Podcasts about Mad Libs

Earlier this month, world model company Runway introduced GWM Worlds 2, a research preview that “turns high-fidelity video and audio generation into real-time interactive simulation.” Runway calls this an “autoregressive diffusion” model; with autoregressive describing how it generates over time.One new feature in particular caught our eye: WorldPrompt, a proposed input format for specifying a generated world and the actions within it. It allows you to fix some aspects of a simulated environment — including the first frame — and then create a series of timestamped events. The events, or actions, can even be prompted in real-time.To understand the implications of WorldPrompt, we spoke to Kamil Sindi, Runway's CTO, and Robin Kahlow, its Principal Research Scientist for generative video and multimodal AI. We also have exclusive comments from Anastasis Germanidis, co-founder & co-CEO of Runway, courtesy of a podcast swyx and Vibhu did with him.Who's building real-time interactive world models?First, some context about world models that can generate interactive video and audio in real-time.Runway is reportedly valued at $5.3 billion, based on its most recent fund raise of $315 million in February. Its first release, GWM Worlds, was launched last December.Alongside Runway, there are several other notable projects in this domain: Google DeepMind's Genie 3 (which also generates at 720p and 24 fps), Odyssey-2 Pro, and World Labs' RTFM (Real-Time Frame Model). We've summarized their differences in the following table:Given the complexity and massive latency demands of real-time video and audio generation (which we'll get into below), all of the projects listed above have limitations. For instance, Google notes that Genie 3 “can currently support a few minutes of continuous interaction, rather than extended hours.”But as our interviews with Runway show, real progress is being made.The central idea of WorldPromptWorldPrompt, a new feature in GWM Worlds 2, helps differentiate Runway from its competition. You can think of it as a control layer for characters, cameras and the environment. As Kahlow put it, it's a way to “control all the different subjects in the world” — similar to a computer game.“Like, if there's an NPC [Non-Player Character] somewhere, the NPC might walk up to you and say something. So you could achieve the same thing with this kind of model, where you can have very detailed control over everything in the scene.”As the name suggests, WorldPrompt is a prompting mechanism — not a programming language. So, unlike virtual world games like Minecraft or Roblox, GWM Worlds 2 doesn't offer scripting capabilities or the ability to control state. But there's a power to that, as Sindi pointed out.“You can create promptable worlds on-demand with video and audio in sync, across all these different domains and environments. That's not a distant-future hypothetical thing,” he said.But there are also limitations to prompting a world model. We asked how reliably the model would follow an instruction to create, for example, a law of gravity or a certain ability in a character?“Yeah, so it's a research preview,” Kahlow replied. “So it's not perfect, of course, and there are still flaws. It really depends on how difficult the action is. I would say movement works quite reliably.”Sindi added that more training plus scaling the data and models is resulting in “better following.”How a video model becomes a real-time runtimeDespite the current limitations of GWM Worlds 2 — especially if you compare it to pre-designed and scriptable worlds like Minecraft or Roblox — the true promise of world models like Runway is that they'll eventually lead to fully self-generated, real-time games and experiences. Which is an extremely hard engineering problem, as Kahlow reminded us.“There are two challenges. One is making the model not generate a whole clip at once. So instead, you want it to generate frame by frame while you're looking at it. And the other challenge is actually making the generation fast, so you can play it in real time.”GWM Worlds 2 offers real-time interactive worlds streamed in continuous 720p video at 24 frames per second (fps) and audio at 48,000 Hz.Runway achieved this firstly by taking its foundational audio-video generation model and fine-tuning it to the new WorldPrompt format, so the model can follow that. It then post-trains the model to generate autoregressively.“And after that, we work on making it real-time through distillation methods,” Kahlow added.Co-CEO Anastasis Germanidis offered more technical details in our podcast with him. He told us that the process starts from “bidirectional diffusion that basically generates an entire video at once and [makes] it autoregressive.” This allows the model to “generate one frame or a few frames at a time.”Germanidis described two possible forms of distillation in order to make it real-time: distilling a larger model into a smaller one or reducing its diffusion steps. As a general example, he said a model might go from around 50 denoising steps to four, with some quality loss but potentially comparable results.The challenges of real-time generationGermanidis admitted that there were issues with how it generates real-time interactive video.“The biggest challenge with autoregressive models is error accumulation,” he said. “You're feeding generated frames back into the model to generate the next frames, and if there are any small errors, they accumulate over time.”Sindi told us there are also challenges dealing with “infinite generations” of content.“There's all these challenges around what context to keep, what to discard that's not important. And so there's all these optimizations we have to think about, so we're not blowing up our GPU memory.”Another current limitation is long-term memory. “The model does not have perfect memory,” Kahlow said. “That's still an open research problem.”Causality and correctnessWhile performance is the primary challenge for Runway at this time, its world model also has to produce plausible consequences when a user takes different actions.Germanidis used the example of simulating football; he pointed out that online video training data contains more successful goals than failed goal attempts, so a video model might render the first more convincingly.“If I take this action versus this action, you want it to generate equally realistic outcomes,” he told us. “That's, I think, the big gap between video models and world models: that idea of counterfactual generation.”Sindi told us that evaluation gets harder the more complex interactions get.“If you have this multi-prompt, multi-character, multi-scene [environment], how do you really understand what was causal and what was not?”To try and solve that, Runway has some automated verifiable tests. But since GWM Worlds 2 is a research preview, Kahlow noted that doing tests yourself is also advisable — “trying out your model to see what doesn't work is really important.”More than gaming — there are agent use cases tooGaming is the obvious use case for what Runway is building, but there are others. Kahlow mentioned robotics — for example using a simulated environment to test how a robot works.Another, more intriguing, use case is to use it to test agents at scale.“Having thousands of simulated environments is much less challenging if you have a suitable model like GWM Worlds,” Kahlow said.But how does an agent know what's changed in the world — is there a structured state that it can read, or is it just the generated video and audio that it's consuming and understanding?“So there's no structured state here,” Kahlow replied. “It's just observing the same thing you might observe in real life, just [in this case] from cameras.”Sindi noted that GWM Worlds can also be used for “synthetic data generation for agents.”Finally, Germanidis suggested there's potential to use these world models alongside reasoning models.“You're maybe using some reasoning [for] planning of the scene, and then you're passing it into the diffusion head that's actually generating the pixels.”Anastasis Germanidis* LinkedIn: https://www.linkedin.com/in/agermanidis/* X: https://x.com/agermanidisTimestamps00:00:00 Introduction00:05:17 Runway's Origins and the Bet on Generative Video00:12:23 The Stable Diffusion Story00:18:44 Gen-2, Controllability, and the Weekend Hack00:23:02 From Video Generation to World Models00:28:03 Learning From the World, Not Just Language00:35:04 Sora, Runway's Existential Crisis, and Gen-300:39:39 Why Real-Time Video Is Inevitable00:43:06 Interface World Models: Software Without Code00:50:25 The Fully Neural Operating System00:55:11 World Models for Robotics01:02:32 Robot Policies and World Action Models01:07:47 The Lucid Dream Test01:11:41 Video Agents and Omni Models01:23:12 Artists, AI, and Creative Workflows01:27:14 Physical AI and the Future of World ModelsTranscriptIntroduction: Runway, Creative AI, and the Early ThesisSwyx [00:00:00]: Okay, we're here with, Anastassios from Runway, with, me and Vibhu in the studio. Welcome.Anastasis [00:00:08]: Good to be here.Swyx [00:00:09]: Congrats on all your success and progress with Runway. You're opening offices all over the world. Did you envision this when you first started out?Anastasis [00:00:16]: Not quite. I think even when we started, we had this idea that, It was more a matter of when, not if, we were seeing the early generative models of 2016, 2017, and just extrapolating, assuming, we resolution, quality increases predictably over time. There's gonna be a point where most of content will be generated, and that was maybe the initial thesis of Runway was we will need, as a result of those generative models, rethink how creative tools are made. and as we built out the research behind, our generative models, it then became clear that they were useful far beyond that as well.Anastasis' Background: Art, Simulation, and Machine LearningSwyx [00:00:57]: And it is more obvious now with, like, the real-world stuff and the world models that we'll talk about later. I'm just kinda curious how you go from a background in, like, Zocdoc and, computer vision into Runway. Like, take us back to that early conversations with Chris and, whoever else is on your founding team.Anastasis [00:01:14]: I was always splitting through those two worlds. One was the I had my own art practice. I was making a lot of interactive art, I think for a long time. and then on the other side, I was working in startups, and I was working as a ML engineer, as a backend engineer at different companies. I've always been interested in, coding and computation, and especially interested in simulation and brought it back into my early artwork as well. And at the same time, I was interested inSwyx [00:01:43]: The personal site has a few, right?Anastasis [00:01:44]: Yeah.Swyx [00:01:45]: Is there one that we should pull up? Just in case there's something that's like. I just like to go down memory lane.Anastasis [00:01:50]: Yeah.Swyx [00:01:50]: Okay, what is this?Anastasis [00:01:51]: So this was, a project that I made, I think back in 2015, where I built this software that would give, voice instructions to people in a gallery space. So it would coordinate interactions between people. And so it will first give you an identity, like you're an, architect, you're 30 years old, and, you like sports. and then it would match you with another person, and you have this completely generated interaction. language models were not quite there at the time, and so it was it was a mix of some templates and some, like, some Markov chain-generated text, and it would just completely simulate these small talk conversations between, everyone in the gallery space. so was always very fascinated on the one hand with, generative models and, like, the early machine learning work that was being at that time. But at the same time, there was this separate thread of simulation and what it means. Like, what can we learn about humans by creating those very simple models of their interactions and their behavior?Early Generative Art: pix2pix, GANs, and Uncanny ValleyVibhu [00:02:56]: Did you generate the prompts or, the 30-year-old, whatever? Was it you generating them? How'd you, how'd youAnastasis [00:03:03]: Exactly. So the program would just generate- those, from. Yeah, a lot of it would be Mad Libs style of justVibhu [00:03:10]: YesAnastasis [00:03:10]: You have lists of different professions, lists of different,Vibhu [00:03:14]: HobbiesAnastasis [00:03:15]: Personality types, lists of different, ages, things like that. And then it would just combine those things together. And then maybe the next project we go is, Uncanny Valley, Uncanny Road, which wasSwyx [00:03:27]: GansAnastasis [00:03:27]: One of the first projects that, we built with, one of my two co-founders, Chris. This was taking, pix2pixHD, which was one of the early image-to-image models that NVIDIA released back in 2016 or 2017. and it was a model that would take a semantic map of a scene and then generate a photorealistic, let's call it, output. very early days, so it was not very high-fidelity outputs, but it w I think was the first image-generation model that could generate at 1K resolution. And it was all trained on self-driving datasets. So the semantic categories it would support were only, things you would encounter on the road. So it would be pedestrians, traffic signs,Vibhu [00:04:16]: StoplightsAnastasis [00:04:17]: Bikes, stoplights. And so that was one of our first indications that we built this and people were making all this, like, very surreal imagery of, yeah, a million plus a million pedestrians or a million traffic signs or, like, gigantic humans. And it was a indication that you could take a model that was trained on this very boring dataset, essentially, of, like, not that many interesting things happen when you're on the road, and then you can repurpose it and go very out of distribution and make something that was artistically compelling. And that was It's a summary of the thesis of Runway in some ways, that you can take the same generative models, and if you look at them from another direction, if you build interesting tools around them and you give them to artists, they're gonna do things that you don't expect.Vibhu [00:05:02]: Very cool. I like the, UX of it. You're just given an empty canvas, try whatever, do whatever. And then the other one, like, you see everyone with wired headphones? Like, that's, that's a sign that it's, it's veryAnastasis [00:05:16]: The AppleVibhu [00:05:17]: YeahAnastasis [00:05:17]: Apple, your version.Vibhu [00:05:17]: Original ads. Yeah. Take us to today. You've been doing this for seven years at Runway. How have we got to this? Like, how do we go from driving simulator data to all this? And you cover the whole stack of generative media?From Creative Tools to a Research LabAnastasis [00:05:33]: Interestingly, we're almost back in, we're, we're full circle. We're, we're now applying our models and beyond creative tools into real-world scenarios. But it was a, it was a long journey. It was very early on we realized the first version of Runway was a way to easily use the, all the open source model of the day, things like pix2pix to. and give them to artists. That was the initial idea, is those models are too difficult to use if you're not a machine learning engineer. Like, what happens when you give them to artists? Very quickly, we realized we needed to build a research org, inside of Runway, and that happened maybe on year one. And, a lot of the mandate there was. The image-generation models of the time, the video generation models of the time, or there were barely any video generations all the time, but they were not quite there where they could be productionized and brought into tools that would be part of creative workflows. so we need to push the frontier of the research. And so maybe the first four years of Runway, research was almost happening on the background until there was a moment in 2022, with latent diffusion, with, DALL-E 2, where, there was that step function change, and you guys maybe remember around the time.Swyx [00:06:49]: I started in this space because of latent diffusion and Stable Diffusion.Anastasis [00:06:54]: Yeah.Swyx [00:06:54]: Because I was like, “Wow, this is not only, like, feasible, it is doable on consumer hardware.”Anastasis [00:07:01]: Exactly, yeah.Vibhu [00:07:01]: I think the delta is also huge. Like, I learned pix2pix. Like, this was intro to ML, the TensorFlow, like, Jupyter, Google Colab notebooks were like this, and then you have a sudden step function change, with diffusion and whatnot. Any other ones since that. Like, there were clear examples of what early diffusion were to get to here. Any other changes in key technology research?Green Screen, Rotoscoping, and Early RunwayAnastasis [00:07:26]: Between, 2018 when we started and 2022?Vibhu [00:07:29]: Yeah.Anastasis [00:07:29]: So one of the early work that we did in Runway was solving segmentation, image and video segmentation. It was a very important problem because most VFX involves essentially separatingSwyx [00:07:42]: RotoscopeAnastasis [00:07:42]: Subjects. Yeah, rotoscoping. Extremely manual process. Nobody enjoys doing that. and so a lot of the early days of Runway was building this tool. It was called Green Screen, and it was for a long time the main thing that people were using Runway for. It ended up being used in, Everything Everywhere All at Once and a bunch of other high-visibility films and series. But that was essentially, Runway for a long time was a post-production tool until latent diffusion and generat- Gen-1, Gen-2, happened.Swyx [00:08:12]: Cool. let's, let's go past that moment. You've come a long way. Then you started releasing your own models. Maybe describe that journey as well.Scaling Video Models and the Bet on 1,000 A100sAnastasis [00:08:20]: Yeah, so we go to the other point, yeah, in mid-2022 when it became clear that we're doing research at a fairly small scale of compute, and it became clear that, like, scaling laws would apply to, image and video gen in the same way that we're applying to language generation. So we made a big bet, and I think at so at the time, we signed this deal to build a cluster of a thousand A100s, which at the time we were a Series B startup. That was a almost, slightly irrational decision maybe, but we really believed that if we trained a video model at a large scale, we would get, like, a great model at the end. And at the time, the goal or we set the goal around fall of 2022 of what is, what does the latent diffusion, Stable Diffusion moment look like for video? And at the time, the best model of the time was called CogVideo. it was one of the early video models. It was very 256 by 256 resolution, very not very high quality. and so we decided we're gonna build out this cluster, and we're gonna just invest in, like, in building out our own video model. it became clear as we're training Gen-1 that it was difficult to get to fully. we wanted to build text-to-video, but it became clear to us that an easier starting point would be to start from video to video. Because when you have a stronger conditioning, it's, it's an easier problem to restylize an existing video versus generate the video from scratch. And so we released Gen-1 first back in, it was January of, 2023. Yeah.Vibhu [00:10:04]: It's just a fun visual podcast, honestly. Like, if we can see February 2023, what was the state of stuff?Gen-1: Video-to-Video and Depth ConditioningAnastasis [00:10:10]: It's so interesting ‘cause at the time when you see those results, you think this is so incredible, and this is like, it's almost like image generation or video generation is solved. And then you look back a few years after, and it's like, it's It's just like you get used to the results very quickly, with those models. But at the time when we started seeing those results, it was, it felt quite incredible, and the level of, like, quality that you could get. And, so the Gen-1 was a depth-conditioned video model, so it would turn. it would take a input video, it would predict. it would it would first convert it into the depth map, and then we would generate, pixels with a latent diffusion model.Swyx [00:11:01]: Yeah, very effective.Vibhu [00:11:02]: Yeah. I didn't realize how distracting the blog post would be. Sorry.Anastasis [00:11:05]: Yeah, but, one of my favorite examples of on those, on Gen-1 was both, if you go up to mode three or mode two, there was this storyboard use case where people would makeVibhu [00:11:18]: OohAnastasis [00:11:18]: WouldVibhu [00:11:20]: You can mess around with theAnastasis [00:11:20]: Make a city out of books or out of boxes, and then they would shoot a video with their phone and then translate it into a photo-photorealistic output. There was all these ways in which those models were starting to be used for storyboarding and also for really. and then if you go to mode four, like, of taking untextured 3D scenes and then turning them into photorealistic output. So we saw a lot of use cases early on where people that were familiar, were power VFX editors would just take a blender, render, and then they would get translated in with Gen-1 or create a scene in Unity and then take a capture a video of it and then translate into, restylize it. So I still think video to video is powerful. I think we had a recent video-to-video model as well, and it's one of my favorite ways of using those models is essentially using them to use ground truth video as, like, the initial inspiration and then translate into different styles or different outputs.Stable Diffusion, Stability AI, and Open SourceSwyx [00:12:23]: But I think we're gonna go into, like, the rest of Runway and catch people up to speed today. I did wanna cover the, let's call it the Stable Diffusion controversy, or, what happened with Stability AI, whatever. I think there was a two sides of the story. I think there's part of that is a normal thing of, like, people, join and leave companies, but what is the, retrospective now that, there's been some years behind it?Anastasis [00:12:49]: Yeah, it's a very, it's a very long story to go into. I think it wouldSwyx [00:12:53]: Which I remember you wrote a really long post about.Anastasis [00:12:56]: We would probably cover the whole hour to go into it in more detail. But, essentially, there was the latent diffusion paper that came in, I think that was at the end of, 2021. And then Patrick Esser, who was one of the researchers behind, latent diffusion, and he worked at Runway at the time, he built latent diffusion in collaboration with Robin Rumbach and a few other folks back, in the in, CompVis, which was, a labSwyx [00:13:26]: Like a research group, yeah.Anastasis [00:13:27]: And, after releasing the early latent diffusion model, they, essentially they were. the goal was to keep working on versions of the model, scale it up, incorporate new data, incorporate new tasks. And Stable Diffusion was the same model, but trained on more compute, and then with a few more tricks, like a classifier-free guidance paper came at some point, I think in the early 2022. And thatSwyx [00:13:52]: Which, like, was a big prompting improvement.Anastasis [00:13:55]: Yeah.Swyx [00:13:55]:?Anastasis [00:13:56]: That improved results. it was trained on better data, so like, the esthetic subset of LAION, but it was effectively, the same underlying architecture. And there was that big training run, that, happened on Stability's cluster. Stability financed that run. And looking back at that story, I think it was the work to build and train that model was done. It was a, it was a research project. It was done as part of, like, continuation of the latent diffusion work. It then, I think it the model became very successful, and it, I think there were the. And I think as a result of its success, other companies tried to, figure out the commercialization path for it. But for us, it was very important that we try to, we make sure that we. It was meant to be an open source research project, and so the we decided that we should continue releasing versions of it, since that was the original goal of Stable Diffusion, and that led to releasing Stable Diffusion 1.5. There was maybe a day of, a bit of, miscommunication there, but ultimately that was resolved very quickly within hours. so yeah, there wasSwyx [00:15:12]: OkayAnastasis [00:15:12]: Not a niceSwyx [00:15:13]: I just wanted to. you have toAnastasis [00:15:15]: Yeah.Swyx [00:15:15]: You're one of the main players in that journey, and so it's nice to hear from the source of, like, what happened. Yeah.Anastasis [00:15:22]: Yeah. I think it's all, it's all in the past nowSwyx [00:15:26]: YeahAnastasis [00:15:26]: I would say. and, like, both companies, Stability took its own path, Runway took its own path.Swyx [00:15:32]: Yeah. There's still. James Cameron is backing the new Stability, whatever they're doing with the Hollywood studios.Anastasis [00:15:38]: Right.Swyx [00:15:38]: I don't know what they are doing. I think one thing that impresses me, and I'm happy to move on, is that back in the that time, let's say, like 2021, 2022, there was this community of people that you were involved in that was researching all this stuff, right? And, like, from everyone I talked to who was active then, it seemed like it was fairly obvious that somebody would do the hero training run that would produce Stable Diffusion. So, like, I guess the question is, like, you had the you were you had made investments. You were you had the foresight. Is it accurate to say, like, that is reflective of, like, what people were thinking at the time? Or was it still very much like, “Well, we'll use it as, like, a post-production tool or something. I don't know.”? Like, where in the sentiment were we that maybe you can think back to, like, what the community was like back then?The Early Creative AI CommunityAnastasis [00:16:28]: I reminisce and I think very fondly those early years, from like 2018 to 2022, because it was a very small community that, as you said, were very convinced that this was gonna be a big thing. And at the time, anyone who. Because it was such a small circle and, everyone who would, like, be part of that circle and, like, make projects with it would, immediately get, go viral. so likeSwyx [00:16:55]: And you didn't know who they are, right? They're just some name on a, GitHub or Hugging Face somewhere.Anastasis [00:16:59]: Exactly, yeah. So I remember one of the first big viral moments of creative AI was, there was the neural style transfer paperSwyx [00:17:09]: HuhAnastasis [00:17:09]: ThatSwyx [00:17:10]: Something dreaming?Anastasis [00:17:11]: I think it was called neural style transfer.Swyx [00:17:14]: Okay.Anastasis [00:17:14]: There was also Deep Dream, the puppy sliceSwyx [00:17:16]: YesAnastasis [00:17:16]: Which was, also really cool. but, yeah, there was this project that, Jim Kogan, who was an early advisor of Runway and one of those,Swyx [00:17:25]: Marketing guysAnastasis [00:17:26]: Big, creative AI, folks, he literally just, like, showed a video of himself taking the New York Subway and going over the Williamsburg Bridge and then stylized it with, I think in the style of Van Gogh or, like, one, painter. And that was. Like, at the time, that was, like, so cool and it went viral and it was completely revelation to people that you could do this with generative models. And that was only, it was less than. It was maybe 10 years ago. So just, like, as an indication of, like, how quickly things have gone.Vibhu [00:18:02]: It's pretty crazy. Like, even since then, you've got people at every level of the stack. You've got devs, creatives, artists, hobbyists. You've got everyone using it. And for people that tried stuff early, they'll remember how hard it was to use regular diffusion, right? Like, nowadays, you can use your favorite ChatGPT image gen or whatever, give a sentence, get a beautiful output. But diffusion was like, the whole ultra HD, 4K, high resolution. Like, prompting these things was very different. anything you learned on the tooling side, like from the offerings you guys have now, so like creatives, devs, you really took the. Research and brought it to everyone to use. anything interesting there to share?From Gen-2 to Controllable Video GenerationAnastasis [00:18:44]: We had to build the entire model serving infrastructure for video diffusion models. There was nothing else, already, like, because we had Gen-2 was the first text-to-video model, I think, out in the market. So many things that we learn over time. I think the I think the biggest one was, like, we. it was very clear early on that text-to-video was not gonna be the answer. Like, you. Like, people wanted a lot more control than that, and so we invested in, like, control building on top of those models very quickly. how do you use the camera trajectory as control? How do you use an initial input frame as control? So that was a very early learning for us. With text-to-video was, like Gen-2 was an amazing, step function improvement in the quality of video models, but it was used much more in an exploratory way because there was nothing to ground it to. There was no reference that you could bring into it. There was no. You couldn't really control the camera motion. You couldn't control the object motion. And so the first year, in 2023, was really all about what are all the interesting ways in which we can condition those models? And it was a lot of just post-training rounds on top of the base model to figure out, like, what, -- how do people wanna control them? And so there was, like, this quick succession of the we it was called Motion Brush, which was you could, like, you could draw arrows and dictate where things should move in the scene.Vibhu [00:20:09]: That's so cool.Anastasis [00:20:09]: There was camera control that was you could just describe, like, how you want the camera to move in the scene. And because we work with filmmakers from the most of the history of Runway, we immediately got this feedback and got this, decided that this was worth investing in. And so control ability became a big theme, I think, very early on as we were building, as we were building those models. Something fun that I haven't really talked about too much was just how Gen-2 came to be out of Gen-1. So it was a bit strange because we announced Gen-2 two months after Gen-1 andHow Gen-2 Came From a Weekend HackVibhu [00:20:43]: We're accelerating.Anastasis [00:20:44]: It was before Gen-1 was even generally available. But Gen-1 was a depth-to-video model, so it would take a depth map and it would convert it into RGB. and we couldn't get, text or image-to-video to work directly, and that's why we started from depth to video. but, and we had discussions of like, okay, we need to spend the next six months investing in text-to-video, maybe increasing the compute scale or the model scale, like train a larger model. And I had this weekend project idea, which was, what if I take a model that, starts from text input and converts to depth maps and then use Gen-1 to convert the depth maps Into RGB?Vibhu [00:21:29]: It would probably work.Anastasis [00:21:30]: And so Gen-2 was that.Vibhu [00:21:32]: Oh. The hackathon pipeline.Swyx [00:21:35]: The weekend hackathon pipeline.Anastasis [00:21:36]: Yeah.Vibhu [00:21:37]: But it looks good.Anastasis [00:21:38]: And it worked pretty well. there were if you, with the knowledge that it has this, like, two-stage pipeline, you can tell in some cases that the structure of the video looks a bit off because you had to generate the depth first before you go into the output video. But it worked and it allowed us to bring this to our, to users very quickly. But it's now it's interesting because, like, people are coming back to this almost two-stage approach. Like, if you look at the Reve text-to-image model that came a few months ago, it had this planner model that would generate bounding boxes before it fed that into the diffusion transformer.Swyx [00:22:19]: Yeah, Ideogram also the same day.Anastasis [00:22:22]: Yeah.Swyx [00:22:22]: I remember that was very strange that both of them came out the same day with the same exact innovation.Anastasis [00:22:26]: It's a small community, I think.Swyx [00:22:28]: I'm like, this is like, this is completely coincidental, right?Anastasis [00:22:32]: People talk. So yeah, there's, there's definitely something into this approach. And, now, like every single like, video generation model in production uses a complex prompt completion pipeline under the hood. I think that's no secret that there is. ThatSwyx [00:22:48]: Humans are terrible at prompting.Prompt Rewriting, Camera Control, and the Seed of World ModelsVibhu [00:22:51]: I think across the board.Anastasis [00:22:51]: Yes.Vibhu [00:22:52]: But yeah, I think like the original Sora one blog post even told you that what happens after your input is rewriting your prompt. It's much more descriptive about what you would want.Anastasis [00:23:02]: Exactly. I, And there was the DALL-E 3 paper beforehand that, was the first public, description of the fact that synthetic captions and really detailed captions work really well. And then Sora built on that. Yeah, so it was 2023. We were releasing all these updates to Gen-2, like the camera control, Motion Brush. And there was something very interesting about camera control because it was the first time that you felt that instead of, like, you were creating video, you were creating a short video, you were navigating inside the world. And I think camera control was maybe the seed of some of the ideas that we had around world models and really opening up that research direction. We realized, it was this era and this series of, Gen-1 and Gen-2 models really proved to ourselves, yeah, this is theSwyx [00:23:56]: Cool.Anastasis [00:23:57]: So this is not the original camera control. This was the updated camera control on top of Gen-3. But yeah, I think it made those models usable to filmmakers, I would say. The so camera control was very popular. And so we realized, there is one way of seeing those models, which is, you're just as content creation machines, and there is the other way, which is you're. As you're predicting video in order to predict video well, you need to simulate the world in an increasing and increasing capacity. And if scaling laws apply on video, just like they apply on language models, then as we scale the compute that we put into those models, then they're gonna be able to simulate physics, they're gonna be able to simulate human actions and dynamics increasingly well and predictably well. That was the thesis about around our efforts on world models, and we spin up this research group to just focus on the world models and how do we turn the video generation models that we're building into something broader and something that would be useful beyond, also content creation as well.Swyx [00:25:04]: And that was roughly when?Anastasis [00:25:06]: Yeah, so that was inSwyx [00:25:06]: OhAnastasis [00:25:07]: In late 2023.Vibhu [00:25:08]: Interesting. like, I think, a lot of people have been saying a lot of video gen model companies have all pivoted to world models these days, but like, 2023, you're posting it. oneWorld Models: From Video Generation to SimulationSwyx [00:25:21]: It's, it's debatable whether it's a pivot.Vibhu [00:25:23]: Yeah.Swyx [00:25:23]: Like, arguablyVibhu [00:25:24]: YeahSwyx [00:25:24]: That's what you always had to do anyway, right?Anastasis [00:25:26]: It's in a way an expansionVibhu [00:25:28]: YeahAnastasis [00:25:28]: Of the applicationsVibhu [00:25:29]: YeahAnastasis [00:25:29]: Of the models as they become more capable.Vibhu [00:25:31]: The early signs, it seems like the original models you guy had, guys had, people would say it's very not bitter lesson pilled, right? You're adding, rewriting prompts, you're having all these one-off things, but that's just the state of the tech as it was versus the future of as you said, you can scale it up as, we can scale up to world models.Anastasis [00:25:50]: Yeah. So it just became. And if you looked at the outputs of Gen-2Vibhu [00:25:56]: YeahAnastasis [00:25:56]: It was not. I think it was not obvious to people that this would scale to become a general simulator of the world. Like, you had very limited movement, you had, very low fidelity or low resolution, like obvious mistakes in human anatomy, like all kinds of limitations. But it was just, the idea was that's just GPT-two, and GPT-two, it can barely generate, like, coherent sentences. Similar, Gen-2 can barely create coherent video, but if you scale it up, you're gonna. There is no reason why it shouldn't work in a way. It's, And I think that was. That's, that's always the mindset of Runway is like this extrapolation of, like, if, like, even when we started in 2018 and you looked at the results of the day, you need to look more at the trend of, like, where we were in 2018 versus when we were at the, when the first GAN came out in twenty, four 2014 or twenty, fifteen. And, you started from, like, thirty-two by thirty-two images of faces, and then by the time in 2018, you could generate, street images at the 1K resolution. And it was the same with world models, very early signs of something much bigger.Swyx [00:27:08]: Yeah. I was gonna say, like, it's diffusing into focus. Like, if you look at our visible output from year to year, it looks like a diffusion process itself.Anastasis [00:27:17]: Yeah.Vibhu [00:27:17]: Especially watching the early, like, old blog posts, you can really see the choppiness, the details.Anastasis [00:27:24]: Yeah. Like human civilization starting from random noise and thenVibhu [00:27:27]: YeahAnastasis [00:27:27]: Denoising intoSwyx [00:27:28]: Yeah. Just run it a hundred years.Anastasis [00:27:30]: Civilization.Swyx [00:27:30]: Yeah.Vibhu [00:27:31]: That's how you're on track, you're still noising, right?Swyx [00:27:34]: Yeah. I like the way that you guys phrased it when you, announced it in June, which is, oh, that you had a video essay. “The human mind is no longer the center of AI. Our world is.” Right? Which is, let's, let's call it the past five years of LLM-based AI is very much like trying to emulate human preferences and human speech. But now that's, like, mostly solved. I think that's, like, some of the context of your essay, which you also wrote around the time. And now it's like the focus is on modeling the world accurately.Scaling Laws for Video and Why Predicting Pixels MattersAnastasis [00:28:03]: Exactly, yeah. So the way we see it is, there is that, initial mission statement of DeepMind, which is, solve intelligence and then use it to solve everything else. But I think it's starting from everything else, could be valuable of, like, starting from. there is just so much complexity, and detail in the world that in order to. That it's, it's hard to learn directly from just human descriptions of the world. Like, we're assuming that, like, language models learn from everything that humans have written about the world, like our own understanding as of, the twenty twenties. And there is just so much that we don't know and so much that's not captured by existing text, about both the low level dynamics of the world, like we're not describing in detail. if I tell you to describe, like, how do you tie your shoes, that's a very difficult thing to describe in words, but it's very obvious thing to demonstrate. And so I think there's been. And there's, more of X paradox, like we're constantly underestimating all the complexity that goes into very, like, things that we do subconsciously as humans, and we don't even necessarily always have the words to describe them. And so in my mind, the simulating the world and simulating, physics, simulating the dynamics of the world has always been underestimated, compared to, we place too much emphasis on the things that are easy to talk about. but there is just all this complexity and richness of the world that if we just try and train directly on that observational data instead of training on how people describe the world, we would learn something new that we wouldn't otherwise know.Swyx [00:29:54]: You think that the present architectural paradigm is fine? You don't need, like, another layer, like JEPA, like another famous, New York AI leader would say?Anastasis [00:30:05]: We're a very pragmatic research lab. If, we have evidence that an approach works better than the approach that we're taking, then we have no qualms to taking it. We just have seen no indication that video prediction itself doesn't scale. And even if you look now, not just our work, but the work of others, you're seeing in robotics some of the most promising work, starts from video prediction models, and then you adapt them to also the action models, for example. so there is very little evidence that you need something else and that your time is better spent on a novel architectural change compared to improving data and improving the, and scaling the current approach. And so, We don't have any indication that. the, there is that counterargument that I think there was a tweet by Yann LeCun a few days ago that, understanding the dynamics of the world is very different than, generating, cute videos.Swyx [00:31:05]: And your answer is no, they're the same thing.Anastasis [00:31:07]: Yeah, they're the same thing.Swyx [00:31:08]: My cat videos are the same as understanding physics.Anastasis [00:31:11]: Right, because if you wanna generate. video models can cheat and, like, they could you could give, like, successive dif shots of the scene in a way that doesn't require you to simulate difficult physics. There is like, all these different ways in which you can hide the deficiencies of the model, and it's important not to be too tricked by the performance of the current video models. It's easy to, cherry-pick examples and think that video models are further advanced than they are. So there is a lot more work that we need to do to improve those models. But in my mind, very similar to language, and, like, we've. you go from barely coherent sentences to something that, could hold a conversation with a human to something that could can operate autonomously for a day and, like, create entire code bases. And the main difference, there is some architecture improvements along the way, but the main thing is scale. And so it's the same bet for video, and we have no indications that this is saturating. Like, we have benchmarks that we use for measuring the physics of those models, and we see those predictably improve as we scale those models. So there is. If you want to Google up, Physics-IQ, is one of those benchmarks that measures how well does the model perform at solid mechanics or fluid dynamics or optics.Vibhu [00:32:32]: I'm curious if you've seen any emergence, any scaling law around this.Swyx [00:32:37]: Yeah, he's saying there is a scaling law, right?Anastasis [00:32:39]: Exactly.Vibhu [00:32:40]: Yeah,Anastasis [00:32:40]: So the way those models, those benchmarks work is you. the researchers have gone and, like, captured, a few videos that are representative of different physical phenomena, and then you can take the first frame and then pass it through an image-to-video model and then generate a rollout that shows what should happen next. So you have, a ball hanging from the ceiling, and then you use that as input, and then you the model predicts how the ball should fall on the ground. and this measures. we have an intuitive understanding of physics. I know, you can imagine what will happen next if I drop this bottle. So it's measuring that same intuitive physics understanding of those models, and we've measured that at different model scales, and we see, and compute scales, and we see that the score on physics IQ predictably improves. There's other, tricks and techniques that you can make to improve the score even further, but even scale alone helps, in the model learning better physics.Swyx [00:33:40]: My main sympathy with Yann LeCun is the, Plato's cave allegory, right? Like, you're, you're, like, learning on the output of a thing, not the internal process of a thing, and it's very noisy. And, if only you could observe the internals of a thing. It's hard to observe the internals of a human mind, but you can very much observe, or at least we have a whole branch of science and physics that we're ignoring on how to model Physics and movement and, gravity and, other interactions. and we're just, like, throwing away all of that and just saying just scale data, which is very much the lesson of unsupervised learning, but it feels wrong. that's the main idea.Anastasis [00:34:21]: I think the history of machine learning is, at large, it feels wrong.Swyx [00:34:25]: Yeah. It's a bitter lesson, right? Yeah. It's, it's, it's the simple answer to that.Vibhu [00:34:29]: I guess, how much can you scale? So, like, even on, let's say, the video generation side, like, there's one side of video understanding. Video generation, are we still gonna have tools where it's like, I wanna generate two hours, twenty hours? there's a infra way to do it in batches and stitch it together, but, like, do we just keep scaling? Do we just continue long generation consistency, all that at scale? And, like, tying it into where we're at now from we looked at Runway two to four point fiveGen-3, Sora, and Runway's Scaling InflectionAnastasis [00:34:58]: Yeah.Vibhu [00:34:58]: Like, technically, what advancements have we made to today, and then where do you see things still going?Anastasis [00:35:04]: So part of the answer is definitely scale. and that was. We learned that lesson in a big way for with Gen-3. So Gen-3 was the model we released the year after, like in 2024. That was a few months after Sora was released. so yeah, there's an interesting story of that came to be as well. Gen-3 for us was, the first time that we really needed to build. we had to learn all the lessons that the language model world learned in two in three years in the span of a few months. one of the biggest changes of Sora was using diffusion transformers instead of convnets. So a lot of the early, latent diffusion models were all, convnets for the diffusion model part. And the diffusion transformer paper came at some point in 2023, and it showed scaling laws for image, diffusion transformers. And we realized at that point that we needed to invest in infrastructure for model parallelism, for really scaling training to larger than, a few billion parameter models. And we spent maybe the, most of the fall of 2023 building out our infrastructure for distributed training. And we had a lot of false starts and a lot of failure in trying to scale, image and video diffusion transformers. And at that point, February 2024, Sora comes out, and the results areAnastasis [00:36:35]: Very much superior to what Gen-2 could produce. There were a lot of, a lot of chatter on Twitter about Runway. Runway's done. like, there is no way Runway will catch up. And if you remember, also OpenAI in the early twenty-It felt very, like it's aSwyx [00:36:56]: To the moonAnastasis [00:36:57]: It's a formidable opponent now, but at that point, it, they were on the top of their game. nobody could even get close to them. There was maybe Gemini was just the first version of Gemini had just released. So when OpenAI came with Sora and it was such a big jump of like quality, it gave me, there was like an existential crisis for a few hours. But that, I think the amazing thing about Runway and like I think the, we've been around eight years now, which is almost we're dinosaur in AI, and we had to like, we had there was a lot of those moments we had to learn, adapt very quickly and build out skill set in the team that we didn't have. And so, if you ask anyone what is their favorite time at Runway that was there during that time, it was that push in like three months to get to a model better than Sora. and it, we scaled 10x the model scale, the model size and the, compute that we were training on. we figured out model parallelism. We had zero expertise in that. And then we came out with Gen-3 during that summer. So that was a big turning point, I think, for the company where the research org grew very quickly, and we really started pursuing this vision of the general world model, in earnest, I think after Gen-3 was out.Swyx [00:38:12]: Yeah. that's the amazing thing about building when you're building. There's no stack to. You have to invent everything yourself. You have to be completely full stack. Now I think like there are inference specialists like Fal or whatever that can help with like, model serving, and I think you guys work with them as well. but yeah, like it's, it. But at the time, it was just. It's very interesting to think about what you do when Sora comes out and people are questioning whether your company should still exist.Distillation, Turbo Models, and Real-Time VideoAnastasis [00:38:41]: Yeah. And yeah, there was no, there was no VLM of diffusion models. Like, we had to build the whole model serving infrastructure and make things efficient. And a few months after we released Gen-3, we released the Turbo version, which I think was the first step-distilled model in production.Swyx [00:38:56]: That was a whole trend that we covered as well. Yeah.Anastasis [00:38:59]: So that allowed us, to serve those models at the larger scale, ‘cause I think the first version of Gen-3 was quite, expensive to serve.Swyx [00:39:09]: I think the whole like trend in like consistency models, Lightning and, Turbo and all these things somehow didn't really stick around. I don't know if you have any reflections on this. Because at the time, I was like, “Well, everything should start with a distilled model first, and then you can upscale,” right? It. your bigger models just turn into fancy upscalers, but like you should always draft with a smaller model and faster model, right? Because you can get it so quickly, like near real-time.Anastasis [00:39:39]: Yeah. I would not be so sure to say that didn't stick around. I think that, it's, it's likely to. that there is a lot of step-distilled models that are actively used in production. there is still a gap in quality compared to the, non-distilled model. but in my mind, we're still. there is a two to three year offset from language models. So the things that, So it's just a matter of time before there is better distillation techniques. we use. Right now we have a real-time model core character that I think is the largest deployment of real-time video models, that's a step-distilled model, and it's actively being used. It's a very specific use case compared to a general video model. So this is aSwyx [00:40:27]: Very cool, by the way.Anastasis [00:40:27]: This is avatars stuff, right?Swyx [00:40:28]: Consistency, character.Anastasis [00:40:30]: Yeah. So this is a talking avatar, model. we were able to. we optimized the hell out of it, and it generates at 24 FPS, and it's a, it's a step-distilled autoregressive video model. So if we look at our world model direction, a big component of it is starting from the bidirectional diffusion that generates entire video at once and making autoregressive shows. So you generate one frame or a few frames at a time. so there's a lot that goes into that pipeline of getting to a real-time model. It's first you need to make it into a causal autoregressive model, and then you just turn it into. You need to do some additional step distillation to get it to be real-time. and I think that part is just starting. I'll be very surprised if we're, two years from now, we don't primarily use real-time models. To me, real-time video generation is just inevitable that, it has much better user experience, it's much cheaper to serve, and, the quality gap between the base model and the real-time model is only gonna close as we figure out better, distillation techniques. And we made a lot of progress there internally on maintaining the quality of the base model when we distill them.Swyx [00:41:49]: How much of this is transferable? So is it the same base model? Like if you're doing diffusion across the whole sequence and you're converting it to step autoregressive distillation, is this like distillation where you still need to train both, you can use the same base and converter? What's that process like to go from regular model to something that's real-time on a technical level?Anastasis [00:42:11]: So the nice thing about diffusion models is you have, two axes of distillation. So there is the. You can distill to a smaller model, which resembles what you do in LLMs, or you can distill in terms of taking less steps, less diffusion steps. So you could take a model that generates in fifty steps and generate in four steps and get to, You have some performance, degradation, but very often you get comparable outputs. So you can even take the large frontier model and distill it with step distillation and get to a real-time performance, and that's what we've seen. So, depending on the use case, in some cases we might also serve with a smaller model, but in a lot of use cases, we just use theSwyx [00:42:56]: Step distillationAnastasis [00:42:56]: The frontier model, and we're able to make it work in real-time.Swyx [00:42:59]: I think this might be a good time to cut over to his laptop to show off some of the real-time stuff that you're doing.Interface World Models and Neural SoftwareAnastasis [00:43:06]: This is one of the research updates that we did recently. so we've been working and f in getting our general world models to, different applications. one of them that we think is very compelling is using general world models as essentially, an interface, a universal interface to software. This is a version of our world model that's called an interface world model. and the idea is that it essentially, replaces, the, front end of a software application. It renders the pixels directly of an interface and is trained to predict what happens next as a result of, a click or another interaction you have with the interface. So this is all pixels. it's there is no HTML, CSS, React that's powering this interface. This is directly at the output of our real-time, video generation model, and it takes clicks directly as input.Swyx [00:44:09]: And drags, click and drag.Anastasis [00:44:12]: Right. So it supportsSwyx [00:44:13]: Ooh.Anastasis [00:44:14]: Yeah, clicks. It supports drags. it also supports scrolling. and the amazing thing about this is that you can effectively describe in the prompt how you want different elements, like what do you want the behavior of different elements to be. So it's almost you're you can turn, an interface from, markup language description of, like, an HTML interface, and instead you can just describe the interface. if I press this button, I expect this to happen. If I press this button, this should happen. And it's useful, we believe, both for prototyping, for, like, just testing, like, what different interactions would feel like. you can also add audio to it. So it's a video audio generation model. So you get you essentially can describe both what the visual outcome should be of your click and also what the if there is a sound effect that comes out of it. So we believe that's gonna be a much more flexible way of building software. Just render. It just, in why generate the code that generates the pixels? Just generate the pixels directly.Anastasis [00:45:18]: It's the end-to-end philosophy applying applied to front ends.Anastasis [00:45:25]: So we think there is a few interesting use case. So you can build creative tools on top of it.Anastasis [00:45:32]: We think that, for any use case that involves a lot of exploration or, like, educational use case where you wanna learn about a new concept and you want some visualization and like, and open-ended exploration, we think those this is a very powerful, approach. you can imagine new forms of, design, industrial design software that could emerge as a result of those models. And this is all, generated in real-time as well. So, you can build a lot of interesting camera transitions and forms of interaction that are very difficult to build otherwise. And one way in which we evaluate this is what if you try to generate the same interface with Claude by just, prompting Claude, “Here's an image reference of my interface that I made in Figma or that I created somewhere else. create this particular interaction,” which in this case it's, drag that object, upwards. and beyond it being slower, it's also very difficult to capture some interactions by just fully, with just LLMs. So we think that this is likely to be the way that a lot of the future, like, software in the future will be created. and one of the additional benefits is personalization might be a lot easier done with those models. Like, you can essentially try out different prompts based on who is visiting the interface. You can, more easily, prompt engineer the interface to have larger size, text for more accessibility reasons, or you can make this or, like, if you have a particular aesthetic preferences. So we're very excited about this approach. It's early days, and I think we'll need to, make it more cost-effective as well to serve those models ‘cause, running a real-time video model versus just purely rendering HTML, there's -- the computational needs are much higher. but we do see a lot of potential in this approach to building front-end interfaces.Swyx [00:47:47]: So we covered this similar thing with Flipbook before with our, Ethan Hara episode with Groq, video. And yeah, I think it's very engaging visually. I think it's maybe very good for education, but it's it does sound expensive. I think there's an upper bound to how expensive it will be, though, right? Like, the inference cost will go down over time. You'll figure out ways to optimize it. Effectively, when it pauses, you don't you're not receiving human input. You don't have to generate anything, right? So.Anastasis [00:48:14]: Yeah, you could also. Like, in this case, you have ambient motion, so there is parts of the screen that might. if you're let's say you wanna, visit Paris and then you get this interface that allows you to explore.Swyx [00:48:29]: People walking. Yeah.Anastasis [00:48:29]: You have people walking or, like, things happening. But, it's, it's a no Yeah, it makes it more expensive because you need to run the model all the time. Maybe you have some looping mechanism so you don't need to do that. But all those things, I think, is stuff we'll need to figure out.Toward a Fully Neural Operating SystemSwyx [00:48:44]: Yeah.Anastasis [00:48:44]: I think our first consideration is let's make this clearly find some use cases where it's clearly a much more compelling interaction compared to traditional interfaces. And then it's a matter of time before it becomes more cost-effective to serve.Swyx [00:48:58]: Yeah. When it comes to the people walking, I think the approach that makes the most sense to me is Nick.Anastasis [00:49:04]: Nick.Swyx [00:49:04]: Oh, God. I keep messing up their name. With Chris Manning and Fanny Yan. I don't know if you've come across them, where they. Mapped to some game engine. I think it's Unity or something, or Godot. And they you can script some NPC behavior behind that and train on that. Whereas here, you can really imagine whatever you want. Like, that is a UI, right? Like, and it feels, like, more tractable, I guess, to, create a world model of software that is interactable because we have many of examples of that, and you can, do your fancy RL environment stuff on that than it is scaling up to embodied and real-world physical use cases. But this is a nice first step.Vibhu [00:49:43]: Or, there's the opposite of you have, like, one B models, three 50 million parameter language models. It just gets so small that they're just predicting, like, fishes moving.Swyx [00:49:53]: Small models are now 120 B, so.Vibhu [00:49:57]: Ultra mini on device.Vibhu [00:49:58]: But, no, I think it, like, it puts it into perspective, at least the car one for me, like, the applications, right? The amount of work to do that, sure, you only make one model year car per year, but applying this, it's also a cost-saving to have to manually make all this, right? So it opens up a lot of possibilities, too. I'm curious if you extend this out two, three years, so where do you see things going even further?Anastasis [00:50:25]: Effectively, the end game of something like interface world models is you have, a fully neural operating system. So I think, Andrej Karpathy has written about that quite a while back. But it's, You, I think to me it's, it's a bit, it's a bit odd that, we have, for example, with an interaction with an LLM of today, you have this LLM that can talk to you about anything. It can You can take the conversation in any direction. You can It's very general, so it can solve all those different tasks, but you interact with it through a very rigid interface. And so to me, it's just a matter of time before the interface itself becomes learnable and becomes, part of the whole loop of, like, you're not just delivering. You're delivering an application end-to-end, and that means you're delivering the language model, but you're also delivering the render and the pixels and that's also a learnable component. And the concept of applications might not necessarily. I think we'll need to figure out new abstractions for software. the concept of application comes from this idea that you need, separate code bases to describe, to, for, to power each individual, tool and each individual application. But you might think of something a lot more unified if you're. if you have, a video model that's generating the interface as you go. so it can take context from an LLM and allow you to combine different functionalities that traditionally would live in different applications. So it's a, it's a way to solve, software end-to-end, effectively. We also see this as a powerful way to train computer use agents as well. so this is, one way to see this as. And in general, with world models, there is those two directions. One is world models for humans and world models forSwyx [00:52:24]: AgentsAnastasis [00:52:24]: To train agents.Swyx [00:52:25]: Yeah.Anastasis [00:52:25]: And so for every new work of, world models that we do, we have this both uses become possible. So this is a powerful synthetic data generator for training computer use models. It could become, a live, RL environment that you could use to do online RL with a computer use agent, and you can get wide diversity of different interactions, kinds of interfaces, just generated on the fly that, to improve the how robust the, your agent, becomes. So that's the same also with the world models that we're working on for a robotics use case as well.Long Context, Error Accumulation, and Autoregressive VideoSwyx [00:53:02]: Is there a research breakthrough that you're Waiting for that would unlock the next set of use cases that you really wanna pursue?Anastasis [00:53:10]: Long context is a very important one, so being able to maintain consistency for long periods of time, and that depends on the use case. So for our characters model, for example, or for the interface world model, it's easier to maintain long sessions of interaction. If you go into more open-ended worlds that you navigate and you take arbitrary actions in, we, like, there is more the context at which you can and duration which you can generate becomes limited much more quickly.Swyx [00:53:40]: Yeah.Anastasis [00:53:40]: So we see more degradation and error accumulation happening. so the biggest challenge with autoregressive models is error accumulation, is you're feeding generative frames back into the model to generate the next The next frames. And if there is any small errors, they accumulate over time. That's not a new problem. It's a problem that LLMs also have, and we've seen the ability to generate now really long outputs. So it's a solved problem, but it's definitely still a challenge.Swyx [00:54:08]: Yeah. And what is the state of the art? so for Grok, it would be like 10 to 20 seconds of context going in there for video.Anastasis [00:54:16]: With our characters models, we're able to generate up to 30 minutes of video autoregressively.Swyx [00:54:21]: Yeah. But that's just for the avatars.Anastasis [00:54:24]: Yeah. So if we look at, GWM Worlds, which is more our open-ended world exploration model, it's, it's on the order of a few minutes, which is Yeah, soSwyx [00:54:35]: Probably enough for people because you have to cut to the next scene anyway, right?Anastasis [00:54:40]: Yeah, it's not, it's not the ideal game experience if you have to restart every few minutes. So I think. But, I think it's. Yeah, for certain kinds of game experiences, you can work around it.

We're recording at 7:15pm and going to bed at 7:30, which means we are bending time and space to record this. First up: TTL Mad Libs, a new segment submitted by Mike the Botox guy, in which we fill in a Kona race guide and somehow end up with Pierce Brosnan at the finish line. Then we get through a full question bag before someone's bedtime.This week we discussed:Kona apparel update: almost everything sold out; what's still available at the Castelli booth on race day and why you can't say "Kona" inside the expoYour proudest Strava CR or QOM — Eric's COVID-era Portland climb rampage, Paula's Bend segments, and Nick's Santa Monica Pier sprint UpLosing 30-45 seconds per mile in the second half of a 70.3 run: fitness limiter, pacing problem, or both?How pro personal needs bottles work at 70.3 Worlds — the sticker system, race number order, and why Paula's never actually used oneThe best triathlon commentatorsShould athlete vitals be shown on the broadcast? Alcohol before a key race — how Paula and Eric have approached it differently this year, and the NA whiskey price problemWaterproof shoes for a 240-mile trail race: Gore-Tex uppers, the bathtub water retention test, and the dry pair rotation strategyCooling techniques for extreme heat: ice bandanas, hands, neck, and where not to put ice cubesAero helmets, bucket hats, and the Omius — where the line is between functional and ridiculousTorn wetsuit: repair it, cut the sleeves off, or buy new? A big thank you to our podcast supporters who keep the podcast alive. To submit a question — or a Mad Libs — head over to ThatTriathlonLife.com/podcast

Yes, I know it sounds bad and you'll hear me realize halfway through that my microphone is broken. I'm doing my best! This week we're talking Taskmaster, Golden Axe, Resident Evil, and Despicable Me 4. It's a real Mad Libs over here!

What do Mad Libs obituaries, Elvis impersonations, shout-outs gone horribly wrong, and wishing inanimate objects a safe journey have in common? Apparently…this episode.

Michael Sorg and Katie Dudas are joined by Sam Eitzen, CEO of Snapbar, for a deep dive into how artificial intelligence is changing experiential marketing, trade shows, conferences, brand activations, and the humble photo booth. Sam explains how Snapbar evolved from physically hauling hundreds of photo booths to events into building a web-based platform that lets brands create interactive experiences accessible from an iPad, touchscreen, QR code, or an attendee's own phone. What started as a necessary pandemic pivot has developed into AI photo experiences, highly personalized AI Stories, and new ways for brands to combine entertainment with lead generation. The conversation also gets beyond the AI hype. Sam discusses the unpredictability of image models, why prompt engineering still requires humans, how Snapbar tests and switches between different AI models, and why brands need to understand that generative AI is not simply automated Photoshop. Snapbar's system remains cloud-based, meaning connectivity and third-party model reliability are still real considerations for live events. Topics and products discussed: What experiential marketing actually means: Sam distinguishes traditional broadcast and digital advertising from interactive marketing designed to bring the audience into the experience through participation. Snapbar's origin story: The company began as a side-gig photo booth business before moving from weddings into conferences, trade shows, sporting events, product launches, festivals, and other B2B activations. The pandemic pivot: When physical events disappeared in 2020, a client asked whether Snapbar could bring its photo experiences online. That request became the foundation of the company's current web-based platform. World Cup fan activations: Sam describes branded soccer experiences that let attendees transform themselves into stylized or animated fans and players without improperly copying team intellectual property. QR codes instead of long lines: Experiences can run on event iPads while also letting thousands of attendees participate from their own phones by scanning a QR code. Understanding the audience: A soccer activation that works at the World Cup may flop at a legal conference. Sam says cybersecurity audiences, for example, often respond particularly well to gaming, fantasy, and trading-card concepts. Digital experiences as event swag: The group discusses whether personalized digital content can become an alternative to another pile of branded pens, bottles, and promotional giveaways. Snapbar's planned digital spinner wheel: Sam explains a digital version of the familiar trade-show prize wheel with customizable branding, prize probabilities, inventory management, QR control, redemption codes, and lead capture. The rise of the AI photo booth: Early image generation was unreliable, producing extra arms, heads, and other artifacts. As models improved, AI photo experiences became one of Snapbar's biggest products. AI Stories: Snapbar adds Mad Libs-like personalization to AI-generated experiences, allowing attendees to influence the resulting scene while brands maintain controls over the experience. Taking event tech into unusual environments: Sam recalls activations at music festivals, on boats, and experiences that attendees could even access while traveling because everything is web-based. Working across AI providers: Rather than building its own image models, Snapbar evaluates available third-party systems and can shift between models depending on prompt adherence, realism, animation style, and client needs. Why testing matters: AI models can regress or behave differently after updates. Snapbar's team tests experiences ahead of events, attempts to break them, adjusts prompts, and can intervene while an activation is live. Treat AI like a new team member: Sam suggests thinking of AI less like an infallible machine and more like a new employee that needs context, supervision, defined permissions, and an understanding of what it does well. AI is not automated Photoshop: Clients sometimes expect pixel-perfect control, but generative systems still involve prompting, probabilities, and outputs that cannot always be completely dictated. Why AI may not magically fix event networking: Sam pushes back on the idea that feeding hobbies and job titles into an AI matchmaking system automatically creates meaningful human connections. Event attendees ultimately want genuine personal and professional connection. The danger of easy AI startups: AI makes prototypes and products dramatically easier to build, but that also means competitors can build similar products just as quickly. Distribution becomes the advantage: Sam argues that customer relationships, audience access, SEO/AEO, reputation, and reaching the right buyers become even more important when everyone has access to powerful AI tools. Learn more about Snapbar at https://snapbar.com, which Sam specifically shares at the end of the interview.

Michael Sorg and Katie Dudas are joined by Sam Eitzen, CEO of Snapbar, for a deep dive into how artificial intelligence is changing experiential marketing, trade shows, conferences, brand activations, and the humble photo booth. Sam explains how Snapbar evolved from physically hauling hundreds of photo booths to events into building a web-based platform that lets brands create interactive experiences accessible from an iPad, touchscreen, QR code, or an attendee's own phone. What started as a necessary pandemic pivot has developed into AI photo experiences, highly personalized AI Stories, and new ways for brands to combine entertainment with lead generation. The conversation also gets beyond the AI hype. Sam discusses the unpredictability of image models, why prompt engineering still requires humans, how Snapbar tests and switches between different AI models, and why brands need to understand that generative AI is not simply automated Photoshop. Snapbar's system remains cloud-based, meaning connectivity and third-party model reliability are still real considerations for live events. Topics and products discussed: What experiential marketing actually means: Sam distinguishes traditional broadcast and digital advertising from interactive marketing designed to bring the audience into the experience through participation. Snapbar's origin story: The company began as a side-gig photo booth business before moving from weddings into conferences, trade shows, sporting events, product launches, festivals, and other B2B activations. The pandemic pivot: When physical events disappeared in 2020, a client asked whether Snapbar could bring its photo experiences online. That request became the foundation of the company's current web-based platform. World Cup fan activations: Sam describes branded soccer experiences that let attendees transform themselves into stylized or animated fans and players without improperly copying team intellectual property. QR codes instead of long lines: Experiences can run on event iPads while also letting thousands of attendees participate from their own phones by scanning a QR code. Understanding the audience: A soccer activation that works at the World Cup may flop at a legal conference. Sam says cybersecurity audiences, for example, often respond particularly well to gaming, fantasy, and trading-card concepts. Digital experiences as event swag: The group discusses whether personalized digital content can become an alternative to another pile of branded pens, bottles, and promotional giveaways. Snapbar's planned digital spinner wheel: Sam explains a digital version of the familiar trade-show prize wheel with customizable branding, prize probabilities, inventory management, QR control, redemption codes, and lead capture. The rise of the AI photo booth: Early image generation was unreliable, producing extra arms, heads, and other artifacts. As models improved, AI photo experiences became one of Snapbar's biggest products. AI Stories: Snapbar adds Mad Libs-like personalization to AI-generated experiences, allowing attendees to influence the resulting scene while brands maintain controls over the experience. Taking event tech into unusual environments: Sam recalls activations at music festivals, on boats, and experiences that attendees could even access while traveling because everything is web-based. Working across AI providers: Rather than building its own image models, Snapbar evaluates available third-party systems and can shift between models depending on prompt adherence, realism, animation style, and client needs. Why testing matters: AI models can regress or behave differently after updates. Snapbar's team tests experiences ahead of events, attempts to break them, adjusts prompts, and can intervene while an activation is live. Treat AI like a new team member: Sam suggests thinking of AI less like an infallible machine and more like a new employee that needs context, supervision, defined permissions, and an understanding of what it does well. AI is not automated Photoshop: Clients sometimes expect pixel-perfect control, but generative systems still involve prompting, probabilities, and outputs that cannot always be completely dictated. Why AI may not magically fix event networking: Sam pushes back on the idea that feeding hobbies and job titles into an AI matchmaking system automatically creates meaningful human connections. Event attendees ultimately want genuine personal and professional connection. The danger of easy AI startups: AI makes prototypes and products dramatically easier to build, but that also means competitors can build similar products just as quickly. Distribution becomes the advantage: Sam argues that customer relationships, audience access, SEO/AEO, reputation, and reaching the right buyers become even more important when everyone has access to powerful AI tools. Learn more about Snapbar at https://snapbar.com, which Sam specifically shares at the end of the interview.

One of our favorite things growing up was filling out Mad Libs. These sometimes hilarious, but always ridiculous, stories were a fun way to pass the time. For this episode, we thought we would bring them back and this time Disney themed! We hope you enjoy!Check out our enchanting extras:⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://linktr.ee/WonderfulThingAboutDisney⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

Right now, before a single snap has been played in Week 1, your fantasy football waiver wire is the most wide open it will be all season. Nobody has panicked yet. Nobody has dropped anybody. This is the window. Kendall Valenzuela, Dwain McFarland and Peter Overzet each bring four moves to make before Week 1 kicks off — real adds and stashes on players who are still sitting on waivers in most leagues. Dwain goes to Terrance Ferguson, who could climb into top-12 tight end territory if he has a real role in Los Angeles, then Ja'Kobi Lane, and closes with a genuine sicko stash between Demond Claiborne and Kaytron Allen. Pete makes the case for a rookie receiver stash with Ted Hurst, Antonio Williams and Chris Bell, then Kaleb Johnson, then a Chargers tight end between Oronde Gadsden and Charlie Kolar. Kendall goes rookie running back with Jonah Coleman and Nicholas Singleton, then Malik Davis, then Malachi Fields. Every add comes with Fantasy Life's Week 1 projections — targets, receptions, yards, and the bust, median and ceiling outcomes — so you know exactly what you're rostering and what the range looks like. Then the back half flips to Utilization Mad Libs: the players they still have real questions about, and precisely what usage would change their minds. If Dalton Kincaid runs 80% of routes, he moves into the top eight tight ends. If Makai Lemon runs 85%, he becomes a WR3 with upside. If Jordan Mason takes a 60% rush share, he's a low-end RB2. Those are the exact numbers to watch on Sunday, and knowing them ahead of time is how you get to the wire before everyone else. Learn more about your ad choices. Visit megaphone.fm/adchoices

Reminder - you can see the pod pics if you become a Patron. The good news pics are at the bottom of the show notes of each Patreon episode! That's just one of the perks of subscribing! patreon.com/muellershewrote Listener Survey: http://survey.podtrac.com/start-survey.aspx?pubid=BffJOlI7qQcF&ver=short Follow the Podcast on Apple: https://apple.co/3XNx7ck Want to support the show and get it ad-free and early? https://patreon.com/thedailybeans https://dailybeans.supercast.com/ https://apple.co/3UKzKt0 Hosted by Simplecast, an AdsWizz company. See https://pcm.adswizz.com for information about our collection and use of personal data for advertising.

Our Sports Expert, Melissa McGurren, tried her best to predict the 2026 College Football season with the help of MadLibs!

Mason can't stop saying weird stuff, Daniel asks us to guess how old things are, and Danny hosts a particularly special round of MadLibs. 

Mad Libs are back! When we aren't struggling with action verbs, Dane is getting sent to the dunk tank, Samuel is raving about Chick-fil-A's new menu, and the guys give their super early Super Bowl predictions.---Please message us if you would be interested in joining our Fantasy Football league. You can do that via email or Instagram DM.---If you want an Until Next Week Podcast shirt for $20 (+shipping), email untilnextweekpodcast@gmail.com or DM us on Instagram. (Large & XL available)---Please follow our Instagram & TikTok to stay updated on all things podcast and make sure to send us a voice message via Instagram DM to be featured on one of our next episodes.https://www.instagram.com/untilnextweekpodcasthttps://www.tiktok.com/@untilnextweekpodcast---Please leave us a 5 STAR REVIEW on both Spotify and Apple for a chance to be mentioned on a future episode.---Get $10 off at Friday Pickleball with a minimum order of $95: [MUST CLICK LINK BELOW]https://www.fridaypickle.com/discount/SAMUEL14434---Get 10% off your order for a Bloom Card with the following code: SAMUEL14434https://bloom.inc---Key words for the algorithm: Clean Podcast, Clean Comedy, Friday Pickleball, Ghostrunners Podcast, Correct Opinions Podcast, Tim Hawkins Podcast, Becoming Something Podcast, Youth Group Chronicles Podcast, Almost Athletes Podcast with Dude Perfect, St. Louis Arch Grounds, Union Station, Chicken & Waffles, Catan, Bobblehead Haul, Bad Ebay Experiences, Fantasy Football, Alvaro Call, St. Louis Part 2, Springfield Cardinals, Early Christmas Music, Fantasy Busts, & Texas Belly Pete.

Inner Childish is what happens when two lifelong best friends hit record on the conversations they've been having since childhood: honest, hilarious, and never surface-level. Through their 25 years of friendship, Vic & Aubs have evolved a hundred times and somehow never outgrew the need to debrief every single thing together. Inner Childish is part sleepover conversation, part therapy session, and part voice memo you were never supposed to hear. Up first: why they started the show, how they landed on the name, and what to expect every Tuesday. You'll get the origin story of their 25 year friendship (yes, they were childhood neighbors born three days apart) and you'll really get to know your hosts through a Mad Libs roast covering who would thrive and who maybe wouldn't survive a zombie apocalypse, toxic traits, villain origin stories, and the things only a best friend would know. Vic and Aubrey also preview two new segments: Star 67, an anonymous call-in line where you can tell them anything, and Something Beautiful, a weekly reminder to notice one good thing in your day. Consider this your new favorite hour of the week. Subscribe and follow so you never miss an episode! Learn more about your ad choices. Visit megaphone.fm/adchoices

On this episode of It's a Bit on 10kTV: Bossman, Jake, and Sarge give their bits of the week including the Minnesota Twins and “The Field of Nightmares”. We also play our own version of Mad Libs, including our predictions on what JJ McCarthy will be doing for a career in 5 years. We end the show by blind ranking random Minnesota Athletes, and choosing the better Minnesota Wild and Minnesota Vikings all time rosters.

Carlos Greaves joins Ophira Eisenberg to talk about the strange math of building a creative career while raising an 18-month-old daughter, especially when your “job” is a shifting collection of satire writing, freelance work, teaching, and comedy. Greaves describes leaving electrical engineering after a film class convinced him he had chosen the wrong life, spending 12 years writing before opportunities at McSweeney's, The New Yorker, and elsewhere made comedy feel possible, and then discovering that the creative life he wanted came with plenty of regrets—and very little stability. As a stay-at-home dad in suburban Charlotte, he is constantly negotiating what it even means to be a working parent when his work happens at night and on weekends, while his wife's nine-to-five schedule means their respective “breaks” are essentially childcare traded for work; meanwhile, Ophira admits that 96% of her conversations with her husband are scheduling logistics. Their conversation turns to Greaves's book Obey in Advance: How to Survive and Thrive Under Authoritarianism, co-written with Ginny Hogan, and the challenge of writing political satire when reality moves faster than a joke and social media can claim a premise before a book ever reaches publication. Greaves explains why the book targets the atmosphere and institutions surrounding authoritarianism rather than relying on familiar impressions, using forms like Mad Libs, word searches, and fake editorial templates to make frighteningly repetitive political patterns visible—and argues that preserving joy can itself be a form of resistance. That idea becomes especially complicated as a parent: Greaves admits that bringing a child into a world facing climate change and multiple other existential threats requires optimism, even as he feels the terror of having “a piece of your soul outside your body” that eventually has to go out into the world. The episode also connects his instinct for satire to his childhood as an intensely rule-following, oldest-child, parent-pleaser who quietly found ways around the rules, including telling his parents he was sleeping at one friend's house when he was actually somewhere else. The conversation ends just as Ophira starts asking about the unavoidable dictator hiding inside every parent of a toddler—and Greaves's Ferris Bueller-adjacent teenage rule-skimming is the last thing left hanging before they pick up the story in part two.

Mason pitches a new opening game, Daniel can't stop laughing, and Danny hosts a childhood-ruining round of MadLibs. 

The HOBI Gang welcomes Jason back from his sabattical to review a slew of mediocre films, Jeff reviews House of the Dragon and Bryan is back on the Ted Lasso wagon! Plus Jason recaps Alaska, funniest sitcom moments, debating best rock songs of all time, Bryan is grossed out by Mad Libs and the crew list their Top Five Songs that Made a TV Moment! This episode is sponsored by the Cincinnati Comic Expo.

Remember Mad Libs? It's okay neither did Andrew. Well this week Veronica takes into the zany world of advertising much to Steve's dismay. We are all Creative Directors this week, or at least we think we are. Veronica takes us into the pitch room for brand partnerships with your favorite auto brands. Will we actually help Ferrari, Fiat and Lexus? Did we do well enough to sell the client? Steve says no.

In which Jimmy shares a new song about a little leaguer and Tommy challenges the guys to complete the lyrics of bro country songs by Florida Georgia Line.

This week we're lollygagging around a rapid fire covering a range of topics, problematic changes to the Home Run Derby, All-Star Mad Libs, an ABS stat update, and more! Do you have any questions or comments about Lollygagging Sports? Reach out to us on Bluesky: Bo Reed (@boreed009.bsky.social), Samantha Bunten (@samanthabunten.bsky.social‬), Lollygagging Sports (@lollygaggingpod.bsky.social). And on Twitter/X: Samantha Bunten (@samanthabunten), Matthew Irby (@IrbyStatMan), Lollygagging Sports (@LollygaggingPod).

This weekend marked America's 250th anniversary, but all we were talking about was what was going on with the wedding of the century. Over the holiday weekend, America's biggest popstar Taylor Swift tied the knot with football player Travis Kelce at New York's Madison Square Garden.  Stepping in while our hosts were away, Senior Features Editor Marley Marius sat down with two Vogue staffers who are Swifties and were closely following the wedding festivities: Anna Grace Lee and Anna Cafolla. Lee shared that she attended Swift's first ever MSG concert back in 2009 as part of her Fearless tour. The group discussed the unusual location, the surprising officiant Adam Sandler, the guests both expected and unexpected, the Dior dress, possible honeymoon locations, and everything in between.  “It reads sort of like Mad Libs,” Lee noted, “It's as if someone was like ‘Who would you have at your dream dinner party?' and then you could have all of those people.” Some of the standouts attendees included Karlie Kloss, Selena Gomez, Fergie, Gigi Hadid, Lena Dunham and Cara Delevingne.  The podcast also got a few dispatches from Voguers who were following closely over the weekend. Chloe, who is currently at Paris Couture Week, shared her speculations on Taylor's dress after attending Jonathan Anderson's Dior couture show, which classically closed with a couture bride. The rallying cry from fans and gawkers alike still remains: release the photos (please)!!   The Run-Through with Vogue is your go-to podcast where fashion meets culture. Hosted by Chloe Malle, Head of Editorial Content, Vogue U.S.; Chioma Nnadi, Head of British Vogue; and Nicole Phelps, Director of Vogue Runway, each episode features the latest fashion news and exclusive designer and celebrity interviews. Learn more about your ad choices. Visit podcastchoices.com/adchoices

Mason once again proves he's a nerd, Daniel informs us about a Korean event, and Danny hosts the WILDEST round of MadLibs you could possibly imagine. 

Colorado isn't much of a swing state anymore, but we're covering its primaries anyway. Both of its senators and one longtime member of Congress are facing bigger headwinds than you might expect. Our focus groups of Colorado Democrats will tell you why. Kyle Clark, host of Next with Kyle Clark, joins Sarah to discuss Colorado's upcoming primaries. Plus: Kyle's crazy run-in with the Republican frontrunner for governor, whether Rep. Lauren Boebert has gotten less crazy, and how Democrats feel about Gov. Jared Polis's pardon of Tina Peters.Show notes:Kyle's interview with Rep. Lauren Boebert

What does it look like to truly listen to your girl in a world filled with constant distractions, busy schedules, and endless noise? In this encouraging episode of the Raising Godly Girls Podcast, co-hosts Rachael Culpepper and Melissa Bearden unpack the beauty and importance of active listening—and how meaningful communication can transform the atmosphere of your family.  As part of this week's series on listening, Rachael and Melissa explore the difference between simply hearing words and intentionally engaging with the hearts behind them. From Bible doodles and journaling to silly family games and late-night dinner table conversations, this episode offers practical and grace-filled encouragement for families longing to reconnect in deeper, healthier ways.  Listeners will hear an insightful Raising Godly Girls Minute from Patti Garibay about kinesthetic learners, Bible journaling, and how doodling and note-taking can help girls store God's Word in their hearts. Whether your daughter is an external processor, a quiet observer, or somewhere in between, this conversation reminds parents that communication is not one-size-fits-all—and that curiosity, delight, and intentionality matter deeply.  Rachael and Melissa also tackle one of the biggest modern barriers to connection: distraction. From smartphones to after-hours work demands, today's families are constantly pulled in competing directions. But when parents intentionally create open bridges of communication, girls feel safe, valued, and heard. This episode offers simple but powerful phrases parents can begin using right away—questions and responses that cultivate trust, invite deeper conversations, and strengthen family bonds over time.  You'll also hear practical ideas for making communication fun again in your home through games like Mad Libs, one-word stories, and the classic telephone game—small but meaningful ways to create joy-filled moments of connection together.  Plus, the team highlights how ministries like American Heritage Girls, FamilyLife, Mama Bear Apologetics, and ScreenStrong are helping families build stronger relationships rooted in a Biblical Worldview.  If you've ever felt too tired to engage, unsure how to reconnect with your girl, or overwhelmed by the pace of modern family life, this conversation is a gentle reminder that listening well is one of the most powerful ways we love our children.    Three Things to Remember:  Find creative ways to make communication fun and ongoing in your family.   Keep an open bridge of connection between you and your girl.   Practice active listening responses that invite your daughter to share her heart.     Scriptures Referenced in this Episode:  Proverbs 7:1–3   James 1:19   Proverbs 18:13   Ephesians 4:29    Visit raisinggodlygirls.com for more encouragement and faith-based parenting tools.  Learn how to find or start an American Heritage Girls Troop in your community at americanheritagegirls.org.         

The HOBI Gang celebrates Bryan's birthday by kicking him out of the studio and welcoming in 1,000 Cheese Coney Pat! The gang is talking failed Batman villains, working for a mobster, sultry films, and the power of Kool-Aid Man! Plus the guys find out if aliens are real, climbing an active volcano, Disclosure Day is a hit, MadLibs goes awry and we list our Top Five Mindless Movies! This episode is sponsored by the Cincinnati Comic Expo.

Hosts: TJ, Brett, & Krissy This week on the show: Segment One (0:00:00): (0:00:00) It's some Pre-Show Magic, as TJ and Brett discuss the merits of two legendary backup QBs: Vince Evans and Bubby Brister. (0:16:07) TJ makes a State Of The Quad M Union address as it's been brought to our attention that Spotify has decided to censor and remove episodes of The Show from their platform (thanks for the heads up, Tennessee Lee!) and we give Spotify the hearty Eff You it deserves. (0:26:02): Brett and Krissy discuss the goings on during their time away including a vacation to Glacier National Park and a completed model. (0:47:15) TJ's time is not as exciting as his time involved helping The Mrs. housesit for The Carlsons, a nightmare with insane grass growth due to fertilization and Mother Nature being a ‘C', a new purchase, and steps being taken to deal with a vole infestation. Segment Two (1:15:59): (1:19:06) This weeks FGS brings us drunken drive-by droning! (1:27:20) HOT TAKES kicks off with some legendary passings in this week's GRIM REAPER ROUND UP. (1:36:03) The gang reviews the new films Masters Of The Universe. Segment Three (2:04:11): (2:06:15) KRISSY'S KRAZY KORNER brings us more Mad Libs. Hilarity ensues. (2:22:28) PICKS O' THE WEEK It's THE QUAD M SHOW!

Craig is on vacation!Griff is a caretakerRick has a popcorn problemand we're all replacing balls with board games.We have some food newsFlorida man Newsand we end with a terrible game of Madlibs that makes no sense...Come on in, and get yourself Effin' Cultured

The system failed her. She told the truth anyway.Part II picks up with Emma making the drive back to his house — not for reconciliation, but for answers she was never going to get. She arrived to find a man who looked like a total mess, said nothing about her new car, and within minutes set a large knife in front of her on the bed.What followed was assault. Coercion under the guise of reconnection, with a loaded gun and that knife within arm's reach. Completely restrained, face down, staring at red velvet curtains while Stranger Things played in the background. A phone appeared. A photo she never consented to. A chuckle.She got out the only way she knew how. Fawning. Years of trauma had taught her body exactly what to do to avoid things turning violent. When she got home and finally looked at her phone, she found two photos and a four-second video of herself — taken without her knowledge or consent. Both illegal. A week later, a lawyer by her side, she filed a police report.The DA picked up the case the same day. A felony warrant was issued the next morning. He spent two weeks on the run — attending the concert they were supposed to go to together, posting on social media, and quietly soliciting Mad Libs-style fake witness statements from strangers. Emma sent everything to the DA. They did nothing.The grand jury disposed the case. No forensic phone examination. No follow-up interview. The victim advocate stopped returning her calls. The restraining order was denied. He still has the material. He always will. Her healing journey can be interrupted any day by whatever he decides to do with it next.She is learning to live with that. And she came on this podcast anyway — because people like him thrive on secrecy, and she promised herself she would never be quiet.

Jenny Hagel joins Ophira Eisenberg to talk about parenting through big feelings, awkward questions, creative careers, and the strange emotional math of raising boys while working in comedy. Jenny shares how her now-12-year-old son transformed from a tiny Brooklyn tornado she once carried out of donut shops “like a sack of potatoes” into a “fun, chill roommate,” and explains how one preschool meltdown led to the line “my mad is too big for my body,” which completely changed the way she thought about tantrums and emotional regulation. The conversation moves from Mad Libs ruined by the phrase “diarrhea juice” to surprisingly thoughtful discussions about kids' emotional language, including Jenny's son describing a crush as “a string” connecting two hearts. Ophira and Jenny also compare notes on parenting boys with huge emotions, the pressure put on working mothers, and the exhausting flood of parenting advice from strangers who assume every family has the same structure and flexibility. Jenny talks about building her live comedy show Advice Nobody Asked For during the writers strike, where audience members anonymously submit questions into buckets labeled “family,” “love,” and “job,” before a real therapist comes onstage to grade the advice — including the time Jenny recommended secretly vaccinating a relative's baby while babysitting. Along the way they talk about single parenting, Late Night with Seth Meyers, queer parenting, American work culture, and therapy as an emotional toolbox.

Most employee advocacy programs fail because they turn employees into parrots, repeating the same product message over and over until no one wants to share anything. In this episode of Content Amplified, Matt Mullan, Director of Social Media at NinjaOne, explains how to fix that by positioning employees as thought leaders instead of megaphones. Matt walks through giving people industry content they actually want to share, using Mad Libs-style suggested copy with guardrails so posts sound human, and motivating adoption by shouting out every organic win across Slack rather than relying on prizes. He gets specific on measurement: why earned media value and potential impressions are made-up numbers, why UTM link tracking is the only honest metric, and why he holds his programs to a 50% monthly usage bar. He also makes the case that LinkedIn comments now out-earn reshares, and shares how his team built an in-house "social ambassador" tiger team to keep conversations going. If you run social and your advocacy program has stalled, this conversation gives you the playbook.About MattMatt Mullan is the Director of Social Media at NinjaOne, an IT operations platform. He has spent roughly 13 years in social media, going back to experimenting with Google Plus and MySpace, and has worked across industries from an international toy manufacturer to HR and payroll software, cybersecurity, and IT management companies. Matt is focused on B2B social media as his day-to-day craft, and he believes the real audience for an advocacy program is not your followers, it is your own employees.Show Notes- Connect with Matt on LinkedIn: https://www.linkedin.com/in/mullanmatthew/Text us what you think about this episode!

Threevisiting on the Tues: Lauren, Paul and Scott talk about Nermal, a baseball game, and do some MadLibs. Send Threetures and emails to threedomusa@gmail.com.Leave us a voicemail asking us a question at hagclaims8.comFollow us on Instagram @ThreedomUSA.Unlock every episode of THREEDOM and THREEMIUM, ad-free, on cbbworld.comGrab some new Threedom merch at cbbworld.com/shop

For the second week in a row, we find ourselves wading back into the cinematic swamp of “animals who have absolutely had it with humans.” This time, the creature feature du jour is THRASH (2026), a Netflix exclusive that once lounged around Sony's living room before being scooped up by the streaming giant. It splashed onto VOD on April 10th, 2026, and to the shock of absolutely no one, it feels a bit like déjà vu of CRAWL (2019)—only someone swapped the alligator for sharks, as if playing a very chaotic round of ecological Mad Libs.According to IMDb, the plot goes something like: “When a Category 5 hurricane decimates a coastal town, the storm surge brings devastation, chaos and something far more frightening: hungry sharks.” In other words, Mother Nature looked at the disaster movie genre and said, “You know what this needs? Teeth.” The film comes courtesy of Norwegian filmmaker Tommy Wirkola—yes, the mastermind behind DEAD SNOW and VIOLENT NIGHT—who clearly woke up one morning and chose aquatic violence.The cast boasts Phoebe Dynevor, Whitney Peak, Djimon Hounsou, Matt Nable, and more brave souls willing to pretend they're being hunted by CGI fins. Reviews have ranged from “eh” to “please no,” but Netflix has been promoting it with the enthusiasm of a proud parent whose child just ate an entire crayon. Luckily, your cohosts are joined by actor Dan Lench (CIRCLE, MAXXXINE, THE LURKING MAN) to dive into this toothy tempest of nature‑gone‑wild horror.

Mason eagerly wants to give a viewer his address, Daniel quizzes us on homophones, and Danny runs a particularly special round of MadLibs.

Jon and Jim share who they would like to see the Lions play Week 1, on Sunday Night Football, on Monday Night Football, on Thanksgiving, and Week 18

6:00 HOUR: Lions Dream Schedule Mad-Libs, Power Surge or Power Trip?

MOOBARKFLUFF! Click here to send us a comment or message about the show!Welcome to BFFT! The Injured Nerves Network brings you another exciting and time wasting episode of BFFT!  Taebyn is in rare form this episode as he gives us a story, explains some 3d/4D things, and interjects everywhere.  We go over upcoming events. Read an AI generated MadLibs. Cheetaro gives us their 76th movie review! BFFT Labs tries out another new concept called: No Time For the Movie. We have all the usual stuff too. So join us, won't you, for another T-Riffic (that is Taebyn-Riffic) episode of BFFT! Moobarkfluff everyfur!Click here to help RayShugga on the Head to Heart GoFundMeMERCH: https://bfft.dashery.com/Email: bearlyfurcasting@gmail.com  Staff Artist: https://www.instagram.com/bunncubus Musical submissions: https://forms.gle/FfvoNUph7R9GxFDp6Con Roommate story submissions: https://forms.gle/bb36jP194RJf2PMf7This podcast contains adult language and adult topics. It is rated M for Mature. Listener discretion is advised.Support the showThanks to all our listeners and to our staff: Bearly Normal, Rayne Raccoon, Taebyn, Cheetaro, TickTock, and Ziggy the Meme Weasel.You can send us a message on Telegram at BFFT Chat, or via email at: bearlyfurcasting@gmail.com 

The Richley boys are back and struggling with their words again. John breaks down an important moment in beverage history while Joe reminisces about a fictional junior high dance. All of this, Madlibs and more! Feast your ears!

Michael Arden joins the show to discuss the monumental task of bringing The Lost Boys to Broadway and the technical alchemy required to turn a cult classic film into a soaring musical experience. He opens up about his "mad lib" approach to stagecraft, explaining how he utilizes traditional theatrical tools in unexpected ways—like tilting the entire orientation of a set to keep an audience off-balance or ensuring the set moves entirely on its own to make the space feel "alive". Michael also reflects on the high-stakes pressure of bypassing an out-of-town tryout, the "fearless skydiving" energy of his cast during a grueling preview process, and his years-long quest to convince his favorite band, The Rescues, to join him in the theater. The conversation also dives into Michael's deep-seated love for the "visual feast" of theater, tracing back to his childhood days rigging special effects in his garage. He shares how his collaboration with the design team at At Rise Creative allows for a "crash and burn" mentality that eventually leads to the most innovative solutions, from the irising neon boxes of Maybe Happy Ending to the complex verticality of the Palace Theater. Looking ahead, Michael previews his upcoming work on Happy Feet, discussing the challenge of mashing up music and integrating massive puppetry to bring the Antarctic to the stage. Michael Arden is a distinguished, two-time Tony Award winning director, recently honored for Best Direction of a Musical for Maybe Happy Ending. In 2023, he won the Tony Award for the acclaimed revival of Parade, following previous nominations for Once On This Island and Spring Awakening. He is the co-founder of At Rise Creative and has directed a wide range of works, including the 2024 Met Gala and Ben Platt's concert residencies. Beyond his directing credits, Michael is an accomplished performer who has appeared on Broadway in Big River and King Lear, as well as in television and film projects like The Marvelous Mrs. Maisel and Source Code. Connect with Michael @michaelarden Connect with The Theatre Podcast: Support the podcast on Patreon and watch video versions of the episodes: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Patreon.com/TheTheatrePodcast⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Instagram: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@theatre_podcast⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Facebook.com/OfficialTheatrePodcast⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠TheTheatrePodcast.com⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Alan's personal Instagram: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@alanseales⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Email me at feedback@thetheatrepodcast.com. I want to know what you think. Learn more about your ad choices. Visit megaphone.fm/adchoices

This week we're lollygagging around a rapid fire covering a range of topics, MLB managers getting the axe, ranking MLB bottom teams, Lollygagging Mad Libs, space baseball park factors, and more! Do you have any questions or comments about Lollygagging Sports? Reach out to us on Bluesky: Bo Reed (@boreed009.bsky.social), Samantha Bunten (@samanthabunten.bsky.social‬), Lollygagging Sports (@lollygaggingpod.bsky.social). And on Twitter/X: Samantha Bunten (@samanthabunten), Matthew Irby (@IrbyStatMan), Lollygagging Sports (@LollygaggingPod).

Email is saturated, and your best content is stuck behind a screen. In this episode of Content Amplified, Kris Rudeegraap, Co-CEO of Sendoso, walks through how to take the digital content already performing well for your team and put it in front of prospects as a physical mailer they actually open. Kris explains how to shortlist your highest-performing assets using sales enablement platforms, web analytics, and paid ad data, then how to repurpose that content into formats worth mailing: Mad Libs books, scratch-off insight cards, workbooks, video mailers, trading cards, even quarterly printed magazines. He lays out where physical mailers fit across the buyer's journey, from top-of-funnel SDR plays to stage-three air cover in competitive deals to post-sale onboarding kits. He also breaks down how AI is changing the space through personalization, print-on-demand, smart delivery to home addresses, and signal-based automated workflows, plus a simple get-started plan: pick your best-performing asset, print 50, pick 25 in-pipeline deals and 25 target accounts, and test. If you're looking for a way to break through the digital noise without burning your budget, this episode is worth your time.About KrisKris Rudeegraap is the Co-CEO of Sendoso, the direct mail and gifting automation platform he founded about a decade ago after a career in sales at TalkDesk. A lifelong entrepreneur, Kris started Sendoso after feeling the pain firsthand: packing boxes at night, running to FedEx, and watching tracking links, all while email was losing its edge. He believes the tangible psychology of unboxing, the pattern disrupt of a physical package, and the personalization AI now makes possible are what give physical mail its edge in a saturated digital world.Show Notes- Connect with Kris on LinkedIn: https://www.linkedin.com/in/rudeegraap/- Sendoso: https://sendoso.comText us what you think about this episode!

When the tech for our old-school PI game goes bust, we attempt to keep the noir vibes alive through a high-stakes round of Mad Libs. Of course, the investigation is permanently closed when a tiny surprise guest storms the studio and officially derails the broadcast. Enjoy! -          Please send your emails to heresjohnnypodcast@gmail.com -          To join our community, feel free to join our discord! (https://discord.gg/htr6kRB) -          Check out our past reviews and lists on our show website at https://www.heresjohnnypodcast.com/ -          If you are able, you can support us on Patreon (patreon.com/heresjohnnypodcast) You can find Rachel on the Zombie Grrlz Horror Podcast, where they review horror films from the feminist perspective. For Stream Queens, we talk about horror movies you can stream on the internet. The More Deadly cast is dedicated to reviewing and signal-boosting horror movies directed by women-identified artists. The Cast of Ka tackles Stephen King's definitive work, The Dark Tower, one book at a time. Also, check out Rachel's Star Wars content over at Outpost Unknown (https://www.youtube.com/channel/UC8oumJZs4V_bTeL5cm7MAFg)!

Turning 50 comes with a lot of surprises, but reading a custom Mad Libs advertisement about a hairy luxury tomato cruise might be the most bizarre one yet. Before jumping into childhood lunchbox trauma, Daniel Murray and Jay Schwedelson share some surprisingly effective email marketing tactics that go against conventional wisdom. You will find out why putting newsletter edition numbers back into your subject lines is suddenly working and how three simple words can drastically improve your open rates.‎ Best Moments:(01:56) Daniel reads a hilarious custom Mad Libs advertisement created for Jay's 50th birthday(03:44) Why a documentary about a broken cruise ship is highly recommended viewing(04:44) Jay explains why adding the edition number back into newsletter subject lines is lifting open rates(06:04) How adding a simple personal question to your emails improves reply rates and deliverability(07:45) Using the words and, but, or plus in your pre-header text to increase open rates by 10 percent(11:02) Daniel reveals his childhood trauma of eating banana-flavored sandwiches before lunch

Hosts: TJ, Brett, Krissy, & Jo This week on the show: Segment One (0:00:00): (0:04:02) Brett's looking forward to mowing, gives us an update on his jet model, and more GOAT Guns. (0:09:40) Krissy helps the daughter dog sit and has a MAJOR family announcement. (0:15:44) TJ recaps the glory and wonder of his endoscopy and colonoscopy procedures. Prepping is FUN! Segment Two (1:06:19): (1:09:12) FGS is kind of a big deal in the news this week as the gang discusses Dayton Webber, the quadruple amputee cornholer who shot his side seat passenger. (1:32:18) HOT TAKES gives us a litany of loss on this week's GRIM REAPER ROUND UP (1:45:50) It's new bit time as Krissy introduces us to her favorite conspiracy theories. This week: The sinking of the Titanic was a hit job! Segment Three (2:21:27): (2:24:00): KRISSY'S KRAZY KORNER comes on strong with more Mad Libs! (2:50:50) PICKS O' THE WEEK Open up and say “Ah!”, Mr. Damon! It's THE QUAD M SHOW!

Daniel asks us riddles in the form of a round of “What am I?”, Mason struggles to come up with a good birthday idea for a viewer, and Danny hosts an incredible round of MadLibs.

Tonight is going to be another evening if mixed tales from the internet, including the latest on a rash of bigfoot sightings in Ohio. An old Moon Landing deathbed confession video made its way back into my feed the other morning and I think it should make good fodder for conversation, especially if anyone in the audience has been present for a deathbed confession. But do not miss the second half when comedian Mike Baldwin (MikeIsFunny.com) swings by for a visit, to laugh at some reels we have been collecting together, as well as play a little MAD LIBS with the audience. Unleash Your Brain w/ Keto Brainz Nootropic 15% OFF w/ code MARCH: https://tinyurl.com/2cess6y7 Every purchase enters you into a MASSIVE Product RAFFLE! E-Mail me for FREE SAMPLES of KB or SALTE Hydration Packets! Sponsor Monthly for VIP Perks: https://www.quitefrankly.tv/sponsor One-Time Tip: http://www.paypal.me/QuiteFranklyLive Quite Frankly Amazon Storefront: https://amazon.com/shop/quitefranklyofficial Official Coffee & Mugs: https://www.coffeerevolution.shop/category/quite-frankly Official QF MERCH: https://tinyurl.com/f3kbkr4s Gold & Silver: https://quitefrankly.gold Send Holiday cards, Letters, and other small gifts, to the Quite Frankly P.O. Box! Quite Frankly 222 Purchase Street, #105 Rye, NY, 10580 Tip in Crypto: BTC: bc1q97w5aazjf7pjjl50n42kdmj9pqyn5zndwh3lng XRP: rnES2vQV6d2jLpavzf7y97XD4AfK1MjePu Quite Frankly Socials: Twitter/X: @QuiteFranklyTV Instagram: @QuiteFranklyOfficial Discord Chat: https://discord.gg/xPu7YEXXRY Official Forum: https://tinyurl.com/k89p88s8 Telegram: https://t.me/quitefranklytv Streaming Live On: QuiteFrankly.tv (Powered by Foxhole) Youtube: https://tinyurl.com/yc2cn395 Rumble: https://tinyurl.com/yeytwwyz Twitch: https://www.twitch.tv/quitefranklylive Audio On Demand: Spotify: https://tinyurl.com/yk4yfdsa iTunes: http://apple.co/2dMURMq

Initial shock has given way to grave concerns as the US and Israel's joint attack on Iran continue, stepping both countries into a war without a clear goal, end date or exit strategy. To help explain where congressional powers lie and the limits of executive authority, Mary and Andrew call upon Tess Bridgeman, international law expert and Co-Editor-in-Chief of "Just Security”. Tess stakes out the scope of the 1973 War Powers Resolution, and why Congress is meant to be the body that decides if, and when the US commits to armed conflict with another nation state. Then, Mary and Andrew turn focus to a few immigration updates, as more judges chastise the government for continually violating court orders, and a Columbia student is detained by ICE under false pretenses. Last up, the co-hosts turn to the decision in the case involving whether a journalist's devices seized while executing a search warrant could be searched. Plus: the Trump administration's decision to stand down on defending Trump's sanctions against law firms— only to do a seeming about face the next day. Further reading: Here is the piece Tess Bridgeman co-wrote on "Just Security": Top Questions the Trump Administration Needs to Answer on War with Iran Here is the opinion Andrew and Mary were referring to out of the Southern District of West Virginia You can pre-order Andrew's book, out May 19th, here: Liar's Kingdom: How to Stop Trump's Deceit and Save America Sign up for MS NOW Premium on Apple Podcasts to listen to this show and other MS podcasts without ads. You'll also get exclusive bonus content from this and other shows. Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Hard conversations in relationships, attachment styles, anxious vs avoidant dynamics, and emotional disconnection are at the center of this week's Ask A Matchmaker. Matchmaker Maria sits down with therapist and author Colette Fehr to explain why couples fight about small things like Duolingo, texting back, or Valentine's Day flowers when the real issue is feeling unheard or unimportant. They break down how to stop people pleasing, how to say "that hurt me" clearly, and why serious conversations should never happen over text. Colette shares tools from her book The Cost of Quiet, including her emotional Mad Libs method for speaking up without pushing your partner away. They also tackle anxious and avoidant attachment patterns and whether separate bedrooms, like Keke Palmer suggested, can actually work in a healthy relationship.   ♥️JOIN MARIA'S COMMUNITY + SUBMIT A QUESTION ❓ Ready to date with intention?

This week we're breaking down Did I Stutter? When Stanley snaps at Michael, Michael tries to stand up for himself as his manager. Meanwhile Dwight buys Andy's car, and Pam has to forgo contact lenses and wear her backup glasses to work. Angela rocks her original Did I Stutter? shooting draft, Jenna does a deep dive on Mad Libs and the ladies reveal The Office writing staff's mantra: “small, real, relatable”. This is a wonderful episode that definitely doesn't sound like noise coming out of an ugly scientist. Office Ladies Website - Submit a fan question: https://officeladies.com/submitaquestion  Follow Us on Instagram: OfficeLadiesPod Follow Us on YouTube Follow Us on TikTok To learn more about listener data and our privacy practices visit: https://www.audacyinc.com/privacy-policy Learn more about your ad choices. Visit https://podcastchoices.com/adchoices

Macadamia nuts. Labor shortages. Volcanoes. All that might sound like econ Mad Libs, but they're all connected to the Federal Reserve Bank of San Francisco's entry into the Beige Book this month: labor shortages are hurting macadamia nut harvests in Hawaii. On today's show, we take a vacation and talk to someone on the Big Island who runs a macadamia nut farm. He calls them “mac nuts.” Related episodes: Why beef prices are so high For sponsor-free episodes of The Indicator from Planet Money, subscribe to Planet Money+ via Apple Podcasts or at plus.npr.org. Fact-checking by Sierra Juarez. Music by Drop Electric. Find us: TikTok, Instagram, Facebook, Newsletter.  Learn more about sponsor message choices: podcastchoices.com/adchoicesNPR Privacy Policy

A jam-packed review tonight as I have some things to say about Nick Shirley's Part II to the expose` he is compiling on the true state of State of Minnesota. It all ties in with a world that is enamored with new ways of making money easily and dishonestly, while those who want to work toward establishing a personal legacy for themselves and their family are becoming fatigued by the load. Although, like with most things, there are silver linings, bright outlooks, and plenty of real people who are not willing to let defeat take them without a fight. In the second half, Mike Baldwin will stop by for his first appearance of the new year to comment on tonight's topics as well as have some fun of our own. Unleash Your Brain w/ Keto Brainz Nootropic 15% OFF w/ code JANUARY: https://tinyurl.com/2cess6y7 E-Mail to Request for FREE SAMPLES! Sponsor Monthly for VIP Perks: https://www.quitefrankly.tv/sponsor One-Time Tip: http://www.paypal.me/QuiteFranklyLive Quite Frankly Amazon Storefront: https://amazon.com/shop/quitefranklyofficial Official Coffee & Mugs: https://www.coffeerevolution.shop/category/quite-frankly Official QF MERCH: https://tinyurl.com/f3kbkr4s Gold & Silver: https://quitefrankly.gold Send Holiday cards, Letters, and other small gifts, to the Quite Frankly P.O. Box! Quite Frankly 222 Purchase Street, #105 Rye, NY, 10580 Tip in Crypto: BTC: bc1q97w5aazjf7pjjl50n42kdmj9pqyn5zndwh3lng XRP: rnES2vQV6d2jLpavzf7y97XD4AfK1MjePu Quite Frankly Socials: Twitter/X: @QuiteFranklyTV Instagram: @QuiteFranklyOfficial Discord Chat: https://discord.gg/xPu7YEXXRY Official Forum: https://tinyurl.com/k89p88s8 Telegram: https://t.me/quitefranklytv Streaming Live On: QuiteFrankly.tv (Powered by Foxhole) Youtube: https://tinyurl.com/yc2cn395 Rumble: https://tinyurl.com/yeytwwyz Kick: https://kick.com/quitefranklytv Twitch: https://www.twitch.tv/quitefranklylive Audio On Demand: Spotify: https://spoti.fi/301gcES iTunes: http://apple.co/2dMURMq SoundCloud: https://tinyurl.com/yc44m474