Spiral: Designing an AI Ghostwriter With Taste

Good writing has always been downstream of good thinking. The average language model can help you write faster—but can it help you think better? Danny Aziz wrestled with this question while building the new version of Spiral, an AI writing partner informed by our editorial taste at Every that launched yesterday. The result is a product—and a philosophy—built by the ultimate craftsman who believes you can lean into AI without blunting your edge with slop. We had Danny on AI & I to talk about using AI without losing your craft. We get into the hidden alpha in AI tools that slow you down, how to code with AI without losing your craft, and everything Danny learned about cajoling AI to write well. If you found this episode interesting, please like, subscribe, comment, and share! Want even more? Sign up for Every to unlock our ultimate guide to prompting ChatGPT here: https://every.ck.page/ultimate-guide-to-prompting-chatgpt. It’s usually only for paying subscribers, but you can get it here for free. To hear more from Dan Shipper: Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Ready to build a site that looks hand-coded—without hiring a developer? Launch your site for free at Framer.com, and use code DAN to get your first month of Pro on the house. Timestamps: 00:00:00 – Start 00:01:00 – Introduction 00:05:26 – How Danny used Spiral to prepare for this podcast 00:08:29 – Why slowing down makes AI writing better 00:13:42 – The agents working under the hood for Spiral 00:14:46 – How Spiral helps you explore the canvas of possibilities 00:24:41 – Why Danny pivoted away from the old version of Spiral 00:31:51 – How to use AI without losing your craft 00:34:55 – Danny’s workflow for building Spiral as a solo engineer 00:40:39 – Code with AI while staying in control 00:45:26 – What Danny learned about getting AI to write well 00:47:52 – How Danny used DSPy to give AI taste 00:56:16 – Dan v. AI Dan: Can the machine match the man? Links to resources mentioned in the episode: Danny Aziz: Danny Aziz (@DannyAziz97) / X Give Spiral a go: Spiral The article Every published about DSPy: I’ve Stopped Writing Prompts—DSPy Does It Better

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Speaker 00

  Most AI writing is slot. Unless you're spending hours babysitting prompts, you're getting generic output. And when you do put in that effort, you're not writing, you're holding the AI's hand, explaining what you want, re prompting, guiding it towards something usable and that sounds like you. I'm Danny, the general manager of Spiral. I spent seven months rebuilding it from the ground up to solve this problem. Spiral is now an AI writing partner with Taste. In this conversation with AI and I host Dan Shipper, you'll hear how I use AI tools like Droid and Claude Code to build a really beautiful and intentional AI writing experience. How we taught models to judge their own writing and the philosophy behind making an AI writing partner instead of a slot machine. By the way, this intro was co-written by Spiral. Let's get into it.

• 1:00Dan Shipper?

  Seven, eight months, we went through a ton of iterations and then you were like, I want to make this the most beautiful fucking app I've ever made. Like, show us the app right now. Show us what it looks like.

• 1:09Speaker 00

  Okay, so here we are. This is the new Spiral.

• 1:14Speaker 00

  And there's like so many tiny moments that we like thought about on this. You know, James and I and Lucas, we all really just like spent a lot of time thinking about like, what is the experience that you want to have when you come here?

• 1:28Speaker 00

  And, you know, it's very subtle. This is one thing that I just like, I love it every single time. But we have this like slight papery feeling effect. It's noise, but in the background, it feels like it's paper. Like, you know, we intentionally chose this like typeface.

• 1:42Dan Shipper?

  Wait, I want to pause you here. Like, just looking at this, right? There's so much here. There's obviously like, what are we writing today, Danny? There's, and for people who are listening, there's like a, there's a, there's a, there's a box where you, you know, you type in the post you want to write about. And then there's like a plus button where you can attach more context. There's a microphone button where you can talk to it. There's a styles button where you can add styles. But then there's a whole sidebar of different workspaces. And within each workspace, you have different products. There are these little icons. It's like, there's one for Cora. So if you want to write about Cora, another product, like you can go in there and, and that's all beautifully designed. And then there's like a history. And what, what I want to emphasize to your point is you built all of this.

• 2:27Dan Shipper?

  By yourself. That is crazy. That like, that would have been totally impossible a year ago. Or two years ago. And, and so I think you're, I think you're making a really important point about what you can achieve with these tools if you use them well and you want to make something great.

• 2:47Speaker 00

  Yeah, I think it really, you know, it allows you to go from like idea to something really quickly. And I think you can go from something to like, something beautiful also really quickly. And, and you know, we, I worked with some really talented people like Lucas, James, you know, we, we all jumped in here. And I think the really cool thing was that it allowed, you know, both Lucas and James, who are not engineers, to like mess around and Claude and be like, oh, can we figure this out? Like to your point of, you know, being able to speak to it, we have like a monologue integration and we have this like dithering animation. And I think Lucas made the first one in like a code sandbox using Claude. And then we like iterated from there and then messed around in Figma. So like,

• 3:32Speaker 00

  it allows also a bunch of people to jump in and, you know, who aren't necessarily engineers to like, help play around and like take it to that final place.

• 3:43Dan Shipper?

  I, so that makes a lot of sense, you know, for people who, who are not as familiar with the every ecosystem. Monologue is another product that we build internally. And so now Spiral connects to Monologue, which is super cool. And that would actually be kind of fun to talk about. But why don't you show us how Spiral works, just so we get a sense for, okay, once you're like opening the Pandora's box of it, like what is possible? And then what I actually was, what's really interesting to me right now is I want to learn more about your workflow. Because I think we do a ton of Claude code content on every, and you are actually a droid boy. And, and I feel like you have some, some ways of working that are maybe a little bit different

• 4:26Dan Shipper?

  from some of the stuff that we've done previously. And this is really making me. You know, one of the things I feel about you is just from looking at your hair and how how beautiful your hair is. You and also that leather jacket you're wearing. You really have this, and you've said this before about yourself, you have this like measure twice, cut, cut once mentality where you're just like, you're a craftsman. And I think that that has come through in this product. It has come through in how you think about building a tool for writers. And, and I, and I think that that to your, to a point you made earlier, it,

• 5:09Dan Shipper?

  it's sort of at odds with what people think you can build with AI. It's like, oh, you're just gonna make slop. And actually, you can build, build beautiful things with AI. And I think you're a really good example of that. So let's start with using Spiral.

• 5:22Speaker 00

  Thank you for those lovely words, by the way.

• 5:26Speaker 00

  So I actually prepared beforehand, talking about this interview with Spiral. And I thought that could be kind of meta to go through.

• 5:33Dan Shipper?

  That's really cool.

• 5:34Speaker 00

  How it worked. So first of all, I did it inside the Spiral workspace. And the whole idea of workspaces is kind of like projects in ChatGPT or Claude, which is like, it just has documents and stuff and context beforehand. And so it knows what you're talking about. And so I literally said like, hey, I'm about to jump on a podcast with Dan to talk about you. Help me prepare some notes. And what it actually did, well, that was a little janky, I gotta fix that. But one of the things that it did was that it asked itself, what do I know about myself? And it kind of like thought about it. And it sort of spat it all out and was like, hey, here are a bunch of things that you could talk to about Dan, like most AI writing is slop, Spiral has taste. We could talk about what makes Spiral different. It chats first and it interviews. It explores three different angles, these are all things to come.

• 6:17Speaker 00

  We can also talk about the evolution story. So Spiral like suggested a bunch of things to me. And then I could, you know, the first thing that Spiral does is it asks questions. It always wants to know more concrete details from you. And so it asks, would you like me to expand or help you through, think through specific stories or examples that you could share? And so I said, actually, one of the other things I want to talk about is like the sheer number of iterations that we went through, testing and experimenting. And then Spiral again, look through what it knew of the story of Spiral and kind of came through, here are these different like arcs, you know, the realization, the old one isn't working, the pivot. And then it started asking me questions for each one, like, what was the first thing that I tried differently? When did the chat first insight emerge? How many iterations did I go through?

• 7:02Speaker 00

  What did you learn about what makes writing good that surprised you? And so like, it's gone through its understanding of itself, but it's asking me questions all along the way. It's like really figure out concretely, what the, what the hell is it that I'm actually trying to say? And this is like super useful, because I think a lot of the times when I've gone to old Spiral and other AI tools, like ask for something, it may ask questions, but usually you have to prompt it to ask you questions. And the questions don't really help me really think about what I'm saying that well. We had a, we had an early user who said something about Spiral. He said that Spiral helped him go downstream from the original thought that he shared with Spiral, as opposed to it just being a repurposing of the original thought that he shared.

• 7:45Speaker 00

  And I think that like put it really like well and succinctly of like Spiral will help you take that initial like jumble of thoughts that you had and go a little bit further with it. From these questions, which I think is like super useful in figuring out what it is that you're trying to say.

• 8:03Speaker 00

  And I guess it's also like seeing it from different perspectives also helps really like understand the shape of the thing that you're trying to talk about.

• 8:10Speaker 00

  Yeah, so I monologued into it a bunch of stuff and then sort of like helped me like think through the different things that I wanted to talk about right now. So that's the interviewing part of Spiral and like sort of figuring things out.

• 8:26Dan Shipper?

  And just, I just wanna, I just wanna like pause you there. I think the interview thing is an interesting thing and it's, it's one of the things that we came to very early on in this process. Because we were thinking about, oh yeah, how do you build a, how do you build a writer with taste? And

• 8:42Dan Shipper?

  One of the metaphors that we use to think about this is how would a person do this? And I think that's a really good and important metaphor for building AI products is if you're building an agent, first you have to think about like, how does an actual person do the task that the agent is gonna do? And so, you know, I was thinking about for me, in my, in my writing,

• 9:05Dan Shipper?

  how, how do I ghostwrite for people well? And, and in order to do that well, I would need a,

• 9:13Dan Shipper?

  I, I, I need to get a sense of who that person is and like ask them questions about it. And there's this like, you know, mutual discovery process. And you took that and, and like built this basically like interview mode, which I think is, is one of the things that

• 9:30Dan Shipper?

  makes this really different is it's not, its job is not to just spit out the answer right away, because that's how you get slop. It does spit out an answer if it knows who you are and what you want and all that kind of stuff. Because if you built a relationship with a ghostwriter, for example, and you're doing something like what you've done before, that is actually can be a pretty quick process. But otherwise, a good ghostwriter, their job is to make you feel seen, like really get underneath the thing that you're trying to do. And, and that's how you make, that's how you ghostwrite something that feels like it came from the person and isn't just like some generic bullshit.

• 10:05Speaker 00

  Yeah, yeah. And I think LLMs are, and this actually goes deeper into the story of how else this program works. But LLMs are great at doing that, just sort of like helping you see things from an infinite number of like perspectives. And I think one of the things that we spent a lot of time with the prompt for the interviewer inside Spiral is like, yes, anding you. Sort of, you know, coming from like improv is it always kind of has like provide value in the questions. Like some questions are kind of annoying and it's like, you know, if it's not providing value and we try our best, it's like, yes, and.

• 10:40Speaker 00

  And like it, it is giving me a lot of questions like how, like, you know, how do you encode asking good questions to the prompts? Which is kind of what you just asked. And so like it's thinking through all of the things and.

• 10:51Speaker 00

  To your point of like slop, one of the things that we were very intentional on of like, we're going to use a reasoning model and we're actually going to show the user all of the reasoning. And you can see it all because, you know, we we're calling it a writing partner. And I think that word partner is really important. And I think it's kind of one of those like principles that we've anchored everything around. And with like any good collaborator or partner that you're working with, whether it's writing or, you know, engineering or design, um, understanding the perspective that they're coming from and how they're thinking about the thing, um, helps you understand like, oh, this is where they're thinking about it. This is where we're, um, here's where there's a delta between how I'm thinking about it, how they're thinking about it, or like, oh, they've got it completely wrong.

• 11:34Speaker 00

  They they've understood something incorrectly or differently from how I have. And it's really useful to be able to like, look at the thinking. Um, I, you know, when you start a conversation with Spiral, the thinking is open by default. You don't have to click it open, um, as opposed to, you know, other AI apps. They do show you the thinking, but you have to click it open. I think that's a very small, tiny intentional thing of like, we want you to read it, like, actually understand what it's doing, because if it's doing something you don't want it to do, you took people to see that and you could just tell it. Um, yeah, I think that's super important in building something that everybody else is trying to make content like his, you know, even the old version of Spiral is like an infinite number of, you know, it will spit out an infinite number of things, a click of a button.

• 12:16Speaker 00

  And I think we've gone completely the opposite way, um, where we've kind of zagged and been like, let's go slowly, like, we're going to use a thinking model and it's going to think for a sec for for quite a few seconds and slow down, be a bit more intentional, answer the questions. And sometimes it's annoying, sometimes the questions are annoying, um, but sometimes and like more and more and more, the questions are really helpful of being like, oh, yes, that's exactly what I meant. Or it'll ask me, you know, it'll ask me a question and I'd be like, you're way off, dude. And here is actually what I mean, but that helps me articulate what I actually mean, because you're asking me this question that's like way over left field.

• 12:48Dan Shipper?

  Totally. Okay, so so I think we've gone through the interview stuff. Now show us, once it's gotten a sense of who you are and what you're trying to do, um, how does it, you know, we really focus this around short form content. So like tweets, LinkedIn posts, emails, um, uh, you know, other types of like short form marketing type stuff. How does it? How do you actually make something with this? Once it's interviewed you?

• 13:12Speaker 00

  So usually when you, when you start with it, you'll, most people will say, help me write a LinkedIn tweet, X post, you know, email, blah, blah, blah. So usually by the time you've answered quite a few of its questions, it will just be like, great, I'm ready. Let's start writing. But in this case, I'm just going to say, hey, help me write a banger tweet about this, even though I started with saying I'm doing a podcast.

• 13:33Speaker 00

  And the first thing that it's going to do is reason over all the things that you asked it, that you've like replied to it with. And then one of the things that we learned sort of in the journey of building this is this needed to be a multi-agent system. Like having one big model do both the interviewing and the writing just really didn't work. As we tried to layer on more functionality, it just started to break because of context rot. You know, all of these labs are talking about one million context windows, one million token context windows. And it's just like, that's, yes, it can do that, but how well can it actually pay attention to all those tokens? Just clearly isn't there yet. So we have a handoff system where the interviewer gives it to the writer.

• 14:18Speaker 00

  But actually they share the entire same context window. So it's not a summary of the previous thing. It's not like a tool call where the interviewer is summarizing the conversation to the writer. We're literally taking the previous context window and just write into a new system prompt. Oh, sorry, write into a new system context window, just being like, hey, here's your previous chat. And we do some prompting to make the writer like, understand what's happening, like, hey, you're coming from the interviewer and that kind of stuff.

• 14:46Speaker 00

  And so like we just saw here, it did a bunch of thinking. And the first thing that it did is it spat out three options. And we have this UI where you can kind of explore all three right in one go. And it's thought a lot about what we've said. And the reason that we did this is I think when we first started down this process of creating a new product. I think you were really, really interested in the idea of exploring the sort of infinite canvas of possibilities that L L Ms could give. And this was like something you were really, really excited about and like traversing up the tree and then like branching from the tree.

• 15:27Speaker 00

  Yeah, like March 2025 was a lot of trees and thinking about trees.

• 15:33Speaker 00

  I actually vividly remember.

• 15:36Speaker 00

  I think it was like, it was like a Thursday or a Friday and I was in our old office in Manhattan and you just like sent me a fucking tree on Discord. Like it was like here in Brooklyn, it was probably like in Fort Greene or something. You just sent me a picture of a tree. I was like, this fucking guy. Yeah, we were really, really interested about this idea. I mean, it's like, it's true, right? Because they can just produce an infinite number of tokens and you can kind of explore all these different ways of saying the same thing. I think what we realized is, one, from the same context window, every single iteration that you ask it for, it just degrades in, in quality. And we even see that still today with Spiral. Like, we're still not there yet with like its writing ability.

• 16:20Speaker 00

  But there is still something really interesting there about this, seeing things from different angles and sort of pruning and being like, you know, recently I've been saying like chiseling marble. You know, you, you start with this like blank slate. Maybe it's not the best analogy because you have these, whatever. But you kind of like pick and choose what works and what doesn't work. So it starts off in this UI, you have three options.

• 16:42Speaker 00

  You know, and very quickly, you know, it gives you sort of titles of like, what is the, the general gist of this version? So this is like an honest realization. This one's more about the failed experiment. And this one is like questions over drafts. And, you know, I think we spent a lot of time thinking about how do you actually interact with these three options? Because chat is one thing, you know, I can come in here and I can like, you know, type. But also, we kind of want the AI and you to be able to interact with all three of these things. So right now Spiral can read all three of these things. It has context of what's open. So like if I close one, it knows that there's only two open right now. If I like, you know, close all of them, it'll understand that. But also if I make edits, it understands about the manual edits that I've made.

• 17:28Speaker 00

  The other thing that we can do is you can just come over here and you can just highlight things. You know, like I can say, you know, here's a bunch of stuff across all three that I, you know, I don't like these.

• 17:43Speaker 00

  Remove them. And I can still

• 17:47Speaker 00

  Collaborate with Spiral across all three drafts. It doesn't have to be one draft at a time. And it kind of just like allows me to go and traverse the tree. Sort of, but just three at a time. Like I don't, I, there's only so many that I can handle mentally. It's also text. I think one of the, one of the things that we learned over the last like six, seven months is I think everybody is really used to from tools like Midjourney, seeing multiple options when it comes to image generation. But text generation, like multiple options, it's really hard to pass what the hell the differences are. Like you can tell, okay, the middle one here is bigger, but like, is it that much better? And so three kind of felt like that perfect middle ground between showing you multiple options, but not overwhelming you.

• 18:32Speaker 00

  So yeah, that's how it works. And typically when people, like when I use it, when I've noticed, you know, a lot of our users using it, they sort of start here. They, you know, they'll find one angle and they're like, ah, I don't want to go down this angle. I want to go down these two angles.

• 18:45Dan Shipper?

  I like the first one. The questions is greater than, than drafts. I think that's actually the, the, the, the, the hook actually got me.

• 18:53Speaker 00

  Right. And, and so like, that's typically what happens with people. They use it. They're like, ah, that one didn't get me, but that one got me. And they'll like, go, they'll find bits that they like and they'll bring them over. And then, you know, a couple of more conversations back and forth and they'll find something that they're like pretty happy with.

• 19:10Speaker 00

  So yeah, that's, that's generally how it works. Like it's, we're, we're calling it a writing partner. A big part of that is that it talks to you, has conversations, sorry, asks you questions. And then it drops and it's just like very helpful in drafting across three different things. You can, you know, I can ask it for, hey, give me a bunch of options for the hook. And we have this UX where it'll generate a bunch of different options within one specific draft and you can kind of very quickly

• 19:40Speaker 00

  change them and switch them out and see what works and what doesn't work.

• 19:46Speaker 00

  And we've like taken a lot of inspiration from code code. So it has all these tool calls of like it reads the draft and then it'll like then make edits. So like I built an arrow. So like next, here's another one. There's another one. I can always go back and see the original. Here's another one.

• 20:01Dan Shipper?

  Oh, interesting. I this I've never even seen this. This is really cool.

• 20:06Speaker 00

  Yeah.

• 20:06Dan Shipper?

  You're building so fast, I can't even keep up.

• 20:11Speaker 00

  Yeah. And so like, there's a lot of tiny little moments like this that we've added to like, help make it sort of useful to do that. That's kind of currently where it is. Like we have, you know, like we talked about workspaces, we have writing styles, which is very much grounded in what old spiral was, you know, you give it a bunch of examples, it tries its best to emulate those that writing style. And again, I think one of the things that I think I found over this experience is that writing is something that is fluid. I think when we first started this experience, one of the things that I did actually was I read this book. I read Why I Write by George Orwell. And this was written during the Second World War. When I was reading it, I was like, this writing

• 20:55Speaker 00

  kind of sucks. There's some parts of this that I don't like, I didn't like. And I think that made me realize how much the like, the way that we talk, the way that we communicate changes so much. And so like, good writing is so fluid. I think that's something that I've had to come to accept. And, you know, we're not training our own model. I think we, you know, we kind of was like, how far can we push frontier models? And just with prompting and sort of context management and like sort of economics and doing handoffs and that kind of stuff. And there's so much of that training data that is slop. And that is something that I think we've

• 21:37Speaker 00

  We're like, it's interesting. I remember when we first started this, I was going down this very much like rules-based approach. All of my prompting had these like rubrics with scores and I would ask the writer to like score itself of how well did it write a hook? Um, and none of that worked. Um, it was all really like, it was all really bad. And I think we decided to move more into like, let's allow it to be fluid. Let's allow it to like be flexible. Like, let's not give it, let's not constrain it with these really hard rules. Um, and that plus sort of the most recent generation of models, sort of Claude four, G P T five, they unlocked

• 22:18Speaker 00

  a new like level of capabilities. Um, there just wasn't possible for, especially for writing, especially for like interviewing well and reasoning over a long context window. And

• 22:31Speaker 00

  yeah.

• 22:33Dan Shipper?

  Yeah, I mean, I love all of that. I think the thing that's in my head about this is just looking at this and listening to you talk. I'm just like, I'm so proud of you. Because where you were eight months ago is so different and where the product was is so different. And you've just taken this thing and completely reinvented it. And it's, um, and in a lot of ways, I think you've reinvented the product. And I think you've, I don't know if you've reinvented yourself necessarily, but you've, you've certainly pushed yourself in this new direction, um, to really understand what makes writing great. And it's been just awesome to watch. And what I want people to see is where you started. So could you open up old spiral so we can show them what that looked like? So they can get a sense for like how different it was.

• 23:19Speaker 00

  Um, and interestingly, this is not the first version of spiral. This is.

• 23:26Dan Shipper?

  I guess that's true.

• 23:27Speaker 00

  Yes. So the first version of spiral was AI generated slop by Dan Shepard.

• 23:33Dan Shipper?

  It was.

• 23:36Speaker 00

  That's my specialty.

• 23:39Dan Shipper?

  At Ever, we run four AI products in-house, and we just launched a new one. When we needed to build a beautiful landing page for it, we used Framer. Most design tools lock the good stuff behind a paywall. Expensive and definitely not fun. Framer is different. Framer already built the fastest way to publish beautiful, production-ready websites. And it's now redefining how we design for the web. With the recent launch of Design Pages, a free canvas-based design tool. Framer is more than just a site builder. From social assets to campaign visuals to vectors and icons, all the way to a live site. Framer is where ideas go live from start to finish. Your entire workflow lives in one place. No Figma imports, no messy HTML. Design your end result in Framer and it turns into a working website.

• 24:23Dan Shipper?

  Faster, cleaner, and more efficient. Because Framer is a true design tool that also publishes professional, production-ready sites, you get features like P3 color spaces, SVG animation, inline editing, and precise scaling. It'll help you stand out as a professional. Ready to design, iterate, and publish all-in-one tool? Start for free at framer.com/ design and use the code DAN to get a free month of pro. Rules and restrictions may apply, as always. And now, back to the episode.

• 24:51Speaker 00

  So this is the current or the previous version of Spiral. It got a bit of a facelift when I first joined about a year ago or so now. And what it does is you will feed it examples. You would feed it examples of writing that you liked. And then you would give it a new input and it would try its best to recreate that examples that you gave it. So here is one. Rough outlines into punchy short tweets is one of the spirals. And the way that it worked is we just gave it a bunch of these examples of things. Like, look, Japanese population is collapsing, Japan's population is collapsing. And what it would do is it'd take all those examples and it would create like basically a style guide. And then, you know, the prompting was very simple.

• 25:34Speaker 00

  You would just give it, you know, let's take maybe just the prompt that, see what that does with that. And then it would just like generate three. And there are people who still use this today. I think there is like certain parts of Ever that still uses this for like summaries and bullet points of things. And this allowed you to very quickly get some options. I think what was interesting to me.

• 26:03Speaker 00

  Was that this was a great first start for last year. Um, I think that's why a lot of people kind of gravitated to all this was like, oh, it's made well. Um, what it, what it said that it did, it, it definitely did it. Um, but I think we would look at the outputs that came out of this and we're just like, ah, it's not there. And then this paradigm didn't allow for collaborating. And I, you know, I tried to hack it a bunch of ways, like I had.

• 26:30Dan Shipper?

  Collaborating with the AI specifically.

• 26:32Speaker 00

  Collaborating with the AI, exactly.

• 26:33Dan Shipper?

  Yeah.

• 26:33Speaker 00

  Um, and you know, I tried to add on a bunch of things, like, you know, a lot of people who still use this today will like, write custom instructions and that that's where they will try and like, push the AI towards where they're actually trying to go, but then it never really worked. Yeah, I think we, we saw usage declining and like personally for me, I, I never liked the stuff that came out of it and I never found myself going like, uh, reaching for it ever for anything. And when I did, it was because I was like, I should be, it, it very much felt like a should. I should be using the product that I'm claiming to, to wanting to work on. Um, but as I've learned over, you know, the last couple of years, shoulds are not what I should actually be doing with my life.

• 27:16Speaker 00

  And yeah, I think it was, it was also this like interesting tension of this people who actually use this thing. There are still people who use this thing today, um, which is really cool, but I, I just, I'm struggling to care and we're not using it. And I think one of the things that has become very apparent for the product studio over the last couple of months, is if we're not using it, it just doesn't matter. It doesn't matter if other people are using it. I think, you know, Naveen in Monologue is such a good example of that. Like he just hammered away for months until he found something that he was really excited about. And everybody else was excited about, and then he hammered away until it actually worked.

• 27:57Speaker 00

  Like I was actually, I think out of everybody at every, I was the last holdout to use Monologue because he just wasn't there yet. And then, and then, and then he got me and like, and I think that's one of the things that we've learned at the product studio is like, I think if we're super excited about it and the people around us are super excited about it, like, let's just do it and it's going to be great. Um, yeah, and.

• 28:16Speaker 00

  This, I just don't, I don't think any of us were excited about this anymore.

• 28:19Dan Shipper?

  Yeah, yeah. I think there's a couple of lessons in here for me is, uh, one of them is, yeah, like when, when I first built the first version of Spiral, it was very cool. And, but things move so fast in AI that because it, it stayed with this sort of like text transformation thing, as soon as the models got better, it needed to be totally different and we just didn't do that, basically. And I, and so that's one thing. Another thing is,

• 28:52Dan Shipper?

  it, it really underscored for me how important a daily use product is. And it made, it forced me to think about,

• 29:03Dan Shipper?

  well, how useful is this sort of text transformation for a writer and how often am I going to need to do that and,

• 29:13Dan Shipper?

  and, and also how complicated it is to actually produce really good content and how hard it is to do that in a one-shot way. And that we needed something like more dynamic. But I think the, the biggest thing is, um, I built the first version of this and then handed it off to you. And this is something that we've seen a lot, actually. Now, we've seen it with you, we've seen it with Yash, who, um, is building Sparkle, which is something that I built in like 2020. And, uh, there's this process that a GM has to go through if you're working on something that's not yours to like fully own it. Because, um, I, I think, you know, seven or eight months ago, whenever that was,

• 29:57Dan Shipper?

  you came to me and you're like, I don't know if I'm the right guy for this. Like, I don't know if I should be working on this.

• 30:03Dan Shipper?

  And you were just banging your head against the wall, being like, I gotta get the MRR up and,

• 30:13Dan Shipper?

  and, um,

• 30:16Dan Shipper?

  and that sucked to see. And when we dug into it together, it was clear that,

• 30:28Dan Shipper?

  You didn't have a vision for it because it didn't feel like yours?

• 30:32Speaker 00

  Yeah.

• 30:32Dan Shipper?

  And then that was really demotivating. And for me, I was like, well, I mean, I have a thousand, like, I can give you a bunch of stuff, but like, I don't think that solves the problem because like, I'm not the GM. Like, you have to, you have to solve the problem. And I can be there to support and help and whatever. And I sort of put it to you, is this like what you want to spend your life on? Like, do you want to work on this? Or do you want to do something else? Because if you want to do something else, one of the, one of the lovely things about, about what the setup we have at Every is you can do something else. Like, you don't, it's not like, uh, their funding runs out and then, you know, the startup fails. It's like, okay, this didn't work. Great. Let's do something else. Uh, let's keep experimenting.

• 31:12Dan Shipper?

  And I think you went back and thought a lot about, do I care about this problem? Do I really want, actually want to make great writing? Or I think what you came, what you came to is the thing that motivates you is the, is the great writing bit and the text transformation for marketing was not, not that interesting to you. Tell me about that.

• 31:31Speaker 00

  I think, yeah, the journey was really interesting. It, you know, I think it was March. Um, I'd spent January, February and March just like dragging myself out of bed, just like feeling guilt. And yeah, we had that conversation and I think the thing that I realized was that good writing is downstream of good thinking. And that is a really interesting problem of everybody is going towards, let me just generate a thousand things, make a million blog posts, put out a bunch of tweets.

• 32:09Speaker 00

  You know, AI generated replies and it, one, I just think is like, where do I want to, what do I want to do myself? I think I want to be intentional with what I write. I want to be intentional with what I think. I want to be intentional with what I say. And, but that doesn't mean that like, I have to shun away modern tools. I have to shun away this crazy, we've made sand think. I'm not going to say no to that.

• 32:32Speaker 00

  But like, how can I use it in a way that it actually helps like, yes, and me? Or like, you know, gives me that, you know, it's, the sum are greater than the, equal than its parts or whatever that phrase is, you know? And I think that-

• 32:47Dan Shipper?

  The whole is greater than the sum of its parts.

• 32:48Speaker 00

  That's exactly what I was trying to say.

• 32:52Speaker 00

  Dan Shipper steals hats and he steals words out of my mouth.

• 32:56Dan Shipper?

  I think I said that in our Q4 kickoff. So who's stealing from who?

• 33:02Speaker 00

  That's fair.

• 33:06Speaker 00

  And yeah, I think just like I

• 33:11Speaker 00

  I think there's something really powerful with good writing or like, you know, it's not even about good writing. Articulating what you want to say to the world well can do so many things. You know, not to like go all crazy and be like, this changes the world, but like good writing, good thinking, good articulating moves mountains, it moves people, it gets people to do crazy things that they think is like impossible. It gets people to, you know, shun the status quo. It gets people to like, you know, do all sorts of things. And I worry about a world where people are like, ah, cool. I'll just let ChatGPT do all the thinking for me. I'll let Claude do all the thinking for me. It's like, no, like, it's actually just, let's use it intentionally.

• 33:55Speaker 00

  And I think what that requires is, you know, if you think, if you go back to the first podcast that we did, I actually said this, where it's like, most people aren't good prompters. Ninety nine percent of people who are using AI are probably rubbish prompters. And I still think there is this beautiful space for building products where it's like, hey, don't worry about the prompting. Just like use the product well. And if the product is designed and prompted well to do the thing that, you know, I think it should be out in the world, which is taking a beat and actually thinking about what you're writing. AI can help you do that. But I think the models as they are, people, the path of least resistance is just give me this, just write, don't make me think. And I don't, I don't think we should exist in that world.

• 34:41Speaker 00

  And I think deep down, people don't want to exist in that world and AI, we don't have to be Luddites. We don't have to shun away AI to still have that world. We can have both.

• 34:52Dan Shipper?

  I totally agree. And I think that is a really natural segue into how are you building this? And what are the things that you're using to make such a polished product? Fully featured product, useful product as one engineer?

• 35:10Speaker 00

  Yeah, it's, you know, to your point of the models just change so quickly, the tooling changes so quickly, like.

• 35:20Speaker 00

  If I think back to where we were in March when we first started this, I was I was probably bouncing around from cursor to windsurf and that was it and

• 35:29Dan Shipper?

  Windsurf was the new thing. It was like, whoa, this is actually, it was the first thing that was a little bit agentic.

• 35:34Speaker 00

  Yeah, yeah, they had their like cascade feature. And cascade was so different and it was like agentic and it would do all this stuff. And now I'm in my terminal all of the time.

• 35:47Speaker 00

  I, you know, the one thing I regret is learning how to use Vim because I never use Vim anymore. I'm never like bouncing around the text editor in Vim anymore. Shout out to all the people who know how to use Vim. And so now I'm completely inside my terminal. For a very long time, it was all Claude code. And as people who know about every, we all love Claude code. I think Claude code was that first thing that like kind of got rid of the fluff. You don't need an IDE, you don't need all of this. It's just like text input, give the agent a bunch of tools, and it's actually not that many tools. It's read and edit, which is like kind of all it did to begin with and like make to-dos for yourself. I think that's the first three tools that Claude code probably had.

• 36:27Dan Shipper?

  And use Bash.

• 36:28Speaker 00

  And use Bash, right? So four things.

• 36:32Speaker 00

  And it was amazing. The models itself were really good. And then Claude, I think, I think there was this moment, at least this year, who knows, probably by next year, it's not going to matter. But Claude 4, I think, for me, feels like such a pivotal moment in this space because I think it just unlocked so much capability in programming, writing, and like a lot of things.

• 36:57Speaker 00

  I guess the other thing to say is like that also opened up the space for everybody else to try this. So there's so many CLI tools now. We have AMP, OpenAI have their codex, and most recently, I've been using Factory's Droid. And I've completely fallen in love with Droid.

• 37:14Speaker 00

  One of the reasons why, and we can jump into it, I'll share my screen, but I think one of the reasons why is that Droid is model agnostic. Almost, they give you five models to play with, they give you GPT-5, and they give you all the anthropic models, and then they most recently have the GLM 4.6 model.

• 37:33Speaker 00

  The other thing that I think they've done really well is they've really thought about the ergonomics for each model.

• 37:39Speaker 00

  They're clearly prompting it differently. They've really thought about like, okay, we're only going to support this model and how the models interact with each other. And the ergonomics work really well, where I will literally have the same type of request inside Claude Code and another one inside Droid, and Droid will just do so much better with the same model. This is, I'll give you a very concrete example. I had a database migration that completely fucked up. And I was actually in a car going to Ikea to New Jersey. So I was in the car going over the Williamsburg.

• 38:12Dan Shipper?

  New Jersey, not Red Hook?

• 38:14Speaker 00

  Talking to my wife. She ordered the thing in the wrong place.

• 38:20Speaker 00

  And so, yeah, she's driving this car, going over the Williamsburg Bridge. I'm there in the passenger seat, just going insane to Claude Code, like this database migration is fucked. And then I just took the same thing over, same model, it was Opus 4.1. And it just got it, three minutes. It was like, oh, here's the issue, got it. And so they've given it, they've done a better job than I think than Claude or the Anthropic team have in like giving the model the ergonomics and the tools that it needs. It's like, oh, here are the tools that I need. And here's like, I think the right prompting. I don't know what else they're doing, but there's something about it where it's like, I feel so much more confident coming to Droid. That I just don't feel in some of the other tools.

• 39:01Speaker 00

  I think the other thing about.

• 39:05Speaker 00

  Well, your original question was like, how would I build this as a single engineer? Um, I think also I always get shocked every time I talk to other people. We at every, we're clearly at the edge of how to use these things. I think for a very long time I was the number one user of Droid. I've been ripping the most tokens and it like surprises me. So like I'm on their max plan and it was October 3rd to October 24th or something like that. I've already run out of tokens. Like I ran out of tokens well before time.

• 39:38Dan Shipper?

  We gotta call Ben Tassel and get you.

• 39:40Speaker 00

  Get me some more tokens.

• 39:43Speaker 00

  Because yeah, I think we're just like ripping them so much and

• 39:51Speaker 00

  I think going into the deep end, there's a lot of people for maybe not now, but like the last time I spoke to people, they won't, they wouldn't use Yolo mode. They were afraid of using Yolo mode. And I think that's kind of a foregone conclusion for us. It's like, of course you're gonna use Yolo mode. Why are you gonna accept everything that it, you're just gonna let it do it?

• 40:09Speaker 00

  So yeah, I think really leaning in, I think letting go of the identity of I'm an engineer and I'm gonna write, I'm gonna use Vim and I'm gonna write code and blah, blah, blah. Like letting go of that identity and being like, I'm, when you really peel back the layer of what I think I am is that I'm somebody who just makes things. And I don't really care how I make them. I do, I care about like how it's built and like I clearly care about the end product. But I don't care if I have an agent writing the code or if I'm writing the code. As long as it's good code and it does what I want it to do, doesn't really matter, you know?

• 40:38Dan Shipper?

  But how do you do that? Because I think a lot of people listening or watching are saying, cool, great. But how do you actually be a craftsman if something else is coding for you? Isn't that all just gonna be slop?

• 40:49Speaker 00

  Hmm, so let me open up my terminal.

• 40:59Speaker 00

  Before I share my screen, I think it's a philosophy of, you know, you brought this up right at the top of measuring twice and cutting once. And I think this is actually the one thing that I've learned from, from like, trying to build something that writes well, which is also just like looking at something and feeling internally what actually like calls out to me. And like, does that feel right? Or does it not feel right? And I think you could just, you could do that with, with a button. Like, does that button feel right or not? Does that spacing on that thing, thing feel right? Does the, does the, not does the code feel right, but does the thing that I expect, the thing that Claude just ripped out, does it do it the way that I want it to do? But also further, does it, does it add to the piece of the puzzle in the right way? Like, LMS can skin a cat

• 41:44Speaker 00

  in a million different ways. There are probably only a handful that you actually should be using that are like, right, or like, actually fit the, the, the way that you want it to do. And so I think a lot of like, building this product has been, um, feeling out like, okay, when I ask Claude to do something, or one of the other models, does it actually do it the way that I want to do it? Um, so if, oh, if I share my screen, um, a lot of the ways that I use, and, and you could do a lot of this in, in Claude code as well. Um, but a lot of the ways that I use these tools is, one, I'm always doing multiple things at once. Um, I think waiting around for the model to complete. And I think the worst habit that I got into that I had to like, uh, cut out was scrolling Twitter whilst

• 42:29Speaker 00

  I waited for an agent to complete. Um, that is a just killer to productivity for me. Um, so.

• 42:37Dan Shipper?

  And what is it that you do? Because you do a thing that I actually started to copy for this. What, how do you, how do you stop yourself from scrolling Twitter?

• 42:45Speaker 00

  So, Worktree is, is like the big thing. So.

• 42:48Dan Shipper?

  Oh, no, no, I was saying, um, so, wha- what I've noticed you do is you take your phone and you put it in another room. And so I started putting my phone next to yours.

• 43:00Speaker 00

  I know it's confused whose fun it is. Yeah. So we have, we have a couple of places in the office where there's just a couple of ledges or we have this beautiful every sign. My, I think to talking about like intentions is like, one of the things that I try to do the moment I walk in is I take my phone out of my pocket. And I just place it face down on one of these ledges. And I leave it there and I try my best not to look at it. And I also, I'm always on do not disturb. As you can see here on the top right corner, I'm on do not disturb. I have notifications off. Like I have an Apple watch, but like this notifies me about nothing. And I think it's, it's really easy to be like, oh, now because of this tooling, I can do the job of three people as one person.

• 43:39Speaker 00

  And I have seen in myself and in other people that actually what people end up doing is they end up doing the job of one person. And then they just procrastinate or they do the other things in their lives that they think they want to do. And I, I noticed in myself that I wasn't happy doing that. I really am somebody who's all in. And then when I'm, if I'm working, I'm working. Don't talk to me about anything else. My wife hates that about me. And then if I'm not working, I'm not working. Like I'm trying to be present, intentional. If I'm with somebody, I'm not texting other people at the same time. And that's been really helpful. And I, I think it was also really important when working with like LLM models. Cause like programming before was I would look at the code. I would spend a lot of time, attention, reading it. I would read it. I'd read it. I'd read it.

• 44:23Speaker 00

  Tests would pass. I would spend a lot of time. And now it's like, no, I'm just going to let it go rip and I'm going to go do something else. And so what I think that's allowed, and it requires being really intentional is just, can I do parallel things? Like, can I just do multiple things at once? And so one of the ways that manifests is I'll, in, in one terminal tab, I'll have like two panes. Or sometimes I'll have like three panes open and I'm usually like ripping Droid on like a bunch of different things. So like here, this one, I was fixing a bug and like, you know, this one, I might be actually earlier today, Kate gave me some copy edits inside the app. So I had Droid go through and like do those copy edits, but then here in another window, I've actually been messing around with some of our judging prompts. And I've been using like Python notebooks. So I'm like writing up Python notebooks with Droid. I have this other one here.

• 45:08Dan Shipper?

  Just to pause you, the, the judging prompts are like, uh, judging whether writing is good. And that's the sort of core component of making good writing is, is getting the AI to recognize if writing is good or not.

• 45:21Speaker 00

  And I think to, to.

• 45:25Speaker 00

  Go on a quick tangent, really. I think the one thing that we saw about Claude 4, Opus specifically, back in June or July or whenever it shipped,

• 45:35Speaker 00

  it's really good at judging writing and not rubber stamping. I think models before this would, you would give it some of its own writing. It was like, yeah, my writing is great. It's a B+. Or you'd give it other, you know, other people's writing or other agents' writing, and it would always be like a B+. And there was a lot of like, you know, tricks that people would do, like give it a rubric and then tell it that like actually a seven out of 10 is impossible, forcing it to kind of like actually change it from, but then everything would just be a six or like a 5.8. And what we found was that Opus was actually really good at reliably, repeatedly giving Boolean answers and like good

• 46:16Speaker 00

  prose as to why it was saying yes or no for something. So we, we have this one test internally where we see if writing is like engaging. Does each sort of sentence keep a reader engaged as you go through? And we found that like Opus was the first, Opus 4 was the first model that would like reliably, almost every single time would say the same answer and it would say the same answer that we would agree with.

• 46:39Speaker 00

  That then also came over to Sonnet 4.5 and somewhat now to Haikyuu 4.5.

• 46:46Speaker 00

  Yeah, and that's like a really important part of the product, but it's also really important for us building this product and for me, building this product of like, where is it that this needs to get better? And this is actually a feature that we're going to build directly into the product. So like Spiral can kind of like judge itself using another agent to see where else it can improve. And this kind of helps us create this like feedback loop of being able to watch how good or bad are the outputs that come out of it. Also with people just telling Spiral, I don't like this. I think it's really the benefits of having, you know, the one thing that we didn't have from the old product, the old product only had thumbs up and thumbs down. And that was really useless. With a chat-based product, people just say, I don't like this because, and you know, we have,

• 47:30Speaker 00

  we're using something called Raindrop, which is basically like Sentry for AI agents. And we just get a report every single day of like, this is what people said they liked, and this is what people said they didn't like. And here's why. And I could just see the chat and it surfaces it all up for me. So being able to see how people use the product and just read what they're saying to Spiral is really helpful in improving it.

• 47:50Dan Shipper?

  And and one of one of the interesting tangents that we've been down over the last couple of weeks is, and this is one of those things where I only ever read it. So I don't know if this is actually the right way to say it, but Disby and JIPA is how I say it in my head. For other people, maybe it's DS Pi and JIPA. I don't know. But basically, there's this, there's this prompt optimizer, Disby, that is sort of like having, it's having a moment right now among AI people where it will,

• 48:21Dan Shipper?

  basically, you can give it a prompt and it's like an objective and it will, it will optimize your prompt for that objective. And JIPA is a specific method for doing that, that I can't totally explain, but it's a new and interesting way of doing it. And so one of the experiments that we've tried is giving me a bunch of tweets and then having me thumbs up and thumbs down them and then give like concrete feedback to see if we can generate a judge that has my taste. Do you want, do you want to talk about that? And what what we found what's worked and what hasn't worked?

• 48:53Speaker 00

  Yeah, so we, we have a great piece on every with Michael Taylor around Disby. He's actually the one, he, he came here from the UK and sat in the office and like actually taught us how he uses it.

• 49:05Dan Shipper?

  Does he say Disby?

• 49:08Speaker 00

  I don't know, but I, I think it's Disby. I think Disby sounds so much better than DS Pi. Even though I guess like DS Pi is probably the right way to say it.

• 49:18Speaker 00

  And yeah, it, it is just like kind of when people look at it, for a very long time this year, I've been going on their landing page and I'm like, I have no clue what this thing is. And he did a really good job of explaining. And I think we have a video out where he's actually teaching me and Kieran how to use this,

• 49:35Speaker 00

  where he finds just ignore 80% of what it is and just use it as an optimizer. And when you just use it as an optimizer, it makes so much sense. You don't have to throw away all of your like frameworks that you might be using already in your like app, if you're using the AI SDK or whatever, just use it as a prompt optimizer, extract the prompt, put it in your product. Because it's very much built to be this like all encompassing framework, but it's just really confusing. I find it to be, but yeah, using it as a prompt optimizer is great. And What we, I think we can actually like, look at that, that judge that we created for you. The way that it works is you basically just give it a bunch of predefined labels with, you know,

• 50:18Speaker 00

  generate a tweet about blah, and then we had you literally give it a thumbs up or a thumbs down, and then just write out your thoughts. And we would just start with a basic prompt to begin with, see how good did it do? So like, the base prompt was about 58.8% accurate to you. And that was just a prompt that I asked Claude to come up with. So like, just over half of the time, it would say the same thing that you would say.

• 50:42Dan Shipper?

  It's not terrible, but.

• 50:44Speaker 00

  It's not terrible.

• 50:44Dan Shipper?

  Yeah, yeah.

• 50:45Speaker 00

  Yeah. But like, you know, you could flip a coin, basically.

• 50:50Dan Shipper?

  Yeah, I guess that's true.

• 50:52Speaker 00

  Right?

• 50:52Dan Shipper?

  You're totally right. Yeah, it is terrible.

• 50:58Speaker 00

  Especially if, you know, this is just for writing marketing materials, but like 50%, like if you're trying to do something important, this is really bad.

• 51:04Dan Shipper?

  Yeah, yeah, yeah.

• 51:06Speaker 00

  And the way that it works is then G E P A, and I also can't speak to exactly how it works, but my understanding is, is that you, you give it like a metric for how it can, what it will do is it will generate a new prompt, and then it will test that prompt against your, your judges and the data that you've given it. And you'll see how close does this new prompt that is generated get to the sort of like gold standard, which is from you in this example. And then goes, okay, this prompt that I tried wasn't that good. So let me try another prompt. And so the way that I kind of see it is that it's just like trying as many prompts as it can until it finds something that's better. So it really is just sort of like throwing spaghetti on a wall and seeing if it sticks.

• 51:47Speaker 00

  And then, you know, it will rip through tokens a lot. You, you can basically set it to a max number. So here I have like max five full evals. So it goes through, five means it goes through 85 iterations. I don't really know what that means, but whatever. And so like here, you can see, it's just like, here is one of the prompts it came up with, and then it came up with another prompt. And, you know, that prompt was 66.7% accurate. And so like, it keeps going until it gets a little bit better. You know, here's another one that it tried that was 33.3% accurate. So way worse. And so the idea is.

• 52:16Dan Shipper?

  Just do the inverse of that prompt and it would be.

• 52:19Speaker 00

  Exactly.

• 52:23Speaker 00

  And so like, it's just, you know, it learns and it try and it learns from trial and error, which I think is cool, which is when I think about how I was prompting for very subjective things like this, it was just kind of trial and error. And I would work with Claude and be like, okay, the output kind of came out like this, but it is missing this thing. Give me a suggestion or, you know, one of the things that I would do a lot before this, and I still do this, is I would find other people's prompting guides. And I would say to Claude, distill down the principles of these prompting guides and then help me. And like, that's somewhat useful, but I think this, at least for creating judge prompts, is a bit more, it feels a little bit more scientific. Maybe it's because we're in a Python notebook and there's percentages and

• 53:04Speaker 00

  stuff. But it's also allowed it to be like, oh, I can very clearly see the before and after.

• 53:11Speaker 00

  So then finally, it spat out this prompt that was 76.5% accurate, which is a lot better than half. Again, not perfect, but we're getting closer and closer there. And then it like, sort of goes through it and we can actually use it. So maybe what could be fun is if I stop sharing my screen.

• 53:28Dan Shipper?

  Wait, wait, before, before you go there, before you go there, I just want to know, what is, what is this be Dan? What is in the prompt? Like, give me a couple of things that are in the prompts. Because I'm just, one of the things that's, that's really cool about this is it's telling me stuff about how my brain works that I might not even know.

• 53:42Speaker 00

  It's actually very simple. Like, if you asked me to write a prompt like the, like, write a prompt that emulates Dan's judging, I would not write something this simple, which I think is kind of counterintuitive. And this is, it's just a simple list of things. And I don't think this is perfect, right? And it doesn't work all the time. And like, if I was just, you know, in the, in the data set we gave it, it said 76%. I feel like it's probably more like 65% accurate to what like, I, I would perceive as actually good content versus bad content. So like, it definitely still needs some work, but like, it's some very simple things, like, simple, concrete, specific language, not vague generalities. And I think what's really interesting about this is

• 54:25Speaker 00

  Past generations of prompting would be like really, really specific on the prompt of like, well, what is simple, concrete, specific language? And it would have like, here are like a bunch of examples of what really simple, concrete, specific language is. And what we've seen from doing this process is actually just letting the model breathe. And like, you know what? They're big enough. They have enough parameters. They have enough training there. They clearly know what simple, concrete, specific language is. Maybe sometimes it's maybe a little too buzzwordy. And so there's like stuff that we have to do there, but it, we, the models have gotten a lot better.

• 55:00Speaker 00

  You know, clear promise that gets paid off. You know, I actually think that's a pretty important one. If I was to say like, the kind of feedback that you've given me is, is, you know, a lot of that.

• 55:09Speaker 00

  Relatable, sometimes funny, focuses on topics that people care about, the proper tense, one clear idea, but like, what is bad content? It's generic openings that could apply to anything. It's the wrong tense. It's too wordy, breathless tone, chop, slop, unclear, choppy syntax, telling instead of showing. So there's a lot of like, there's like some specifics there, like proper tense, but it's also principles of like telling instead of showing.

• 55:35Speaker 00

  I think the other thing that's interesting about the, this prompt here is like sort of the evaluation approach, like how it actually does that. It starts with a hook. Is the opening sentence surprising, counterintuitive, or is it generic and could apply to anything? And then next, always pull exact quotes from the content to support your points. So this is how it's evaluating. It's assessing the voice, looking for specifics, it's checking for a payoff.

• 55:59Speaker 00

  Yeah, I think the thing that's the most surprising to me about this is how simple this actually is. Like if I was to, with Claude, write a prompt that did this, it would probably, you know, this is 112 lines. It probably would have been many more lines of like text. And yeah, very, very interesting.

• 56:17Dan Shipper?

  Well, let's test it. Let's do the Newlywed Games with Dispy Dan and Dan. And we'll, we'll do like a whole, you know, we'll do a little like graphic here and I'll, I'll give a thumbs up or down and we'll see what Dispy Dan says and we'll see if we match.

• 56:31Speaker 00

  Okay, I'm gonna, I'm gonna find a tweet on my timeline and send it to you.

• 56:37Speaker 00

  I'm gonna send it to you and then I'm gonna paste it into Dispy Dan. And what I want from you, Dan, is a thumbs up or a thumbs down.

• 56:44Dan Shipper?

  Do you want any of my, like, actual feedback?

• 56:47Speaker 00

  Yeah, that could be good, too.

• 56:49Dan Shipper?

  Does it, and it does it give, it gives feedback, right?

• 56:51Speaker 00

  It gives feedback, yeah.

• 56:52Dan Shipper?

  Yeah, so we should, we should match the, the thumbs up and the thumbs down will be the main thing, but we should, I'm also curious about my, my feedback.

• 56:59Dan Shipper?

  Okay, so the, the tweet you gave me, we'll put it up so people can see it, but the tweet you gave me was, "I feel like the VC community is doing a disservice to the startup community ecosystem by constantly organizing all these events, especially on weekdays at 6:00 PM. And I never understand how, how so many founders are able to make it to these leaving the office at 5:30 PM. Makes sense from their POV."

• 57:22Dan Shipper?

  This is very thumbs down. Sorry, Flo.

• 57:33Dan Shipper?

  Okay, so first thing is, um, starting a tweet with "I feel like",

• 57:41Dan Shipper?

  sometimes it actually really does work because it is,

• 57:46Dan Shipper?

  it feels more casual and like something that you didn't edit, but also it, it lowers the impact of it. And so if you're using "I feel like", you wanna be pretty intentional about that.

• 58:01Dan Shipper?

  And because this tweet is very counter, it,

• 58:08Dan Shipper?

  he's kind of going after people a little bit. I think you gotta do, it would be better with a full send of, you know, the, the VC community is doing way too many events, like organizing so many events.

• 58:24Dan Shipper?

  I think, oh, you know, I was only seeing part of the tweet. Okay, because I was looking at it in the Discord preview, so it continues. So I feel like the VC community is doing a disservice, blah, blah, blah. I never understood how many so many founders are able to make it to these, leaving the office at 5:30 PM. Makes sense from their POV, they're building a network and effectively running the equivalent of an enterprise sales motion. But in the end, it results in drag in the community. Few founders dare to say no to 99% of the invites they receive, which hurts their business.

• 58:57Dan Shipper?

  The thing I like about it is there's something true here.

• 59:04Dan Shipper?

  And it feels very stream of consciousness, like he just kind of was in the car on the way to something. It was like, blah, blah, blah, here, like, here's what I think. And I think that that's where all the best tweets come from. And there's something interesting about the core idea of it, which is,

• 59:26Dan Shipper?

  if I had to take a little bit further, there are certain stable equilibriums in ecosystems where

• 59:36Dan Shipper?

  everybody in the ecosystem doesn't like it, but you end up there, you end up stuck there. So like having so many events is, it's one of those things where it's actually not good for anyone. Because VCs are like, I guess I have to put on all these events and I'm wasting money on it. And people, I guess, show up, but I don't know if it's really that differentiated. And founders are like, I wish I could work.

• 59:58Dan Shipper?

  But, but everyone keeps doing it anyway, because they feel like they have to. So I think there's a core idea there that's kind of interesting.

• 1:00:07Dan Shipper?

  But I think this would just hit way harder if it was.

• 1:00:13Dan Shipper?

  I think VCs are actively hurting the startup community by holding so many events. With maybe like one or two more sentences of why that is.

• 1:00:25Dan Shipper?

  As it is, it's like, it's a little wordy, and he's also going after

• 1:00:30Dan Shipper?

  VCs and founders at the same time. And as I think a little bit, it feels like.

• 1:00:38Dan Shipper?

  Don't necessarily want to open up a two-front war at the same time.

• 1:00:44Dan Shipper?

  So I give him points for an honest observation. That has a, there's an interesting idea at the core of it, but I think execution on this, it's not done in a way that allows, allows me to be like, to light up and be like, yeah, you're totally right. I'm kind of like, I don't know, it's too long to read and I think he's kind of making fun of me too. Um, instead of like getting me on board with him because I would be down to bash VCs, you know? But uh, yeah, that's, that's, that's, those are my feedback. Thumbs, thumbs down.

• 1:01:16Speaker 00

  Thumbs down. Do you, cause you, you said that thumbs down with such vigor. When you first, has it, has it, is it, is it softer thumbs down or is it still a, is it still a really strong thumbs down?

• 1:01:28Speaker 00

  That's me leading a little bit.

• 1:01:29Dan Shipper?

  It's a

• 1:01:32Dan Shipper?

  I think it, I think it is softer in the sense that I only read the preview and so it looked like it was, it was just cut off, like makes sense when the preview was where it stopped and I was like, what even is that? So I'm a little less less vigorous, but it's still not, not a great tweet.

• 1:01:50Speaker 00

  Okay. So this is what Dispy Dan had to say. So he gave the tweet a thumbs up.

• 1:01:58Dan Shipper?

  Whoa.

• 1:01:59Speaker 00

  But what was interesting was that actually, you know, you said similar things, slightly wordy in places. A clear playoff, which is like, you know, the, sorry, yeah, like clearly it felt like he'd written this himself. It felt handwritten, not AI generated, but Dispy Dan felt like it was counterintuitive. Like the VC community is doing a disservice to the startup ecosystem, sort of like a bold contrarian take. Not something, so there is, I think there's clearly still work to do. I think Dispy Dan is really thinking more about like, is, is more, what is this saying as opposed to how is it written? So like, that is something, we have other judges that look at like, how are things written? So I think one of the, one of the things that we found, kind of said this earlier, having a model do many things doesn't work.

• 1:02:44Speaker 00

  Having it do one thing is good, but sometimes that one thing isn't the whole thing.

• 1:02:49Speaker 00

  Yeah. So it'd be interesting to see adding this into some of the other judges we have, how it, how it act. But also I think this is going to be, one of the things that I've come to accept is that a product like this is going to be always evolving. The, um, the models are going to change, you know? Sonnet four point six is going to come out next week or something like that. And

• 1:03:10Dan Shipper?

  I'm so tired.

• 1:03:13Speaker 00

  And I think, you know, GPT five was really interesting of to use it, you have to prompt differently. There was a while where GPT five was the writing model inside Spiral and the prompt was so different. It had all these XML tags and it was like very spin. And now we've gone back to a Claude model and it's a much different prompt. And yeah, I think it's

• 1:03:38Speaker 00

  there is no, I mean, I don't ever really think there was ever a thing of like done when it comes to building products, especially software. I think it's more so evolving because the product itself is non deterministic. You can put whatever you want in the chat input and whatever else it wants is going to come out. And we want that to be outputs that we can, it's, it's actually a really interesting problem because you want it to be outputs, you know, if I was making Instagram filters and if I was an engineer at Instagram,

• 1:04:07Speaker 00

  I never was, just to be clear. But if that's what I was doing and I was coding up a filter, I could be like, great, this filter is sick and it works with the things that it, and like I never have to touch it ever again unless it breaks, right? But like, I don't have to, whereas now I'm like, I actually can't, I would love to say that I could stand by all of the rain that comes out of Spiral, but I can't, I literally cannot do that because it would require an infinite number of me looking at an infinite number of outputs, which is impossible. So it's a, it's a really interesting like shift in building products that

• 1:04:39Speaker 00

  I don't even think I've really fully come to terms with just yet.

• 1:04:44Dan Shipper?

  I think you're right, like good writing is alive, like it comes from something that is alive and is honest to a living experience. And so anything that is static, it can be good for a while. But over time, it becomes sloppy and static. And that's something that I think we're starting to grapple with and has some really interesting implications for the direction of this product over time.

• 1:05:10Speaker 00

  Yeah, yeah. And I think I think it has implications for like what the next generation of models look like and like what they're trained on and you know, like a lot of these models, you know, AIisms, I don't really think that AIisms come from two things, which is one, I think we just get used to them, especially I think like us, because we're looking at AIisms all the time. But then also just like the amount of nonsense that was written on the internet over the last fifteen, twenty years, and just how much of that is in the training data. You know, in an ideal world, Anthropic would hire us to like prune the nonsense out of their training data and then train like Sonnet four point nine with with

• 1:05:55Speaker 00

  the every bespoke training data. That would be great. Dario.

• 1:06:00Dan Shipper?

  Let's, yeah, if you're listening, let us know. Danny, this is fantastic. I actually feel like I learned a lot. Like I said, so proud of you and what you built and so excited for getting this out into the world, getting into people's hands and also for what comes next. Where can people find you and where can they find Spiral if they want to give it a shot?

• 1:06:26Speaker 00

  So Spiral, you can go to writing dot new is the domain. It's also rightwithspiral.com. It's try Spiral on Twitter. You can also follow every everywhere and you will find links for it. And I am Danny Aziz ninety seven everywhere on the internet.

• 1:06:42Dan Shipper?

  Awesome.

• 1:06:42Speaker 00

  Thank you very much for having me.

• 1:06:44Dan Shipper?

  Thanks for coming on.

• 1:06:45Speaker 00

  Of course.

• 1:06:54Speaker 02

  Oh, my gosh, folks, you absolutely positively have to smash that like button and subscribe to AI and I. Why? Because this show is the epitome of awesomeness. It's like finding a treasure chest in your backyard, but instead of gold, it's filled with pure unadulterated knowledge bombs about ChatGPT. Every episode is a roller coaster of emotions, insights, and laughter that will leave you on the edge of your seat craving for more. It's not just a show, it's a journey into the future with Dan Shipper as the captain of the spaceship. So do yourself a favor, hit like, smash subscribe, and strap in for the ride of your life. And now, without any further ado, let me just say, Dan, I'm absolutely hopelessly in love with you.