions of dollars of contracts for, like, you have to say, “Well, here's what you spend on humans-”Swyx [00:56:15]: “. And here's what we save you, and it's 85% similar.”Joon [00:56:19]: And certainly, the value case, is something that we care deeply about. Like, what is the value that we provide to the users and the decision-makers? But this is also where, like, as a founder, I think valuation only tells one very superficial aspect of the story, and I try not to think too much about valuation, in general, because that's not what also motivates a team or certainly doesn't. I'm, I-- Again, the interesting thing about researchers is we are happy living in academia, getting paid next to. we get paid okay. we don't get paid that much, as a researcher here in academia, but it's the impact and it's the, it's the value that we can provide to the individuals and the society that really drives us. And in that way, ultimately what drives us is the impact. Does the simulation we provide have a real impact in people's decision-making in ways that progresses our society forward? If the answer is yes, then yes. that has to be great business, and we see that in numbers, and we do care deeply about that upside story, but that's the heart of it.Where Simulation Goes NextVibhu [00:57:27]: Do you have any timeline predictions? So we talked about scaling laws of simulations.Vibhu [00:57:33]: You brought up, okay, maybe one day we can simulate how to solve climate change.Vibhu [00:57:38]: Where are we now?Vibhu [00:57:40]: If that's not the end state, what is an end state, and what does progress look like?Joon [00:57:45]: So what I sometimes tell people is simulation as industry, it feels a lot like where GPT-3.5, GPT-4 was, for the AGI saga, which is we have now technology that is powerful enough to do real damage on the verticals that we are tackling. At the same time, there's a lot of progress that is yet to come. And that's, I think, where this is. So the way I see it, I do think there will continue to be breakthroughs both in data, in algorithms, and there will be much more aggressive scaling that will also happen over the next few years. But I think that's roughly where we are.Swyx [00:58:27]: I think that was about the ro

Welcome to the History Guy Podcast: Counterfactuals. What is a counterfactual? At it's most basic, it is a ‘what if'. It's a way of understanding history as it is by discussing what it could have been. Today we talk about a 1944 supreme court decision that fundamentally altered the American electorate and set the stage for civil rights victories that culminated in the Civil Rights Act: Smith v. Allwright.

ABC:LHS #089-6 OPTIONAL COUNTERFACTUAL... ...history of the United States when I asked CoPilot to create a country that abolished slavery at its beginning and then limited immigration. It gave me a startling picture of an unrecognizable country.    This section is almost exclusively generated by CoPilot.

Welcome to the History Guy Podcast: Counterfactuals. What is a counterfactual? At it's most basic, it is a ‘what if'. It's a way of understanding history as it is by discussing what it could have been.On today's episode we talk about the deadliest accident to ever strike a presidential cabinet: the explosion of the cannon on board the USS Princeton in February, 1844. The explosion killed both the Secretary of State and the Secretary of the Navy, and fundamentally changed the trajectory of the era.

On today's episode, we talk about an event often thought to have ended the “High Renaissance” period: the sack of Rome by a mutinous contingent of German and Spanish mercenaries in May, 1527. Often forgotten, it had a profound impact on history.

Welcome to the History Guy Podcast: Counterfactuals. What is a counterfactual? At it's most basic, it is a ‘what if'. It's a way of understanding history as it is by discussing what it could have been.Today, we talk about one of the deadliest diseases in human history, and one we often don't think about at all today: Rabies. How has it changed the world, and what might be different without it?

Star Wars fans love to debate whether controversial characters are sorely misunderstood or rightfully condemned, and we at Hoth Takes are not immune to that temptation. In this episode, Eric and Grace each present a character they think deserves to be reconsidered. Our conversation delves into Star Wars's trickiest moral and metaphysical issues — light and dark, fate and free will, emotion and logic, child soldiers and clone servants. If you enjoy exploring gray areas, this episode is for you!

On today's episode we talk about an unsung hero of the modern age: the elevator. Without them, the world wouldn't be the same. 

آیا تصویر سنتی ما از DNA به عنوان یک «دستور پخت خطی» یا «بلوپرینت فیکس‌شده» از نظر علمی دقیق است؟ زیست‌شناسی مدرن چگونه از پارادایم ژن‌محوری (Gene-centrism) به سمت درک سیستم‌محور (Systems Biology) و کل‌نگر حرکت می‌کند؟در این قسمت از پادکست هشیوار، میزبان دکتر عطا کالیراد، زیست‌شناس تکاملی و پژوهشگر مؤسسه ماکس پلانک آلمان هستیم. در این گفتگوی عمیق، لایه به لایه از تقلیل‌گرایی کلاسیک فراتر می‌رویم تا با رویکردی تحلیلی، تلاقی مفاهیم فیزیکی، شیمیایی و فلسفی را در تبیین تکامل و تکوین موجودات زنده بررسی کنیم. اگر به دنبال درکی ریشه‌ای از چالش‌های پیش‌روی نئوداروینیسم و پارادایم‌های جدید علم حیات هستید، این گفتگو برای شماست.#

On today's episode we talk about a man whose influence on the trajectory of American history is undeniable and pervasive, but whose name you may never have heard of: John Hay, a secretary to President Lincoln and Secretary of State under Mckinley and Teddy Roosevelt. What might the world be like without him?

This is a free preview of a paid episode. To hear more, visit www.splitzoneduo.comHost emeritus Steven Godfrey joins Richard and Alex for a look back at the Big 12's extremely public flirtation with expansion a full decade ago. It was a strange spring and summer in 2016, as the Big 12 basically put on realignment tryouts for a long list of schools including several (BYU, UCF, Houston, and Cincinnati) who did get into the conference — but not until years later, when others dominoes had fallen. Let's revisit the summer of realignment that wasn't, and then let's think about how it changed the next decade of college football.In this episode:* 0:00: Why the realignment fashion show became so public* 8:10: The now-quaint factors that drove realignment decisions back then* 12:28: The candidate pool, including Houston and Cincinnati's very different campaigns, BYU's many complications, UCF before the Scott Frost/Josh Heupel run, and SMU before it became an ACC playoff team* 32:02: Why the process came down to BYU, Cincinnati, and Houston. (Also, why the Big 12 was genuinely scared of Houston)* 43:48: Counterfactuals: whether earlier expansion would have changed Texas and Oklahoma's exit, the Pac-12's collapse, or the expanded playoff's politics around non-power teams* 56:08: The afterlife of the public audition, from Memphis and Sacramento State to the next round of conference-movement anxiety.Everyone can hear a free preview of this episodeTo get the whole thing, become a paid subscriber today. For $10 a month (or you can get a free month with an annual subscription), subscribers get about twice as many Split Zone Duo podcasts, as well as our coach carousel reporting, deep dives on college football history, Q&A opportunities, and many more goodies as we think of them. You also help keep this show independent and ensure we're making a podcast that puts our listeners, not anyone else, first.Producer: Anthony Vito

On today's episode we talk about a pivotal battle in a poorly remembered war: The battle of Paardeberg in the Second Anglo-Boer War. The war would consolidate all of South Africa under British Colonial rule, and radically transform the Canadian military. But what if it didn't?

On today's episode, we talk about a little remembered campaign of the Civil War fought west of the Mississippi, when a former Missouri governor attempted to shake things up as hope for the south dwindled. Ultimately it all went wrong - but what if it didn't?

Early bird discounts for the San Francisco World's Fair, the biggest AIE gathering of the year, end today - prices will go up by ~$500 tonight so do please lock in ASAP!From near-universal AI tool adoption inside Shopify to internal systems for ML experimentation, auto-research, customer simulation, and ultra-low-latency search, Mikhail Parakhin joins us for a deep dive into what it actually looks like when a 20-year-old, $200B software company goes all-in on AI. We cover why Shopify has become much more vocal about its internal stack, what changed after the December model-quality inflection, and why the real bottleneck in AI coding is no longer generation, but review, CI/CD, and deployment stability.We also go inside Tangle, Tangent, SimGym, which are three major AI initiatives that Shopify is doing to make experimentation reproducible, optimization automatic, customer behavior simulatable, and search and catalog intelligence faster and cheaper at scale. Along the way, Mikhail explains UCP, Liquid AI, and why token budgets are directionally right but often measured badly, why AI-written code can still increase bugs in production, what makes Shopify's customer simulation defensible, and what he learned from the Sydney era at Bing.We discuss:* Mikhail's path from running a major Microsoft business unit spanning Windows, Edge, Bing, and ads to becoming CTO of Shopify* Why Shopify is talking more publicly about AI now, and why staying at the frontier has become necessary for the company* Shopify's internal AI adoption curve, the December inflection, and why CLI-style tools are rising faster than traditional IDE-based tools* Why Jensen Huang is directionally right on token budgets, but raw token count is still the wrong way to evaluate engineering output* Why the real unlock is not more agents in parallel, but better critique loops, stronger models, and spending more on review than generation* Why AI coding can still lead to more bugs in production even if models write cleaner code on average than humans* Why Shopify built its own PR review flow, and why Mikhail thinks most off-the-shelf review tools miss the point* How PR volume, test failures, and deployment rollback are becoming the real bottlenecks in the agent era* Why Git, pull requests, and CI/CD may need a new metaphor once code is written at machine speed* What Tangle is, and how Shopify uses it to make ML and data workflows reproducible, collaborative, and production-ready from the start* Why Tangle is different from Airflow, and why content-addressed caching creates network effects across teams* What Tangent is, and how Shopify is using auto-research loops to optimize search, themes, prompt compression, storage, and more* Why Tangent is becoming a democratizing tool for PMs and domain experts, not just ML engineers* Why AutoML finally feels real in the LLM era, and where auto-research still falls short today* Why Tangle, Tangent, and SimGym become much more powerful when combined into one system* What SimGym is, why simulated customers only work if you have real historical behavior, and why Shopify's data gives it a moat* How SimGym evolved from comparing A/B variants to telling merchants what to change on a single live storefront to raise conversions* Why customer simulation is so expensive, from multimodal models to browser farms to serving and distillation costs* How Shopify models merchant and buyer trajectories, runs counterfactuals, and thinks about interventions like discounts, campaigns, and notifications* Why category-level behavior is so different across commerce, and why ideas like Chinese Restaurant Processes are showing up again in practice* Shopify's new UCP and catalog work, including runtime product search, bulk lookups, and identity linking* Why Shopify is using Liquid AI, and why Mikhail sees it as the first genuinely competitive non-transformer architecture he has used in practice* Where Liquid already works inside Shopify today, from low-latency query understanding to large-scale catalog and Sidekick Pulse workloads* Whether Liquid could become frontier-scale with enough compute, and why Shopify remains pragmatic and merit-based about model choice* Who Shopify is hiring right now across ML, data science, and distributed databases* The Sydney story at Bing, why its personality was not an accident, and what Mikhail learned from deliberately shaping AI character early onMikhail Parakhin* LinkedIn: https://www.linkedin.com/in/mikhail-parakhin/* X: https://x.com/MParakhinTimestamps00:00:00 Introduction: Mikhail Parakhin, Microsoft, and Shopify00:01:16 Why Shopify Is Talking More About AI00:02:29 Internal AI Adoption at Shopify and the December Inflection00:06:54 Token Budgets, Jensen Huang, and Why Usage Metrics Can Mislead00:10:55 Why Shopify Built Its Own AI PR Review System00:12:38 AI Coding, More Bugs, and the Real Deployment Bottleneck00:14:11 Why Git, PRs, and CI/CD May Need to Change for Agents00:18:24 Tangle: Shopify's Reproducible ML and Data Workflow Engine00:21:19 Why Tangle Is Different from Airflow00:26:14 Tangent: Auto Research for Optimization and Experimentation00:30:07 How Tangent Democratizes Experimentation Beyond ML Engineers00:33:06 The Limits of Auto Research00:36:36 Why Tangle, Tangent, and SimGym Compound Together00:37:20 SimGym: Simulating Customers with Shopify's Historical Data00:42:47 The Infra Behind SimGym00:46:00 Why SimGym Gets Better with Real Customer History00:47:30 Counterfactuals, HSTU, and Modeling Merchant Trajectories00:51:55 CRPs, Clustering, and Category-Level Customer Behavior00:53:30 UCP, Shopify Catalog, and Identity Linking00:55:07 Liquid AI: Why Shopify Uses Non-Transformer Models00:59:13 Real Shopify Use Cases for Liquid01:03:00 Can Liquid Scale into a Frontier Model?01:09:49 Hiring at Shopify: ML, Data Science, and Databases01:10:43 Sydney at Bing: Personality Shaping and AI Character01:13:32 Closing ThoughtsTranscript[00:00:00] swyx: Okay. We're here in the studio, a remote studio, with Mikhail Parakhin, CTO of Shopify. Welcome.[00:00:08] Mikhail Parakhin: Thank you. Welcome.[00:00:10] swyx: I don't even know if I should introduce you as CTO of Shopify. I feel like you have many identities. Uh, you led sort of the, the Bing ML team, I guess, uh, uh, or ads team. I, I don't know, I don't know, uh, you know, it's, uh, people va-variously refer you as like CEO or, or, uh, I don't know what that, that, that said previous role at Microsoft was.[00:00:29] Mikhail Parakhin: Uh, that was... Yeah, my previous role w- at Microsoft was the-- I actually was the CEO of one of Microsoft's business units, which included, as I, you know, as we discussed, all the things that people like to laugh about, uh, including Windows and Edge and Bing and ads and everything.[00:00:47] swyx: Yeah, yeah. What a, what a, what a wild time.You've obviously, uh, done a lot since you landed at Shopify. Uh, one of the reasons I reached out was because you started promoting more sort of internal tooling, uh, primarily Tangle, but also a lot of people have seen and adopted Tobi's QMD, uh, and obviously, I think, uh, Shopify has always been sort of leading in terms of, uh, engineering.I think more-- it's just more recent that you guys have been more vocal about your sort of AI adoption. Is that, is that true?[00:01:16] Mikhail Parakhin: Well, I think AI tools in general are fairly recent development, uh, and we've-- Shopify, you know, at this stage of its development, we're developing AI in-in-house and other, uh, building tools that use AI and, you know, interfacing with the wider AI community, uh, you know, are on the sort of the, uh, runaway trajectory.So it just did by sort of natural byproduct. We, we talk about it more also. We just, uh, just even yesterday, Andrej Karpathy was famous in tweeting about, oh, are there some, uh, ways, uh, that, that you can organize your agents to store the data and then, uh, look up the data so that you don't have to research or, or lose context every- Yestime. And a little bit tongue in cheek, I tweeted that, “Hey, we've, we've done it much earlier, and we even have different approaches, Tobi and I.” Tobi, of course, is a big fan of QMD, and I'm more of a SQL, SQLite fan. But, uh, yeah, very similar things that we've already done here. The point is, yeah, we're very dynamic, you know, explosively growing company, and we have to be at the forefront of AI adoption, obviously.[00:02:29] swyx: Yeah. Yeah. Um, you, your team kindly prepared some slides actually that we were gonna bring up on to, uh, the screen. I think I can, I can screen share, and then we can kind of go through some of the shocking stats that maybe, maybe put some numbers to what exactly is going on. So here we have, uh- An internal AI tool adoption chart.What are we looking at here? What ?[00:02:54] Mikhail Parakhin: Yeah, this is very interesting statistics. Uh, this is number of daily active workers, you know, think of, uh, DAO, basically the active users of-[00:03:05] swyx: Yeah ...[00:03:05] Mikhail Parakhin: AI tool as a percentage of all the people in the company, right? And then- Yeah ... different AI tools. And, uh, you could see two things here is that one is the green is total.Uh, green is just total. So you could see that it approaches really % by now. It's hard not to do your job now without interacting deeply, at least with one tool. You could see another interesting thing is just as many people commented in December was the phase transition when suddenly models gotten good enough that, that everything took off and started growing.Uh, it, it was many people noticed that the thing is that small improvements accumulated into this big change in Sep- December roughly timeframe.[00:03:52] swyx: Yeah.[00:03:52] Mikhail Parakhin: The other thing I would claim you could see is that, uh, CLI-based tools and tools that don't require you to look at the code becoming more popular, and you could see, yeah, various versions of, uh, Cloud Code and Codex and Pi and internal development tools taking off.Uh, exactly, yeah, uh, and blue is our River, just internal agent for coding, where tools, uh, that require IDEs such as, uh, GitHub, Copilot or Cursor, they're not exactly shrinking, but they're not growing as fast. Like, uh, red, red line is, is the IDE kind of tools. So you could see that they're, they're not experiencing as, as fast of a growth.[00:04:37] swyx: As I understand it, basically, every employee has their choice, right? Of choose whatever tool you use, and then you're just kind of doing a, a daily sur-survey or something.[00:04:47] Mikhail Parakhin: Exactly. And, uh, we- Yeah ... the, the push is to get your job done, you can use any tool, and we effectively fund unlimited tokens for everybody.Uh, we, we do, we do try to control the models that, uh, people use, but from the bottom, not from top. Like we basically say, “Hey, please don't use anything less than Opus four point six.”[00:05:09] swyx: Oh .[00:05:10] Mikhail Parakhin: Some people, some people end up using GPT five point four extra high. Some people use Opus four point six. Um, uh, you know, uh, there are some, uh, there are plus and minuses in going for full one million context window versus not.But, uh, we try to discourage people from using anything less than that.[00:05:28] swyx: Yeah, yeah. Got it, got it. Uh, I mean, uh, that's, you know... The, the next chart here, it really kind of shows the expansion and the sort of December twenty twenty-five inflection, right? That, uh, people are using a lot of tokens. I think it's also really interesting that no one was kind of abusing it in twenty twenty-five.Like it was- Had comparatively, uh, to this year, there was almost no growth. I mean, it's still like, you know, probably, probably gave fifty percent.[00:05:56] Mikhail Parakhin: Yeah. This is just a different scale. It's still exponential- Yeah, yeah ...growth at just a different- ...rate of expansion. Uh, there was inflection point, and Sean, I would claim the, the super interesting part here is that you could see that the distribution becoming more and more skewed.Yes. The top percentiles grow faster. So that means- Yeah ...the people in the top ten percentile, they, their consumption grows faster than seventy-five and so forth. So, uh, the distribution skews more and more towards the highest users, which is... I don't know what it tells me. It's like it feels not ideal, to be honest.Or maybe it's okay. We'll see.[00:06:36] swyx: Why does it feel not ideal? Is, is it because of, um, quantity over quality, or what's the concern?[00:06:42] Mikhail Parakhin: Because take it to the limit. That means, you know, if, if this rate of separation continued- Ah, yes ...a year, there will be one person consuming all the tokens. So it's just, it's kinda strange.[00:06:54] swyx: Yeah, I mean, um, uh, I, I think internal like teaching and all that, uh, will, will help sort of distribute things more widely. But in, in the early days, of course, the people who are sort of more AI-pilled will obviously find more ways to use it than the people who are less AI-pilled. Maybe let's, let's call it that.I'll just, I'll just kinda quickly, uh, pause from the, the... You know, we will go back to the rest of the slides, but I just wanna, um, review, you know, there are a lot of CTOs of, of large companies like yourself where they're all considering some kind of token budget, right? Like I think it's something, something that Jensen Huang has been talking about, where like if your 200K engineer is not using 100K of tokens every year, like they're, they're underutilizing coding agents.Of course, Jensen Huang would say that, but like it seems a very quantity over quality approach and like some, some people are basically saying like, well, is this comparable to judging engineer quality by lines of code, right? Which we also know is like kind of flawed, but better than nothing. So I, I don't know if you have like a sort of management take here on, on how to view this kind of, uh, metrics.[00:08:02] Mikhail Parakhin: Well, I mean, you're, you're baiting me. I, I like... This is my favorite topic. Uh, if you let me, I'll probably talk for two hours on just this. I have a lot of things to say. Like I do think Jensen gotten a lot of bad press saying, “Oh, of course you're, you know, this, uh, the- ...the cake seller says you don't need enough cakes.”You know? Like, of course. Uh, but, uh, I actually, uh, think that's undeserved. I think he, he's actually right. Uh, I do think- He,[00:08:33] swyx: he's directionally correct.[00:08:35] Mikhail Parakhin: Yeah. Yeah. He's directionally correct for sure. Uh-[00:08:37] swyx: Who knows what the right number is? Yeah.[00:08:39] Mikhail Parakhin: The thing that I do Uh, want to say, and this is something that we learned through trial and error and very important is like two things.One is that it's not about just consuming tokens. Uh, you can consume tokens and, and in fact, the anti-pattern is running multiple agents, too many agents in parallel that don't communicate with each other. That's almost useless, uh, compared to just fewer agents and burns tokens very efficiently. Uh, setting up the right critique loop, especially with the high quality models, where one agent does something, the other one, ideally with a different model, critiques it, uh, suggests ways to improve it, the agent redoes it with this critique and, and so it takes much longer.So people don't like it because latency goes up. You know, they, they have to wait until this debate is happening. But, uh, the quality of the code is much higher. And another thing, just since you mentioned like, look, uh, uh, yeah, the overall budget is just like, uh, lines of codes. Lines of codes are exploding for everybody right now, or partially because AI is really mover balls, but partially just because AI can write a lot more code, you know, doesn't get tired.And so you have to have to have a very strong narrow waist during PR review. Otherwise, just the number of bugs will go through the roof. It's, uh, it's this unexpected consequence of the just volume trumping everything. I would claim by now good model writes code on average with fewer bugs than, than the average human.But since they write so much more of it, like more of it will make it into production. So you have to- You still[00:10:26] swyx: have[00:10:26] Mikhail Parakhin: more bugs. Yeah. Have to have a very rigorous PR reviews, also automated of course. But, uh, yeah, that to spend a lot budget there. Like this, this for me, for me, actually, the important metric is the ratio of budget spent during code generation versus, uh, spent, uh, expensive tokens like GPT, uh, five point four Pro or, uh, uh, Deep Think from Gemini, you know, checking on PR reviews.[00:10:55] swyx: Yeah, totally. Uh, I noticed in your chart you didn't have any review tools. Do you just use like, like let's say a Claude code to review tools? Or do you have another set of review tools like the Greptiles, the Code Rabbits, uh, Devin Reviews has a review tool. I don't know if you've had those specialist review tools.[00:11:13] Mikhail Parakhin: You are a little bit jumping on my store tool right now because the graphs I was only showing public tools. Uh, uh, the-- I haven't found a good PR review tool that, that does what I think should be done. And, uh, partially my, my thinking is because it's so... It just goes against both what people feel like emotionally they prefer and, uh, some of the, uh, you know, frankly Even business models that, that the companies run.At peer review tool, uh, time, you want to run the largest models. That means, I don't know, Codex or, or, uh, Cloud Code is not gonna cut it. You need to have pro-level models if you really want to, uh, stand the tide of bots from going into production. And you need us to spend a lot of time, the models taking turns, but you don't want, like, a big swarm of, uh, of, uh, agents.So in fact, you end up in a different dual-dualistic world where you generate not that many tokens. You, in fact, generate few tokens, but it takes f-a long time because these are expensive models taking turns rather than many, many agents trying to do many things in parallel. So that's, that's why I feel like I haven't found good tools, so we are using our own for peer review for now.[00:12:33] swyx: Yeah. Yeah. I mean, uh, I think a lot of companies are building their own, uh, especially to their needs, right?[00:12:38] Mikhail Parakhin: Mm-hmm.[00:12:38] swyx: Um, I, uh, you also have a chart here going back to the slides on, uh, PR merge growth, where we're now at thirty percent, uh, month on month rather than ten percent. Uh, and also the, the estimated complexity is going up.You know, this is productivity, right? ‘Cause y- presumably there's more stuff going into the code base and more, more features getting worked on. I'm curious about the backlog, right? Like the, the, the-- I actually don't mind a pro-level model taking an hour or two hours to review my PR, because I've dealt with humans who take a week to review my PR, right?And I keep pinging them on Slack, “Hey, hey, review my PR.” So, you know, I think there's some trade-off here where, like, it still doesn't make sense.[00:13:18] Mikhail Parakhin: Exactly. That, that's exactly m-my point. Uh, that on one hand, you can tolerate longer latencies at, uh, PR. On the other hand, like right now, the real problem is not in spending time waiting for PR.It's real problem is since there's so much more code than- Yeah ... uh, probability of at least some tests failing going up, and then you, like, keep de-failing, then you have to find the offending PR, evict it, retest it without that PR, and so deployment cycle becomes much longer. Uh, so it actually, in terms of the overall time to deploy, it's total time savings if you spend more time on a longer model, like thinking for an hour, because then, then you, you don't have to spend all that time during testing and rolling, you know, rolling back the deployment.[00:14:03] swyx: Yeah, totally. That's still worth it. You know, you don't look at the individual, look at the aggregate, and look at the, the, the change in the aggregate system.[00:14:11] Mikhail Parakhin: Exactly.[00:14:11] swyx: I'm kind of curious if, like, there's this PR mentality and, like, c-- the, the, the CICD paradigm will be changed eventually. Some people are like, obviously a lot of people want new GitHub, but I even wonder if, like, Git is the problem, right?Like, is that the bottleneck? Is the concept of a PR a bottleneck? Do you guys use stack diffs? I don't know if, uh, that's a, like, a merge queue stack diff type of thing.[00:14:34] Mikhail Parakhin: We, we use, we use Stacks, we u- we use Graphite. We worked with, uh, Graphite a lot. Uh, so we use Stack, uh, PRs. I think, uh, like that's clearly the overall CICD in general, and the interaction with the code repository right now is the, clearly the sort of the, the main issue and the bottleneck for us, uh, and highest top of mind.I would say we probably need a different metaphor or different whole design of how to process it in new agentic world. I haven't seen anything dramatically better yet. I, I think everybody right now is just trying to keep their head above the water ‘cause, ‘cause there, there's so many PRs and then everybody's CICD pipelines start creaking, the, the times are increasing, the number of bugs slipping by increasing, and you have to, have to clap on down.And so we are a little bit in this situation when we need to first stabilize that story and then start thinking, hey, what, what it could be a completely different and new world, which I haven't... I know some people working on it. I haven't seen something, like anything super compelling yet, but clearly the old thing were designed for humans will need to be morphed into something new.[00:15:53] swyx: One of the thing that I, I think about is kind of like the merge conflict is basically a global mutex on the whole system, right? And in, in hu- in human organizations, we do have something like that. It's the company standup. But like, other than that, it's like it's actually fitting for us to be somewhat decentralized, somewhat plugged into one stream of information source, but somewhat lossy.Like it's okay, you know, that, that not every delivery is like atomic consistency. Like we're not dealing with a database sometimes.[00:16:27] Mikhail Parakhin: This is a very good point, uh, because since humans don't write code too fast, you know that global mutex is not too bad. Once you-[00:16:36] swyx: Yes ...[00:16:37] Mikhail Parakhin: start writing code at the speed of machine, it becomes the, you know, the bottleneck.Then what do you do? Maybe, and I can't believe I'm saying this because I, I'm long-- lifelong opponent of, uh, microservices, and I always thought that was, like, a really bad idea. And now that you're saying it, like, maybe in new guys like microservices will make a comeback, you know, because then you, you can ship things independently in tiny things and, and the managing all that complexity automatically will be much easier.I don't know. Like, we'll s-- we'll have to see.[00:17:10] swyx: Yeah. I mean, I don't know what the Microsoft or, or Shopify thing is, but I, I read this paper from Google where they have a monorepo that deploys into microservices, right? And then, uh, the other concept that I think about a lot is the Chaos Monkey concept from, from Netflix.Being able to create, like, this robust system where, um, uh, you know, you, you have the service discovery, you have the, uh, the independent, independent microservices discovery and, and, uh, you know, probably going to be a fair amount of duplication. That's how an organic system sort of scales, uh, that, that you have that...I don't know how you call it. Slack? Robustness? Depend-- uh, d-duplication. I, I, I forget the-- I, I'm-- And this-- those-- these are not exactly the terms- Hmm ... I'm looking for, but I c-can't really think of the words. Okay. I was gonna go into Tangent and Tangle. Uh, so, uh, we, we sort of discussed the overall stats that, uh, Shopify has.Uh, but, you know, I, I think some, some pretty cool stuff that you guys are working on is your ML experimentation, uh, and your, your sort of auto tr-research training pipeline. Presumably you're much closer to this one because it's, it's a sort of personal hobby of yours. How, how would you explain them in, together?I thought we have a slide that, like, uh, has the s- the system diagram.[00:18:24] Mikhail Parakhin: Yeah. Tangle first and then Tangent as a-[00:18:27] swyx: Yeah ...[00:18:28] Mikhail Parakhin: as a thing on top of Tangle. And, uh, Tangle is the third generation, I claim, of, uh, systems of, uh, running any data processing, but a bit with a skew for ML experiments, but not necessarily. Any sort of data processing tasks where you need to iterate, share, and you have scale so that you want maximum efficiency.You know how, like, normally you would work, you would-- Imagine you're a data scientist or an ML practitioner, you would get Jupiter notebooks or, or maybe you would get, uh, you know, Pyth- your Python scripts, and you would manage the data, and you produce those TSV files, and you put them in some JFS or something.Then you would notice that, oh, it has this, uh, weird missing values. You go and write another script that, uh, goes and replaces them with, uh-[00:19:20] swyx: Ah ...[00:19:21] Mikhail Parakhin: dash S. And then, then you, then you run some, some, uh, “Oh, I need to filter bots.” And so you run some light GBM model that, uh, removes the bots. And then, then you like-- And then you, you kind of like get into shape, and then you start experimenting, and you run multiple experiments, and then you're like, “Oh my God,” like, “this experiment is worse.”You undo, and you cannot get to previous result. And like, “Ah, what did I do?” Like that. Again, then, then you finally like get everything working. Then you like start throwing it over the fence to production. You, you replicate it, those things don't work, and then sometimes you like don't notice that you forgot some feature naming and the, the features don't match.But then, like imagine you, you did everything, and then six months later you're like, have to repeat it because now there's more data, or you wanted to do another pass, and you're like, “What, what did I do?” Or like, or like, “This script crashes now,” or the, “the path has changed.” And then, then you're trying to, like you spend another month just doing ar- digital archeology on your own, you know, history, right?Now multiply that by many, many teams. Now imagine you got an intern that you wanna ramp up. Now you have to show that intern, “Oh, you know, look, here's the folder, there's the scripts, you know, ask your cloud agent to do, and then, uh, to, to figure it out.” And then cloud agent does something, and then you're, “Ah, yeah, right, right, it was the wrong folder.I forgot to tell you, I actually have this other thing I forgot myself.” And, and that's, that's the, like, the daily life we all, uh, all know it, uh, if, if you're a data scientist, machine practitioner, ma- machine learning practitioner or, uh, or even like any data managing, uh, person.[00:21:00] swyx: Yeah. So I, I used to do this, uh, f- uh, on the quant finance side, uh, in, in my hedge fund.So we did this before Airflow, and then, uh, obviously Airflow came along and, uh, then more recently Dagster, uh, I would say is like, in my mind, what I would use for that shape of problem, uh, where you had to materialize assets and create a pipeline.[00:21:19] Mikhail Parakhin: And that's, that's very good segue because... So Airflow is great, but Airflow is more about you, you have something and you wanna repeatedly run it in production on schedule.It's less about you as a team developing things and being able to share, and you grabbing the standard pipeline and saying, “Hey, I wanna change this tiny little component in the huge sea of data processing, and I don't wanna-- I wanna run ten experiments on this, and I wanna do hyperparameter optimization.”All that is very hard to do with Airflow. It's very easy to do with Tango. Tango is m- more about, it's everything about group of people Running experiments, it might be agents too nowadays. Uh, running experiments cheaply, collaborating, sharing results. Uh, you don't need to understand fully. You, you grab-- you clone somebody else's experiment or somebody else's pipeline, uh, run, uh, change small piece, run it, be, like, get it to production state, and then ship in one click.So then the... You don't have to port it into any other system to, to run in production. You can just run the same experiment. It's, it's fully production ready. And, and it's, uh, it has lots of... Again, as I said, it's third generation system. The original one was, I would claim there was Ether and then, uh, at least in my career, Ether was the first, first, uh, that pioneered this type of approach.And then there was, uh, Nirvana, which, uh, uh, at Yandex, which did kind of sec-second take on this. And now this one aggregates the, the learnings from all of those and, and Airflow as well to, to get to the state where you try it, it, it feels kind of magical. Uh, ‘cause now everything is based on content, uh, hashes.So even if the version changed, but if the output didn't change, nothing is being rerun. It's very efficient. If you... Multiple people start experiment that needs the same sort of data preprocessing, it's not repeated multiple times. It's automatically done only once. If you start ten experiments that all require, you know, some, some data preparation first as the first step, and you don't have to coordinate for that.Like, you don't have to know that other people are starting it. You now, it's very easy compos-, uh, composability, any language you can u- uh, you wanna use, and it's very visual. So you can see immediately, you can edit it easily, you can assemble small things with just even mouse clicks if you want to, and, uh, share, clone.And everybody knows also it's fully kind of static in the sense that we rerun it second time, it will exactly have the same results. Like, you will never have to do digital archeology. So full versioning and everything is also there.[00:24:06] swyx: Uh, so, so people can, uh... It's open source. Go to the GitHub repo and, and, uh, check it out.Uh, and it is also a really good, uh, blog post about it. I think all these is, like, really appealing. The, the, the, the thing that I think sells me the most about it is that, um, sort of development to production transition, right? Which I think, um, a lot of people haven't really solved that, uh, strictly, right?Like, we develop really, really well in, in Python notebooks, but then, you know, that's obviously not a sort of production ready process. I think that, like, any way in which that is solved, I think is, is very appealing. Then the other thing that you mentioned, which also raised my eyebrows, was content-based caching, which you mentioned is, is, um, you know, is ve-very much, uh, um, a sort of efficiency measure about, uh, you know, just like recalculation only on, on sort of content addressing Which I think makes sense.Uh, it surprised me that the savings could be this much, but maybe I just haven't worked at your scale where there's so much duplication, uh, that people just rerun because they change a single ID upstream.[00:25:10] Mikhail Parakhin: It does, yeah. But it's not only you rerun. The, the main savings are coming from the fact that you ran it, you got your job done, and you moved on.Then- Yeah ... somebody else in some department you don't know existed runs the same task, but on a newer version.[00:25:27] swyx: Yeah.[00:25:27] Mikhail Parakhin: Like right now, you can't, in, in most of the organizations, you can't even find out about it so that you can't even measure that you're spending that time twice, right? Here- Yeah ... if everybody's on Tango, that's detected automatically and detected that the output is the same.And then for that person, all it looks like is like experiment just suddenly moved, jumped forward, right? Uh, uh- Yeah ... so that's because, because the, there's network effect of multiple people helping each other.[00:25:51] swyx: Yeah. This is one of those things where it's designed to be a platform from the beginning rather than an individual developer's tool from the beginning, right?And, and everything's gonna streams down from there. That is the sort of Tango, uh, orchestrator, and it's, it manages jobs. We've seen a few versions of this, and this is obviously, uh, uh, the sort of, uh, unique approaches that you guys have, have, uh, figured out. And then there's Tangent.[00:26:14] Mikhail Parakhin: Yeah. And Tangent is basically an automatic auto research loop that can help and kind of do your work for you.Uh- ... you know, uh, effectively, effectively, Andrej Karpathy recently popularized it with auto research. Yes. Remember he said like he was, uh, speed running this, uh... Yeah, uh, you know the story. The, here we're basically bringing the same capability into Tango so that, uh, the, uh, Tangent can analyze it. It's just an agent that can run multiple experiments, figure out what can be changed, and keep on rerunning it, keep on modifying until, uh, maximizing some goal, some loss function, whatever you need to, to achieve.And in general, I would say if you're not using auto research-like approach in whatever you do, like literally whatever you do, then you're missing out. We saw at Shopify that taking like a wildfire, anything where you can put measurements can be done dramatically better. Our-[00:27:19] swyx: Mm-hmm ...[00:27:20] Mikhail Parakhin: uh, speed of, uh, templatization HTML, uh, completely new UX tem- uh, templatization of, uh, reducing latency for liquid themes.Uh, we-- Our, uh, search, uh, recently we moved from It's hard even, uh, quote from eight hundred QPS to forty-two hundred QPS with the same quality just by pure optimizations and not a research loop that kept running and changing code in our index serve on the same number of machines, just increasing the throughput.We, we managed to improve the quality of gisting and machine learning process. Uh, you know, gisting is the prompt compression technique that[00:27:59] swyx: allows for[00:28:00] Mikhail Parakhin: lower latency and, and lower and, uh, actually higher quality slightly. So like literally whatever different walks of life, and it doesn't have to be AI related.Uh, we, we had a reduction in, uh, storage because the agents would go and find data sets that clearly are derivative, uh, and then you don't need to store things twice. You know, we, we, we found somewhat embarrassingly that it was one of the largest tables was hashing random IDs into another random ID, and we literally- Oofput only one. So it was translating, yeah, two random IDs hashed[00:28:36] swyx: into[00:28:37] Mikhail Parakhin: each. So, so[00:28:37] swyx: it has access to the code as well, so it can, it can check the, like what, what the hell is it doing?[00:28:42] Mikhail Parakhin: So there, there cou- it could be run in two levels. You, uh, you know, at the superficial level, it could just use ex-existing components and, uh, reshuffle them.Uh, you know, like you can grab- Yeah ... uh, XGBoost, and you can grab some, some Py- PyTorch module, and then can grab some, you know, grab another tools and, and combine them. At a deeper level, since Tangle is all sort of CLI based underneath you, every, every component is a wrapped really CLI, uh, call and a YAML file, it can analyze code and create new components and, and, uh, keep on iterating as well.So, so you can, you can both have quick modifications of existing t- uh, pipelines with the, with components that are already there pre-baked, or you can create new components, uh, and-[00:29:29] swyx: Yeah ...[00:29:29] Mikhail Parakhin: keep iterating on those. So auto research is, again, this is probably the, the thing I was excited the most in the last two months happening, and we see it taking like, like totally like a wildfire.Just, uh, everybody, every day, every... well, every day, every minute, I would, uh, have somebody Slack message saying, “Oh, look how much better I made it.” And, uh, it's all throughout the research.[00:29:53] swyx: Is this democratized in some way in, in the sense that like is it your ML, uh, engineers and researchers doing this, or is it your regular PMs and software engineers also have the ability to auto-- to use Tangent?[00:30:07] Mikhail Parakhin: This is an awesome question. Like, Tango in general and Tangent in particular are extremely democratizing. Like they- Yeah ... they are the main tools for- ‘Cause I don't[00:30:15] swyx: need the details.[00:30:16] Mikhail Parakhin: Yeah. Exactly. Initially used by ML and AI engineers, but then literally, as you said, PMs are like the highest user right now is one of PMs on our org, uh, Sartak and he was, he was number one by, by usage of, of this ‘cause they're just, uh, energetic and knowledgeable, and now it, it unlocks a lot of capability where you don't have to co-change code manually.[00:30:39] swyx: I mean, I mean, because it kind of cuts out the ML, ML engineer from the process because the, the, the PMs have the domain knowledge and the ability to think about, uh, from first principles about, okay, what, what results do I want? And they can-- they even have the access to the data that, that needs to go in.So it's like in some ways, like this is the magic black box that we've always wanted for, for training and, and for, uh, I guess, uh, uh, hill climbing, whatever.[00:31:04] Mikhail Parakhin: It's basically cloud code for your AI development- ... uh, situation, right? Like now, now you don't have to know exactly how algorithms work. You can just, uh, bring your domain knowledge and expertise and product knowledge and iterate within Tangent until you've gotten the results that you need.[00:31:21] swyx: In my previous roles, every time that someone has pitched AutoML, you know, I've always been like, “Uh, this is not, this is not gonna work. It's, you know, it's, it's always gonna be a flop.” Somehow it's working now. I mean, presumably the answer is now we have LLMs and it's good enough, right? It's, it's an emergent property that we can do auto research, but like, it doesn't feel that satisfying that how come we didn't do this before, right?Like we just did like parameter search and like, I don't know. That's maybe that's it.[00:31:48] Mikhail Parakhin: Yeah. Bayesian optimization and hyperparameter optimization was, was the one that, or facet of AutoML that was used very actively, which incidentally also built into, uh, Tango. But, you know, I know Patrice Simard very well, and, uh, he was such a, uh, such a proponent of AutoML, and he put, like literally spent careers trying to democratize it.Without LLMs, it just turned out to be very hard. Like it, you, you would have flexibility within certain narrow domain, but it was hard to wider scale, and now with LLMs suddenly it's like magic wand, and so suddenly everybody- ... is an AutoML expert.[00:32:28] swyx: Yeah, I, I think it's multiple things, right? Like I'm, I'm just gonna bring up the, the, the chart again, right?Like LLMs can do the monitoring very well. That is the very potentially unbounded, super unstructured. It can do the analysis very well, it can do the... Uh, and basically it is much more intelligence poured into every single step. Uh, there's maybe nothing structurally changed about AutoML, but this is just m-more intelligent and more unstructured.[00:32:53] Mikhail Parakhin: Exactly.[00:32:54] swyx: Any flaws that you've run into? Like everyone is like drinking the Kool-Aid, oh my God, time savings, uh, you know, performance improvements. Like what, what, uh, issues have you have, uh, come up?[00:33:06] Mikhail Parakhin: This is really cool. It's not a solution to all the world's problems for sure. The limitations are usually the ones I-- And this is where we get into a bit of a subjective territory.Uh, I can only share what I've, I've seen so far, and I'm sure the situation, uh, is changing, and, you know, maybe after I say it, like many people will reach out and say, “Hey, what about this?” And you don't know that, and then, then we'll be probably right. But what I've seen is auto research is very good at doing kind of obvious things that you don't have bandwidth to do or you didn't notice or maybe you're not aware of like the-- some standard practices.It is not good at doing something completely out of distribution, something that, you know, you have to think for, for multiple days, uh, and, and do something like none of this. So, so it's, uh, I, uh, set an experiment once, uh, on, on my sort of, uh, hobby thing, and I let it run for, uh, ended up, uh, several weeks run, uh, you know, it's like full production kind of scale, so it, you know, slow runs and, and it ex-- it performed in the end, uh, over four hundred experiments, and only one was successful.I'm like, “Okay, that's, that's good.” But-[00:34:18] swyx: But it saved time.[00:34:19] Mikhail Parakhin: Yeah, I saved time. Like it, it was the, that thing. Yeah, if I, if I were doing four hundred experiments myself, my betting average, as I said, would have been much higher, I'm sure. But also, first of all, it would take me like three years to do four hundred experiments.And, uh, I didn't have to do them. Like the machines were just, uh, the price of electricity did that. So, and I got one improvement, uh, that in, uh, my, my-- Honestly, when I was starting that experiment, my thinking was to go and show that, “Hey, Andre, maybe you just don't know how to optimize.” And I was super smart because in, in my pro-problem, it was optimized for many years, and it was like fully improved.Uh, and I didn't expect it, you know, auto research to find anything at all. Yet it did. So instead of making fun of Andre, I ended up, uh, a big, big supporter. Yeah, that's exactly the tweet. Yes.[00:35:10] swyx: You and Toby really, really go back and forth on-online a lot, which is really funny. Uh, think of it as, as an eval for the optimalness of the code it's running on.Uh, it's almost like it reminds me of like a Kolmogorov complexity thing, but, uh, I guess it's-- there's some optimal thing that you're trying to sort of reduce down to, I guess. Um, and so, so you, you, you know, you should congratulate yourself that you had, uh, you know, uh, ninety-nine percent, uh, optimality.[00:35:36] Mikhail Parakhin: Exactly, yeah. I think Andre really deserves a lot of credit for popularizing this approach. This is, uh, this is incredibly, I think, powerful and cool and You know, the, uh, even him, him just mentioning it led to a lot of gains in a lot of places in the industry, so we should be thankful.[00:35:56] swyx: Yeah. I think he also has a just...I don't know what it is. Like, um, you know, it, it is a simple self-contained project that people can take and apply to other things, which is, is, is one thing, but also just the name. Just like somehow no one, no one managed to call their thing auto research. It's just naming things is very important. I think that that is mostly, uh, our coverage of Tango and, and, uh, Tangents.I think obviously, you know, there's a lot of, uh, ML infra at, at Shopify that people can, uh, dive into. We're about to go into SimGym, but before I do that, any, any other sort of broader comments around this whole effort? Like where is it, where is it leading to?[00:36:36] Mikhail Parakhin: As a segue to SimGym, like all those things start composing strongly.And, uh, you could see a huge unlock when you can look at each one of the tools and, and you see, oh, they're extremely useful. Uh, Tango is useful by itself. Auto Research is useful by itself. SimGym is useful by itself. If you combine all three, you create like synergetic effect. I think that's why we wanted to even, uh, cover them today is because this is something that if you go back even, you know, five years ago, would've been unthinkable.Uh, replicating that, uh, would, would be either incredibly costly or impossible, right? With probably thousands of people are required.[00:37:20] swyx: Well, we have serverless human, uh, serverless intelligence, right? Like, uh, so yes, you do have thousands of hu-- of, of intelligences, not just, not humans. And that's, that's close enough, right?Even if they're not AGI, they're, they're close enough to do the, the task that you need them to do. And, and, you know, that's, there's plenty for, for a lot of routine work, knowledge work. Okay, let's get into SimGym. Um, this is one of those things I, I was surprised to see actually it's apparently your, uh, one of your most popular launches, and I think something that, uh, I think Sim AI, I think Yunjun Park, who did the Smallville thing, there's a very small cottage industry of people trying to do like the simulate customer thing.I think a lot of people maybe don't super trust this yet because they're like, well, obviously they would just do what you prompt them to do, right? But maybe just think, uh, tell us about the sort of inspiration or origin story.[00:38:10] Mikhail Parakhin: That's exactly actually the thing I wanted to cover, because if you don't have the historical data, all you can do is prompt a-agents in a vacuum, and they will do exactly what you prompt them to do.In fact, when I first proposed it, and this is a bit of, um, my brainchild initially, if I, I can boast, even Toby said like, “But wouldn't they, they just repeat what, what you tell them?” And, uh, but I'm like, “Yes, except Shopify has decades of history of how people made changes and what there is, uh, there, what it resulted in terms of sales.”So now what we can do is we can-- we have this... It's not, it's a noisy data. There's a small, usually websites, uh, you know, like things, things are never in isolation. It's almost never AB experiment. It's always AA experiment when there's has two meanings, but basically, you know, in different time you run two different things.But if you aggregate in general, uh, like everything together, and you apply, uh, denoising and collaborative filtering like approach, you can extract a very clear signal. And then you can optimize your agents. And that's why it took so long. It took almost a year of that optimization of just us sitting and fiddling, and, and we had this internal goals of correlation of hitting-- internal goal was to hit zero point seven correlation with, uh, add to cart events, for example.Like that, that if we run real AB test experiment, that it should, it should go and, and rep-uh, replicate, uh, same sort of success that, that humans had or lack thereof. And it, it took forever, and I don't think that's easily replicatable because, uh, like who else would have that data? You have to have this historic, you know, decades, uh, worth of data.And now, now the, like the other thing you need is in-infrastructure and the scale, right? Because, uh, w- again, what we found, uh, stat sig results, you need to run a lot of simulations, a lot of agents, and, and it's-- Those are expensive things. Like you're, you're making actions in the browser because you want a real friction.You want to, to be able to get the image like of what humans will see because you wanna, uh, detect effects like, “Hey, if I make my images larger, will I have more sales or l- uh, fewer sales?” And like usually people's intuition here, by the way, is that I increase my images, I will have more because they look nicer.You know, designers all look sparse and big images. Like usually your sales tank, right? But, but, uh, you know, from HTML, all the characters look the same only the, the size tag looks different, right? So it's very hard. So you have to take visual information, you have to run this in simulated browser environment on the big farm and, and of course, you have to have, uh, like very, very expensive model, good model with multi-model model.So all this it's-- is what's taken so long and, uh, to share my personal fail a little bit there, Sean, is like, you know, we always had this bias to-- for like large company bias. You know, we always, uh, whenever you-- we do, we're like, “Hey, we'll run an experiment,” right? We make, make a change, and we will run an experiment and then, uh, see, uh, see which one's better or like, “No, this is worse,” and most of them are worse, so you discard it and keep iterating, hill climbing.And we're like, “Oh, like smaller merchants, they cannot get stat sig results. They cannot really run experiments simply because, you know, in a week there would be not enough data for them.” So we thought from this perspective. What we didn't realize is that most people don't have A and B, they just have one thing, and they need suggestions of What A and B should be.So, uh, we first build this, hey, we run simulation on two separate teams and, and, uh, say, “Hey, which one is better?” We then morphed it into, and very recently just released it, when you have just your site, your theme, we run over it and we say, “Hey, here's what predicted values of, of, uh, uh, conversions are, and here's how we think you should modify it to increase your conversions.”And then circling back to what you started with, the proof is in the pudding. Like, if we are not correlating with reality, like, people will not be using it. And, uh, thankfully, we see literally every day more users than the previous day. So, so right now, uh, right now- It's working. Yeah. I'm-- Right now my problem is how to pay for it all because the so our major thing is how to optimize the LLMs, do distillation, how to run the headless browsers, uh, and handful browsers, uh, uh, cheaper so that we can accommodate the increase in traffic.[00:42:47] swyx: Yeah. I, I understand that you, uh, you published a lot of technical detail at GTC, so I was just gonna bring it up a little bit. I think s- was this in, in con-conjunction with some kind of GTC presentation? Or something like that, right?[00:42:59] Mikhail Parakhin: Well, we, yeah, we, we did it in several place, but yeah, we had the engineering- Yeahblog, uh, as well. Yeah.[00:43:05] swyx: Yeah. So you're running, uh, GPT OSS. Uh,[00:43:08] Mikhail Parakhin: the, this is an older version. You know, now we run multimodal model. But yeah- Yeah ... GPT OSS, we still run GPT OSS as well for[00:43:15] swyx: And then you have the VMs, and you also have browser-based. I really like this one where it you said, “It violates almost every assumption that standard LLM serving is designed for.”And then you had like, basically orders of magnitude differences between everything.[00:43:29] Mikhail Parakhin: Exactly. Which is, which, uh, which was, you know, a bit of a challenge to implement, like when, like even simple things. Uh, be- since it violates all the assumptions, for example, multi-instance GPUs, like MIGs don't work as well.But we needed, uh, to get MIG to work because, ‘cause otherwise it's way too expensive. And so we had to deal with the, yeah, with, uh, lots of infrastructure and, and, uh, work with, uh, uh, Fireworks and CentML, uh, you know, to help with optimizations and browser-based, as you mentioned. Yeah, like, takes a village.[00:44:04] swyx: Okay. So there's a lot of like, I guess, experimentation in the infrastructure so far, and you've published more or less what you have here. I guess I'm, I'm less familiar with CentML. I, I don't do, uh, that much work in this, this part of the stack. But why was it the sort of preferred instance platform?[00:44:22] Mikhail Parakhin: There are really three probably top companies. There used to be, uh, uh- Three top companies, uh, at least I was aware of that did, uh, LM optimization. You know, together Fireworks and Santa ML, not necessarily in that order. Santa ML recently got acquired by NVIDIA. Uh, what they did is if you have a model and you want to optimize it to a specific prof-- uh, profile of usage, uh, they would go and do it.And, uh, we work with, with those companies, uh, this was work particularly in with Santa ML and NVIDIA to get them the best possible results out of it. And, and sometimes you, you have to retune depending on, like sometimes you want the maximum throughput, sometimes you want minimal latency, sometimes you want like the cheapest, right?And, yeah, or some combination. And so yeah, these are people who would come and help you.[00:45:14] swyx: I see. I see. Yeah, yeah. I'm familiar with these people for the LLM, you know, autoregressive stack. But the other interesting category of these optimizers is also the diffusion people, whereas like Fel and, you know, uh, Pruna recently has come up a lot as well, which I think is like really underappreciated, uh, at least by myself, because I, I thought, oh, all the workload would be LLMs, but actually there's a lot of diffusion as well.[00:45:38] Mikhail Parakhin: Exactly.[00:45:38] swyx: There's a lot here, so I, I, I... it's, it's, uh, it's, it's, it's hard to cover. But I, I do think like people underappreciate the importance of customer simulation, basically. I think this is something that I'm candidly still getting to terms with. Uh, you know, uh, you also-- your team also like prepared this, like, really nice diagram.Uh, I, I assume this is AI generated.[00:46:00] Mikhail Parakhin: Yeah, it looks-[00:46:01] swyx: Maybe it's not.[00:46:01] Mikhail Parakhin: Yeah, it looks, uh, Gemini-ish. Yeah, but, uh, uh, honestly, I, I don't know where, where the hell they generated. It looks, look, uh, looks like it's, uh, Google. But the interesting part, John, that, that, uh, we haven't covered, but I, I wanted to mention is if your store had previous customers, rather than it's a new store, you're like new merchant just launching things, it helps tremendously in just correlation and forecast.Yeah, we take your previous, uh, customer's behavior, and we create agents that replicate those specific distribution of, of customers that you get, and then we a- we apply those to your changes, and then that, that raised raw, you know, the re-- uh, just correlation with the add to cart events or to-- with conversion or whatever it, it, it may be, uh, quite dramatically.So, uh, replicating humans in general seems like an interesting, cool challenge.[00:46:58] swyx: As a shareholder, I think this is the-- like if people are Shopify shareholders, they should really deeply understand this because this is basically the moat. The, the more you use Shopify, the more it will just automatically improve, right?Like you're, you're doing the job for them.[00:47:13] Mikhail Parakhin: Yeah, that's what we started with. Like, uh- ... uh, otherwise, if you're just a startup, I wouldn't do it if, uh, you know, if it was my startup because Without the data, it, yeah, as, as you said, it's, it's exactly the case that, uh, whatever you say in prompt, that's, that's what the agents will be doing.[00:47:30] swyx: The statistician in me wants to like really satisfy the sort of, um, statistical intuition, I guess. Um, to me it's kind of, uh, the, the word that comes to mind is, um, ergodicity. Uh, so let's say a, a customer takes this path, customer takes this path, customer takes this path, right? Um, the... In my mind, the way I explain it is like, okay, here, here's the ninety-five percentile, here's the five percentile, and here's the median, right?Um, but to me, what SimGym is potentially doing is that it can, uh, modify... It can sort of model the sort of in-between sort of journeys as well, that, that maybe are dependent on the previous states. This may be like a very RL-type conclusion where like basically the summary statistics, if you only did naive AB testing, you only have the, the statistics at, at, at a certain point, and you only judge based on the sort of overall summary statistics.But here you can actually model trajectories. Does that make sense? Or-[00:48:31] Mikhail Parakhin: That makes total sense because like, well, that, that makes even more sense that maybe even you realize bec- because-[00:48:38] swyx: Okay. Please,[00:48:38] Mikhail Parakhin: please. Yes ... we do-- Yeah. The, so internally, uh, we have this system, we talked about it briefly once at NeurIPS.We have a huge HSTU-based system that models the whole companies, uh, and their possible paths. And like- Yeah ... what you are, what you are showing, like actually at any point of time, you can either model the user's behavior or you mo- can also think about, uh, the whole merchant as a company, as the entity that acts in the world.You can model that as well. And then you can do, can do counterfactuals. In your graph, like in your blue graph, uh, if you're... Imagine in the center there, uh, somewhere in the middle, you would have an intervention. I give that person a coupon, or I don't know, I send a personal thank you card, or give a discount in some- somewhere.And then you can, uh, then you can do forward rollouts from that counterfactual. So what would have happened with that intervention or without the intervention? And you can even ch- change where that intervention, uh, in time can happen, right? Like some- where, where in this journey. So we, we do this at the Shopify scale for our merchants, and then if we notice that something that they can be fixing, like there's a strong counterfactual, like we have Shopify policy, they basically get a notification like, “Hey, we think your...something is wrong with your-” I don't know, Canadian sales. Like, uh, it looks like it's misconfigured. Here's what you need to do. Or do you think like, uh, you have to set up this campaign with these parameters? And we do that at the buyer level to literally offer discounts or cashback or, or things to buyers.So this is-- I'm getting very excited. Like this is my sort of area of, uh, interest, I guess, and, and hobby. But being able to m-model something complex as human beings or companies and model counterfactuals on it, where you can have interventions in the future and optimize when to make intervention, what kind inter-- uh, what kind of intervention to make.It's such an unlock that previously was completely impossible. Like the-- it was, it was always dreamed of, but never... Like how would you even simulate it without LLMs or HTUs? I think very, very exciting times.[00:50:59] swyx: I just wanted to, uh, to maybe illustrate this. I, I'm not the best illustrator, but I, I am a conceptual statistics guy.And y-you know, you cannot just do this. Like this is a dimensionality AB test doesn't do, right? Like, uh, because it doesn't have the, the, the change over time, uh, stochastic nature, uh, and it doesn't have the sort of contextual like... Here's all the context to this point. Um, okay, cool. Um, that's SimGym.You're, you're gonna burn a lot of tokens on this thing. But you're, you're one of the, the only scale platforms in the world that can, uh, that can do this across a huge variety of workloads, right? I'm even curious on a sort of human, uh, research level of like, well, do, does retail behave d-differently from like clothing sales?D-does that behave differently from electronic sales? I, I don't know. I don't know what else you guys... The Kardashian shoppers, do they differ from like people who buy, uh, I don't know, cars and, uh, whatever.[00:51:55] Mikhail Parakhin: Well, very different, and different sensitivities and different modes of, uh, shopping and, and different levels of what's important.Now, to-totally, you can do aggregations at, uh, at a store level. You can do aggregations at a different, uh, category level. I don't know if, uh, you know, for our statisticians among us, I couldn't believe, but we-- recently we're looking at it, and we had to bring back, uh, CRPs, you know, Chinese restaurant process.It's a, like, way of aggregating and, like, naturally grow clustering. So across... Specifically to answer questions that, uh, like you were just posing on how, how if, if buyers behave different categories. And I'm like, “I haven't seen CRP since two thousand and one.” It's[00:52:37] swyx: so What? It's so- What is... No, I haven't, I haven't seen this.No. This is not in my training. Uh,[00:52:44] Mikhail Parakhin: but, but yeah, it, uh, uh, it actually, like the, the-- there was a very popular kind of theory, popular neurips HTML circles in early two thousands, uh, kind of nice. And now, now it has practical applications, uh- Yeah ... that we were resurrecting.[00:53:03] swyx: Yeah, amazing. Uh, I, I can see, I can see how this is like a, uh, a fun job for you where you get to apply all these things.Um, yeah, yeah, so super cool. Super cool. So, okay, so, so anyone who, who knows what CRPs are and has always wanted to use them at work, uh, they should, they should definitely join Shopify. Okay, so w-we have a lot and but I, I'm, I'm being mindful of the time. I, I do wanted to, to sort of cover some other things.Um, I-I'll give you a choice, UCP or Liquid?[00:53:30] Mikhail Parakhin: Liquid. I think, I think on UCP, you know, like UCP is very important for us and, and it just we are-- UCP, we have a structured, uh, discussions, and you can read about them, and we have, uh, blog posts, and we have a big release this week, in fact, like with our catalog.Oh,[00:53:46] swyx: okay.[00:53:46] Mikhail Parakhin: Uh, yeah,[00:53:46] swyx: but- Le-I mean, we, we can, we can discuss the, the, the release briefly because we'll release this after the-- after it's already announced so whatever. There's a catalog that you guys are doing?[00:53:55] Mikhail Parakhin: Yeah. So we are, we are- Okay ... we are bringing in capabilities of a whole, uh, Shopify catalog.Basically, you now you can search for products, you can do lookups by specific ID, you can do bulk lookups when you need to bring m-multiple products. You don't need to know in ad-in advance what you're trying to show or to sell or check out. Like, you can now, you can now have this decided at, at runtime, and this big area for investment for us for both non-personalized and personalized searches, trying to provide basically a win-window into whole universe of products that are being sold everywhere in the world.And Shopify is really not exactly, but almost like a super set of any-anything being sold. Now we are bringing it into UCP and, uh, and, uh, identity linking is another big thing for us, uh, so that you, you can use, uh, like Google or whatever, whatever identity you have, uh, they're minimizing friction.[00:54:56] swyx: Yeah. So[00:54:57] Mikhail Parakhin: yeah, big release for us.But Liquid AI of course we never talk about, and the problem might be more, more aligned with what we d-discussed previously on this chat.[00:55:07] swyx: Sure. The main thing that everyone understands about Liquid is that it is inspired by Worm, and I still don't know why. I'm curious on your explanation. I think you, you, uh, you can make things very approachable.And also I think like what is the potential of like the, the level of efficiency that you get out of Liquid?[00:55:23] Mikhail Parakhin: You- we all familiar with transformer architectures. And, uh, for the longest time, there was a competing architecture, it's called the state space models. So, so Sams, uh, you know, Chris, Chris Reyes, one of the pioneers and, and lots of startups, uh, trying to make those realities.They have, uh, significant benefits being main being, uh, being much faster and, uh, lower footprint and not quadratic in length, you know, sort of, uh, linear in, in, uh, in your context length. But with state space models- They never quite made it. Like they're used-- They have, uh, certain niches when they thrive, their hybrid architectures are useful, but they never quite made it.And liquid neural networks are, you can think of them as a next step, like, uh, sort of, uh, state-space model square. It's non-transformer architecture that's more complicated than sta-state space and really difficult to code if you-- if I'm being honest. But it's, um, very efficient. It's, uh, subline-- sub, uh, quadratic in, in length of your context.Uh, it's very compact way to represent things, and that's a liquid AI company. They... Their goal is to productize it, and very often you have this need, uh, when you need to have long context and small model, and you want to have low latency. Like in general, it's basically on par with transformers, and if you do hybrids with transformers, it's, it's even better.That's why we at Shopify, when we tried multiple and we constantly try multiple models, multiple companies, we found that for small, particularly with low latency applications, when you have low latency and/or if you need longer context lengths, liquid was the best. And so we still use the whole zoo and always like obviously test and use everything, uh, every open source model and, you know, it feels l

On today's episode, we talk about an incredibly deadly creature, which has determined the course of nearly all human history just by existing: The Mosquito. How has the mosquito determined the course of war, and what wars might have gone differently if it didn't exist?

On today's episode, we talk about something that has held together history, literally. Even though there's probably a roll in just about every household in America, we often overlook the utility and ubiquity of duct tape. But what would we do without it?

On today's episode, we talk about the USS Wyoming and the 1863 battle of the Shiminoseki Straits - a seemingly minor event overshadowed by the American Civil War. But this battle might have altered the course of history. 

In this episode of SERious Epidemiology, Matt and Hailey welcome guest Dr. Peter Tennant to discuss chapters 2 and 3 of Causal Inference: What If. After learning about Peter's late‑discovered love of cashew nuts despite past nut allergies, we shift to a discussion about observational studies and randomized trials. Like the textbook, we start talking about why randomized trials are a helpful framing tool to talk about the identifiability assumptions for causal inference. We then introduce concepts such as marginal and conditional effects, exchangeability, positivity, and consistency. We start to dive into the subtle distinctions in some of these concepts: confounding vs. lack of exchangeability due to random error, the underappreciated practical importance of positivity, and how consistency relates to well‑defined interventions.

On today's episode we talk about the first commercially successful ‘plastic', the beginning of the plastic revolution that has so altered human society. But what if it happened differently?

On today's episode, we talk about a soviet submarine disaster in the Atlantic, which averted potentially disastrous outcomes only by the heroism of its crew. But what might have happened if it went differently?

On today's episode, we talk about the beautiful islands of Samoa, which were the background to a clash between the relatively nascent empires of the United States and Germany in the 1880s. As the crisis came to a head, however, nature put a dramatic end to human ambition. But what if it had gone differently?

As the Winter Olympics begin, Michelle and Chase take a closer look at a surprising insight from author Daniel Pink: bronze medalists are sometimes happier than silver medalists, and the reason why can change the way you think about your career. In this episode, Michelle and Chase break down the psychology of counterfactual thinking - the "what might have been" stories we tell ourselves and explore how both upward and downward counterfactuals influence motivation, confidence, and learning. They share: Why our brains default to certain "what if" scenarios How upward counterfactuals can motivate growth (without pulling you into self‑doubt) How downward counterfactuals help build resilience and perspective Practical ways to turn regret into insight instead of discouragement Whether you're celebrating a win or navigating a setback, this episode gives you the tools to use your past experiences to create better future outcomes. Article: Using Regret To Do Better Got a question? Ask us! Do you have a question you'd like to hear answered on Career Dreams? You can submit an audio recording of your question to be featured on an upcoming episode!  Like it? Share it! If you're finding value in exploring your Career Dreams through this podcast, please share it with your friends, followers and colleagues! Also, your ratings and reviews help others find the show...so please, let us know what you think! You can share your Career Dreams with us anytime via email: careerdreams@forumcu.com. To learn more about making your Career Dreams come true at FORUM Credit Union, visit our website:  https://www.forumcu.com/careers Dream on!

On today's episode, we discuss the Blight that nearly wiped out wine, and how wine and indeed the world might be different if it had unfolded differently.

Inglourious Basterds (2009), written and directed by Quentin Tarantino, revolves around two plots to assassinate Nazi leaders during the closing years of World War II. One plot centers on a secret band of Jewish-American soldiers under the command of Ltn. Aldo Raine (Brad Pitt)—the “Basterds”—who terrorize Nazis. The other involves Shosanna Dreyfus (Melanie Laurent), a young Jewish woman who narrowly escapes death at the hands of notorious “Jew hunter” Hans Landa (Christoph Waltz) and flees to Paris where she runs a cinema under a false identity. The plot lines converge at the Paris cinema where the Basterds and Shosanna are each separately plotting to kill Hitler and other Nazi leaders while they are attending the premiere of a German propaganda film. The film utilizes alternate history to explore themes surrounding the pursuit of justice against the perpetrators of mass atrocities and the complex relationship between law and vengeance.Timestamps:0:00    Introduction2:37     Reimagining the arc of justice8:00     Alternatives to the progress narrative16:51     The power of violence and revenge21:56     Counterfactuals and alternative histories27:03     The limits of legalistic responses to atrocities32:24     The role of cinema in Nazi Germany39:00     Narratives of progress44:10     Ending with a primal moment of revenge  Further reading:Hussain, Nadine, “‘Inglorious Basterds': A Satirical Criticism of WWII Cinema and the Myth of the American War Hero,” 13(2) Inquiries Journal 1 (2021)Jackson, Robert H., Opening Statement before the International Military Tribunal, Robert H. Jackson Center (Nov. 21, 1945)James, Caryn, “Why Inglourious Basterds is Quentin Tarantino's Masterpiece,” BBC (Aug. 16, 2019)Keydar, Renana, “‘Lessons in Humanity': Re-evaluating International Criminal Law's Narrative of Progress in the Post 9/11 Era,” 17 (2) J. Int'l Criminal Justice 229 (2019)Kligerman, Eric. “Reels of Justice: Inglourious Basterds, The Sorrow and the Pity, and Jewish Revenge Fantasies,” in Quentin Tarantino's Inglourious Basterds: A Manipulation of Metacinema (Robert Dassanowsky ed., 2012)Tekay, Baran “Transforming Cultural Memory: ‘Inglourious Basterds'”, 48(1) Film Criticism (2024)Law on Film is created and produced by Jonathan Hafetz. Jonathan is a professor at Seton Hall Law School. He has written many books and articles about the law. He has litigated important cases to protect civil liberties and human rights while working at the ACLU and other organizations. Jonathan is a huge film buff and has been watching, studying, and talking about movies for as long as he can remember. For more information about Jonathan, here's a link to his bio: https://law.shu.edu/profiles/hafetzjo.htmlYou can contact him at jonathanhafetz@gmail.comYou can follow him on X (Twitter) @jonathanhafetz You can follow the podcast on X (Twitter) @LawOnFilmYou can follow the podcast on Instagram @lawonfilmpodcast

Free ZWILLING Four Star Chef's Knife on your 3rd box ($144.99 value) + 10 Free Meals and your first box ship free with code CURTJHFZWL at https://hellofresh.yt.link/4u4Vh7m! This is an interview with Oxford's Timothy Williamson. He's one of the most cited living philosophers, and simultaneously one of the most controversial (yet respected). He dismantles physicalism, solipsism, and reductionism––explaining why consciousness is philosophically overrated and why AI in its current form likely lacks genuine mental states. This will be a tour‐de‐force episode into all things related to looking deeply and fundamentally. If you're interested in consciousness, free will, art, language, and meaning, I believe you'll love this episode. As a listener of TOE you can get a special 20% off discount to The Economist and all it has to offer! Visit https://www.economist.com/toe SUPPORT: - Support me on Substack: https://curtjaimungal.substack.com/subscribe - Support me on Crypto: https://commerce.coinbase.com/checkout/de803625-87d3-4300-ab6d-85d4258834a9 - Support me on PayPal: https://www.paypal.com/donate?hosted_button_id=XUBHNMFXUX5S4 JOIN MY SUBSTACK (Personal Writings): https://curtjaimungal.substack.com LISTEN ON SPOTIFY: https://open.spotify.com/show/4gL14b92xAErofYQA7bU4e TIMESTAMPS: - 00:00:00 - Vagueness & Sorites Paradox - 00:07:12 - Identity, Physicalism, Non-Physicals - 00:22:30 - Realism vs. Anti-Realism - 00:29:50 - The Problem of Skepticism - 00:35:40 - Cognitive Heuristics & Doubt - 00:43:00 - Solipsism's Appeal & Pitfalls - 00:50:00 - Solipsism: A Critique - 00:57:30 - Pluralism & Consciousness - 01:06:00 - AI, Mental States, Ontology - 01:15:50 - Mind, Knowledge, Meaning - 01:26:00 - Philosophical Heuristics - 01:32:00 - Counterfactuals & Logic - 01:38:00 - Personal Philosophy LINKS MENTIONED: - Overfitting and Heuristics in Philosophy [Book]: https://www.amazon.com/Overfitting-Heuristics-Philosophy-Rutgers-Lectures/dp/0197779212 - Timothy Williamson's Published Papers: https://scholar.google.com/citations?user=IH-44VwAAAAJ&hl=en - Sorites Paradox: https://plato.stanford.edu/entries/sorites-paradox/ - Philosophical Investigations [Book]: https://www.amazon.com/Philosophical-Investigations-Ludwig-Wittgenstein/dp/0631205691 - I Do Not Exist [Paper]: https://academic.oup.com/book/53296/chapter-abstract/422023005 - O'Shaughnessy Ventures: https://www.osv.llc/ - Barry Loewer & Eddy Chen [TOE]: https://youtu.be/xZnafO__IZ0 - Bas Van Fraassen [TOE]: https://youtu.be/lhpRAWxvY5s - Matthew Segall [TOE]: https://youtu.be/DeTm4fSXpbM - Jennifer Nagel [TOE]: https://youtu.be/CWZVMZ9Tm7Q - Leo Gura [TOE]: https://youtu.be/YspFR9JAq3w - Iain McGilchrist [TOE]: https://youtu.be/M-SgOwc6Pe4 - The Consciousness Iceberg [TOE]: https://youtu.be/65yjqIDghEk - Karl Friston [TOE]: https://youtu.be/uk4NZorRjCo - Geoffrey Hinton [TOE]: https://youtu.be/b_DUft-BdIE - Elan Barenholtz [TOE]: https://youtu.be/A36OumnSrWY - Ben Goertzel & Joscha Bach [TOE]: https://youtu.be/xw7omaQ8SgA - Claudia de Rham [TOE]: https://youtu.be/Ve_Mpd6dGv8 - Stephen Wolfram [TOE]: https://youtu.be/0YRlQQw0d-4 - Elan Barenholtz & Will Hahn [TOE]: https://youtu.be/Ca_RbPXraDE - Greg Kondrak [TOE]: https://youtu.be/FFW14zSYiFY - Robert Sapolsky [TOE]: https://youtu.be/z0IqA1hYKY8 SOCIALS: - Twitter: https://twitter.com/TOEwithCurt - Discord Invite: https://discord.com/invite/kBcnfNVwqs Guests do not pay to appear. Theories of Everything receives revenue solely from viewer donations, platform ads, and clearly labelled sponsors; no guest or associated entity has ever given compensation, directly or through intermediaries. #science Learn more about your ad choices. Visit megaphone.fm/adchoices

On today's episode we talk about one of the most fraught elections in American history, where violence, initmidation and outright fraud precipitated a constitutional crisis - the 1876 election between Rutherford B. Hayes and Samuel Tilden.

On today's episode, we talk about the mutiny of the Pennsylvania Line on New Years Day, 1781, and how it might have altered the trajectory of the American Revolution, and everything after.

FAN MAIL--We would love YOUR feedback--Send us a Text MessageOne audacious night on the Mississippi may have decided the Civil War. We dive into the capture of New Orleans in 1862 and show how Farragut's risky run past Forts Jackson and St. Philip didn't just seize a city—it fractured the Confederacy's map, gutted its finances, and reshaped the war's momentum. New Orleans wasn't just a symbol; it was the South's engine: the largest population center, a world-class port, a shipbuilding hub, and the gateway for cotton exports and foreign credit.We unpack why the Crescent City mattered so much and how the Confederate high command miscalculated the threat. As Grant pressed from Tennessee, Richmond drained New Orleans of troops to defend Corinth's rail hub, leaving the Gulf approach weak and the river poorly protected. The real heartbreak lies with the unfinished ironclads—CSS Louisiana and the CSS Mississippi. Union officers later admitted that a battle-ready Louisiana in the narrow channel could have ravaged Farragut's wooden fleet. Timing, not just technology, proved decisive.From Porter's mortar bombardment to Farragut's pre-dawn dash, the action was fast and consequential. When New Orleans fell, the Union claimed the river's mouth and effectively split the South. The ripple effects were brutal: cotton exports collapsed, international credit evaporated, and inflation surged as the Confederate government printed unbacked money. Supply lines from Texas, Arkansas, and Louisiana withered, starving armies and cities of food, salt, and matériel. We also explore the powerful counterfactual: if New Orleans had held—its shipyards humming, ports reopened, and ironclads unleashed—European recognition might have become more than a dream.If you're ready to rethink where the war's true turning point lies, this story delivers a sharper lens on strategy, logistics, and the cost of misjudgment. Listen, share with a history-loving friend, and leave a review to tell us: was the war really lost on the night New Orleans fell?Key Points from the Episode:• New Orleans as the South's economic engine and largest port• A divided city with weak support for secession among voters• The Anaconda Plan's focus on the Mississippi River• Confederate misread of the threat and troop shifts to Corinth• Unfinished ironclads Louisiana and Mississippi as lost opportunities• Porter's mortar bombardment and Farragut's breakthrough• Strategic split of the Confederacy after the city falls• Financial shock: lost exports, credit, and spiraling inflation• Logistics cutoffs from the western breadbasket and long-term effects• Counterfactuals showing how completion of ironclads could change outcomesOther resources: Want to leave a review? Click here, and if we earned a five-star review from you **high five and knuckle bumps**, we appreciate it greatly!

Mid-career partners can begin quietly wondering whether they should stay where they are or explore a move. This isn't driven by crisis or failure. It's driven by subtle shifts, such as declining energy for a platform that once fit well, strategy drift inside the firm, client relationships that feel different, or internal politics that have grown wearisome. Yet most partners stall making a decision because they don't want to make the wrong call and the ambiguity keeps them stuck. In today's episode, I walk through the five stages I see that partners typically move through when confronting the stay-or-go question: detecting early signals without overreacting, running a true cost-benefit audit, separating fact from extreme thinking about portability, pressure-testing the market and assumptions, and exploring parallel stay and go plans.  I share the specific diagnostics I suggest partners consider, the risks partners often underestimate, the structural problems that rarely improve with time v. the irritations that can usually be changed, and how to evaluate the potential options through financial, client-continuity, and cultural-stability filters. If you're a partner feeling the need to examine your place in your practice or platform, this episode helps you approach that crossroads with clarity, data, and control. At a Glance 00:00 Why mid-career partners begin questioning whether to stay or go 02:44 Stage 1: Quiet doubt and the early signals partners tend to overlook 03:54 A three-question diagnostic for evaluating how to initially frame what may be going on  05:39 Stage 2: The cost-benefit audit and quantifying what staying v. going actually buys you 07:18 How politics, write-offs, and strategic stagnation erode partner value 08:42 Distinguishing temporary irritations from structural misalignment 10:10 Stage 3: Counterfactuals and why partners get stuck in best-case and worst-case assumptions 10:55 Reality-checking which clients would follow you and which would not 11:24 How to quietly stress-test the market without signaling intent 12:37 Stage 4: The real risks of leaving: portability, client transfer, compensation, and culture 14:19 Identifying what must change for you to stay, and how to design parallel stay and go plans 15:35 The three filters for evaluating any move: financial survivability, client continuity, and cultural stability 16:25 Stage 5: Why this decision can feel like an identity crisis and how to regain agency Rate, Review, & Follow on Apple Podcasts & Spotify Do you enjoy listening to Big Law Life?  Please consider rating and reviewing the show! This helps support and reach more people like you who want to grow a career in Big Law.  For Apple Podcasts, click here, scroll to the bottom, tap to rate with five stars, and select "Write a Review." Then be sure to let me know what you loved most about the episode! Also, if you haven't done so already, follow the podcast here!  For Spotify, tap here on your mobile phone, follow the podcast, listen to the show, then find the rating icon below the description, and tap to rate with five stars. Interested in doing 1-2-1 coaching with Laura Terrell? Or learning more about her work coaching and consulting? Here are ways to reach out to her: www.lauraterrell.com  laura@lauraterrell.com   LinkedIn: https://www.linkedin.com/in/lauralterrell/  Instagram: https://www.instagram.com/lauraterrellcoaching/  Show notes: https://www.lauraterrell.com/podcast

On today's episode, we talk about a forgotten part of the Battle of the Bulge - Elsenborn Ridge, where outnumbered allied units held against veteran German divisions, and what the chances were that the Reich could have turned the tide in 1944.

Frank Gavin, Giovanni Agnelli Distinguished Professor and Director of the Henry A. Kissinger Center for Global Affairs at Johns Hopkins University SAIS and author of Thinking Historically: A Guide to Statecraft and Strategy, joins the show to discuss the promise and perils of using history to guide today's statecraft. ▪️ Times 02:20 Political Science vs. History 05:37 The Importance of Historical Thinking 08:13 Historical Interpretation 11:22 Counterfactuals  14:26 The Misuse of History in Policy Making 17:19 Thinking in Time 22:27 Errors When Thinking Historically 31:57 Putin's View of History 40:01 Philosophical Understanding 47:05 Does History Have a Direction? 53:34 A Checklist for Historical Thinking Follow along on Instagram, X @schoolofwarpod, and YouTube @SchoolofWarPodcast Find more content on our School of War Substack

On today's episode we talk about what is often called the last invasion of mainland Britain - a disastrous and almost farcical series of blunders that ended in abject disaster. But what if it didn't?

Cross-posted from Good Structures. For impact-minded donors, it's natural to focus on doing the most cost-effective thing. Suppose you're genuinely neutral on what you do, as long as it maximizes the good. If you're donating money, you want to look for the most cost-effective opportunity (on the margin) and donate to it. But many organizations and individuals who care about cost-effectiveness try to influence the giving of others. This includes: Research organizations that try to influence the allocation or use of charitable funds. Donor advisors who work with donors to find promising opportunities. People arguing to community members on venues like the EA Forum. Charity recommenders like GiveWell and Animal Charity Evaluators. These are endeavors where you're specifically trying to influence the giving of others. And when you influence the giving of others, you don't get full credit for their decisions! You should only get credit for how much better the thing you convinced them to do is compared to what they would otherwise do. This is something that many people in EA and related communities take for granted and find obvious in the abstract. But I think the implications of this aren't always fully digested by the [...] ---Outline:(03:34) Impact is largely a function of what the donor would have done otherwise.(04:36) Is improving the use of effective or ineffective charitable dollars easier?(06:14) How do people respond to these lower impact interventions?(08:14) What are the implications of paying a lot more attention to funding counterfactuals?(10:21) Objections to this argument. --- First published: November 12th, 2025 Source: https://forum.effectivealtruism.org/posts/YrMFHJm7mbswJd7Me/the-overall-cost-effectiveness-of-an-intervention-often --- Narrated by TYPE III AUDIO.

Today we talk about the most numerous bird on the planet - the chicken - and how the world might be different if we never domesticated it.

On today's episode, we talk about some of the first steel-hulled ships the United States ever built, and how those first few ships might have set the tone for the entire 20th century.

On today's episode, we venture to Asia to talk about a battle that determined the course of Chinese history, and that has become such an integral part of Chinese historical mythology that it is sometimes difficult to sort fact from fiction. What might have changed if the battle went a different way?

On today's episode we talk about one of the most ubiquitous human creations in the modern world: Concrete. What would the modern world look like without this grey material we all take for granted?

On today's episode, we talk about a little-remembered presidential visit in the wake of Pearl Harbor - Christmas, 1941, when Winston Churchill risked the U-boats of the Atlantic to visit his new allies in the White House.

Today we talk about a little remember battle that could have been a turning point in the First World War - a battle between the German High Seas fleet and the Russian Baltic fleet in the Gulf of Riga.

On today's episode we talk about the little remembered espionage side of teh civil war, particualrly the CSA's more outlandish ideas to take the war to the Union. And of course, we talk abotu what the world might look like if it all happened differently.

Pastor Dave asks us to put on our imagination hats and learn from Psalm #124 about how to use our brains “counterfactual mode” to stir up thankfulness and praise to our Maker. * SPOTIFY MUSIC PLAYLIST -- https://tinyurl.com/fkzpkjwh * SERMON PODCAST -- https://tinyurl.com/2sn3msmn * CONNECT WITH US -- https://siderischurch.com/connectcard * MORE GOSPEL RESOURCES -- https://siderischurch.com/resources

Pastor Dave asks us to put on our imagination hats and learn from Psalm #124 about how to use our brains “counterfactual mode” to stir up thankfulness and praise to our Maker. * SPOTIFY MUSIC PLAYLIST -- https://tinyurl.com/fkzpkjwh * SERMON PODCAST -- https://tinyurl.com/2sn3msmn * CONNECT WITH US -- https://siderischurch.com/connectcard * MORE GOSPEL RESOURCES -- https://siderischurch.com/resources

On today's episode we talk about a bird that was once so numerous that Americans thought it would be impossible to kill them all. Until, suddenly, they did. What might the world look like if the passenger pigeon hadn't gone extinct?

On today's episode we talk about the incredible popularity and influence of an odd product: Ketchup. What would the world be like without it?

On today's podcast we talk about the year 1983 - called by some “the most dangerous year” in modern history. In the fall of that year, Western and Communist powers may have nearly stumbled into the one thing that neither side wanted - all-out nuclear war. How might the world be different if that close call went another way?

This episode delves into the use of substitute questions—simpler queries we use to answer more complex ones—and the crucial concept of cohesion between these substitutes and our true objectives. You'll learn how to leverage counterfactual thinking to scrutinize your assumptions and enhance the effectiveness of your decisions. Discover two powerful counterfactual techniques: asking "what else could be true?" to reveal alternative explanations, and employing thought experiments to, for example, precisely define your desires and career aspirations. The discussion offers practical applications, from refining hiring processes by identifying high-cohesion interview criteria to avoiding confirmation bias in debugging. By adopting counterfactual thinking, you can significantly improve your analytical skills, make more informed choices, and build robust strategies.Uncover how cognitively taxing questions lead us to use substitute questions as heuristics, and why understanding the cohesion between these is vital for accurate decision-making.Learn to implement "counterfactual thinking" to rigorously check your heuristics and substitute questions, ensuring they effectively align with your actual goals and underlying evaluations.Discover two key counterfactual techniques: exploring "what else could be true?" to identify alternative explanations for observations, and conducting thought experiments to clarify nuanced personal and professional desires.Explore practical applications of counterfactuals to drastically improve processes like hiring, by challenging low-signal interview criteria (e.g., LeetCode problems) and making more predictive assessments of candidates.Understand how counterfactuals can combat biases like confirmation bias in problem-solving, such as debugging, by prompting you to consider alternative causes and avoid poor pathways of biased logic.Realise the transformative power of counterfactual thinking in refining your thinking process, improving your career trajectory, and enhancing departmental operations by identifying and improving low-cohesion substitutions.

On today's episode, we talk about one of the most famous battle in Roman history, when 50,000 Romans were killed in a single day. How would the world be different if that battle went differently?

On today's episode, we talk about one of the largest naval battles in history, Leyte Gulf, and the task group that was never created: Task Force 34. A series of decisions often called mistakes led to one of the most famous underdog fights when the small force called Taffy 3 faced down Japanese battleships in the Battle off Samar. If any of those decisions had gone differently, the world might have taken a different path.

Today we discuss one of the most powerful earthquakes to strike Europe in recorded history, an earthquake which knocked down Lisbon in a single, violent day in 1755. The aftershocks would be felt throughout history, however, as a shocked Europe came to terms with the power of nature. What might have happened if it went a little differently?