The Startup Ideas Podcast - We Tested OpenAI's GPT 5.6 for a Month

Episode Date: July 9, 2026

In this episode I sit down with Dan Shipper to see how he runs his work and personal life on OpenAI's Codex Desktop with the 5.6 model. He walks through his card-based email setup, daily feeds for his company and Slack, and the in-app browser that lets his agent collaborate with him inside tools like Proof. We build a small SaaS app live, called Turnaround, and use it to explore why maintenance is the real product in the AI era and where Codex-native software heads next. Along the way Dan shares his pirates-versus-architects framing, his approach to fine-tuning a copy-editing model, and the patterns — pulses, Mailroom, and router threads — that hold his system together. The throughline: pick one simple win, let context do the heavy lifting, and manage the system instead of running every task by hand. Learn how to get customers with AI Agents: https://startup-ideas-pod.link/GTM-agents-IB Timestamps 00:00 – Intro 01:16 – Codex and GPT-5.6 Overview 03:40 – Training your own model: the step after skills 04:49 – Automating Email, Slack, Meeting Notes with GPT-5.6 08:53 – Why GPT-5.6 sharpens the results 10:26 – The light bulb moment with Codex 15:05 – Building Turnaround live: a maintenance badge 18:00 – GPT-5.6 vs. Fable: A tier and S-plus tier 19:34 – LFG and goal: looping toward a finished build 24:28 – Huge Opportunity: Codex-native apps 29:33 – The design checkpoint and the "warm paper" quirk 31:32 – Local models 34:04 – From 70% to 100%: pirates and architects 37:22 – Mailroom: giving Codex its own email address 40:58 – Getting started: download, grant access, explore 43:07 – Record and Replay: turning tasks into skills 44:37 – Closing Thoughts: Start small and build over time Key Points Codex Desktop plus the 5.6 model runs as a full operating system for knowledge work — email, research, and building software from one surface. Context is the multiplier: an agent wired into your computer and the web turns every inbox and feed into cards with a clear next action. Maintenance is the real product in the AI era, now that anyone can one-shot a first version. Codex-native SaaS — software you and your agent share inside the in-app browser — opens a fresh category with healthier margins. A live build of Turnaround, a maintenance-status badge, reaches about 70% in one pass; an architect carries it the rest of the way. Start with one simple win, grow the system over time, and let curiosity lead the way in. The #1 tool to find startup ideas/trends - https://www.ideabrowser.com LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/ FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND DAN ON SOCIAL X/Twitter: https://x.com/danshipper Youtube: https://www.youtube.com/@EveryInc/videos Every: https://every.to/

GPT 5.6 is here and it's a big deal. My friend Dan Chipper has been testing it for weeks and in this episode, he shows you how you can use codex with GPT 5.6 to run your personal life and run your business. His setup is really, really cool. And by the end of this episode, you're going to learn where 5.6 works, where it doesn't work. You're also going to learn how to use codex in a really, really, really cool, interesting way so that you can make money, be more productive, and just automate a lot of that boring stuff. I loved having Dan on this episode. He's a fountain of knowledge and he shows everything.

So enjoy the episode and I'll see you at the end. Really excited about this podcast, Dan Shipper. I begged him to come on. He came on. Dan, by the end of the episode, what are we going to learn? We're going to learn how to use Codex to run your entire life and how to use it to build a compelling software business. You have my attention. Should we get started?

Let's do it. Okay. So if you haven't used Codex, it is the OpenAI answer to ClaudeCode, Claude Desktop, Claude, you know,

Claude Co-work. If you've used it before, you may have used Codex CLI, which I do not recommend. It is like, Codex CLIS is trash. The Codex desktop app is what the Claw desktop app would have been if you had just, they'd just like thrown it out and they were like, what is the ideal way to build this? Because right now, like the Caud desktop app, it's like you've got chat, you've got code, you've got co-work.

And I'm always like, which one do I use? And Codex, well, now they have, now they have two tabs, but really it's a much simpler implementation. much cleaner and much more powerful because it was built after OpenAI got to see, okay, like this new paradigm of using an agent on your computer to do your knowledge work, it had already started to happen because of Cloud Code and Cloud Co-work. And I feel like Open AI just like fast forwarded through all the messy stuff. And they're like, this is the ideal implementation. So, and I feel like Anthropic has a little bit of the mandate of heaven right now.

and Open AI is quite underrated. And I think Codex is the reason why. So Codex with 5-6, which I find to be the most usable, most powerful, fastest model for specifically for knowledge work and for coding, but like specifically for knowledge work, it's not Fable level. But Fable is like, it's like a tactical nuke. You know, it's like it's so powerful. It's like actually illegal. And 5-6 is it's more like, I don't want to use a weapons analogy. So I'm going to move away from the weapons analogy because it's not a weapon.

It's more like having a Porsche. It's like great to drive around town. You can do anything in it. You know, it goes fast. It handles really well. It's really good for collaborating. I think of Fable as being something that you have to, you have to have skill, like a lot of skill to use it well. five six it just like works for everything you wanted wanted to do so anyway that's all of all of like big way

of saying five six and codex is where I spend all my time it is my operating system for work I do everything from my emails to writing to I'm actually starting to train models now which I think is a new frontier I don't even know what that means I need I want to get into that later let's get into it let's get into it I would say like just a just a real like a small preview is training your own model is the next step after making your own skill. If you've made a skill for something and it's not quite working, train, like fine-tuning a model is the next step. And until recently, it was completely out of reach and not at all practical. But 5-6 and Fable to some extent, if you can get around the guardrails, is makes it easier, easy enough to make a machine learning pipeline and

run it that and that's everything from like grabbing the data to making like making more synthetic data to like actually running experiments and makes it easy enough to do that I think it's now possible for non-machine learning engineers to start doing it all right well I'm I'm intrigued I'd love to see some you know what you got you want to start sharing your screen let's let's go so this is how I do my email um so this is a little app that I built. By the time this comes out, you'll probably be able to get this app. It's called Tend, but you'll probably be able to get it as an open source library I'll release, but honestly, you can literally just feed this video into codex and just be like, make something

like this, and it will do that. So, you know, do whatever you want. But basically what this does is it goes through my inbox every day, and it just finds every single unread email. And then for each email, it makes a card. And the card, summarized. what was in the email, and then it has a little draft reply that it drafts for me. And then what I can do is, I can say, can you, I didn't deal with this yet. Can you find some more times, like later this week and show them to me in a draft? And then it'll go do that. And now we're on to the next email. And I just go through my emails like this. Let's see. We want to keep writing.new.

It's on name cheap currently. I can get you the Cloudflare credentials. And now we're on to the next one. I'm going to just... This reminds me of how I picture, like, in the 1960s, really wealthy business executives. Like, Mad Men's style would answer their letters. Dude, it's like literally the same thing.

It's just now everyone can do it. And what's cool about this app is it works for your inbox, but it works for, and I will say, this is an open source experiment that I've built. We have an email app called Cora, which is like a full inbox experience that is designed to be used in this way. So if you want to make your own as a builder, you can do this. This is also sort of coming as a full app. But what's really cool about this is I have different feeds for different things that I do every day. So, and in my codex, basically, my codex is built so that I have a bunch of pinned threads for each part of my life that I care about. So this is like my company thread.

And this is in this thread, this is all of the stuff that's going on in my company. So basically what it'll do is instead of sweeping through my inbox, it will find all the slacks that I haven't seen and all the meeting notes that I haven't seen and turn it into cards. And it gives me an idea of the issues that are happening in the company. And I can be like, I can decide, is this an issue that I care about or not? And if I do care about it, which I don't, if I do care about it, I can say like, oh, I'm going to go ping Brandon or ping someone else and be like, hey, what's, what's going on with this thing? In this case, I would just say archive. But what's interesting is over time, it starts to learn what I care about, what it should bring to me. And then also what my next, what the next best action is usually, like what I would normally do. So after I go through a feed,

whether it's my company feed or my inbox, it then compounds the learnings of stuff that I, you know, liked or didn't like archived or didn't archive replies that I did and then it turns it into revised prompts and you can see all the prompts here. So it has a feed policy for here's what Dan cares about. Here's what he's here's what's on his mind. Here's how to get specific sources, all that kind of stuff. And yeah, it just like sort of changes my how I do work every day because everything can be turned into a feed with cards and a next best action. And that's pretty sick. And with 5-6 specifically, you're just saying just better results? Yeah, I think that 5-5 was fine, but not quite good enough. Like, I would say generally the

email response is here. So like this email draft, for example, is like, it's as if I wrote it. Like it's maybe there's something that I would slightly change and I might. But for 90% of the of emails, which are like, you know, scheduling stuff and just more generic, it's, it's really good. So it's, I think it's a very good writer. And it is, uh, it makes far fewer mistakes. Like it doesn't, it doesn't like send emails that I probably wouldn't want it to send. Like it's a little bit more careful. Um, and it's very resourceful.

Like it just, it easily connects to Slack and it easily uses the web. Like I got a new apartment and I like literally have it like, you know, searching Facebook marketplace and like, you know, rendering like what the guest room is going to look like and shit. And that's that's fucking crazy, man. I think that people are sleeping on how flexible and powerful of a tool this is. Because, okay, so it's got the image model in it. And then it also has the ability to change other threads. So I can have this thread message another Codex thread. And suddenly you're orchestrating all these different agents doing different things.

And anyway. Well, that's sort of the aha moment I had at least with Codex was once I was starting to reference other threads and remembering things. And I was like, okay, this is, that to me was like, okay, I understand what, you know, you said Codex is an operating system. I had seen that for such a long time, but it was only until I started really referencing things that I was like, okay, I can see why this is this plus the browser. Yeah.

It feels like an operating system. That's the thing is like I do all, the reason I can do all my work in here. is that it has this in-up browser. So this is a markdown editor that I made. And for example, this is like my day today. And like I'll just be in proof and I'll like plan out my day and I'll like click things. And then I can say like, okay, add an agenda for my startup ideas pod interview. And codexical do it.

And while it's doing it, I'll be like down here writing like, you know, a few. ideas on my mind, you know, Codex as an operating system, blah, blah, and it's just going to like go, it'll go do a bunch of research. It'll, it knows what we're building. It knows what ideas I may have. And that's, that's one of the really cool things about it is it's so, it has all the context on who you are and what you care about that it can bring to any app that you're using. Now I can see now it's already in here. It's, you know, looking at stuff. And I, It just, it makes a big difference because, yeah, the model being powerful is really important, but the model's only as powerful as the context you can give it. And this thing is just like connected to your whole computer and the whole internet. And so I'm just like constantly in here. Like any kind of SaaS app, I think the SaaSpocalypse is so dumb. You know, here we've already got like a nice little agenda. I think the SaaSpocalypse is so dumb because, um,

A, yeah, I'm like vibe coding this inbox app, but 99% of the world is going to want to use something that's maintained by someone else. Like, yes, you can one shot everything. But the, I think the hard, rare thing is moving to, can you build and maintain something over time? And that's still expensive and hard. And in general, I think of software as being, if you can bring your agent to software, software, it's really powerful. It's like giving it a structure to work inside of. For us, we have a pretty big consulting business now. And of course, the first thing we tried to do is vibe code our own CRM and have it be like a combination of agent and, you know, Google sheets and

stuff like that. And it's, you can kind of do it, but it becomes a mess really quickly. And we've just moved to a CRM vendor that has a CLI. And it's like, they've thought through all the little corner cases and they're going to continue doing that. and we get to actually do the work that we want to do instead of like vibe coding, you know, customer records and like thinking about all that kind of stuff. So, yeah, I'm very bullish on SaaS. Like, especially SaaS that's designed to be built inside of,

designed to be used inside of the codex in-app browser. Right. Yeah, I think, yes, you can build anything, but people will pay for maintenance. That's sort of like the insight. is that you know if this thing works I'm fine to pay for it so I think and then I think that like again like another aha moment I had with Codex was just like looking at this seeing like my SaaS like we don't really think about it as a SaaS on the right hand side but it is a SaaS and how it interacts with my threads back and forth back and forth and how you can like ping pong it just feels like I don't know about you but like you can literally it feels like you can spend 99% of your time in Codex or in

whatever super app that you're going to use, right? At this point. I definitely agree. I'm like kind of back and forth on whether the super app thing is going to work, but I absolutely... We're an operating system. Like we say super app,

but it's really an operating system because it's like this episode, like you're showing me ways how you operate your business and your life with Codex and 5, 6. you know, a super app, I don't know. Like that, it's just a cooler way of saying operating. Should we just make something?

Yeah, let's do it. Okay. So, okay, because one of the, and I've been playing around with this already, so there's probably some of it on my computer already, but I think this would be kind of fun. So what we're talking about, I think you framed it exactly right, which is maintenance is the thing that people pay for because you can one shot anything now.

And so I want to make a little SaaS that is designed to help people display that their app is being maintained. And there's already stuff like that on GitHub, for example, where you can kind of see like how many commits have happened over the last like, you know, period of time. But I think we need that for any SaaS app that you encounter on the internet to be like, someone is, maintaining this. And not only that, but whenever a bug is reported or a feature is requested, here's how much time it took to fix it or to add the feature. Because that's the like sign that there's someone who's actually working on it. And it's not just like a vibe cut at one shot. Do you think that would be fun to build? 100%. Let's see if we can do it. All right. Let's see if we can do it. All right. Let's see. All right. I want to build a little SaaS app called turnaround.

There may be some demos and stuff on this computer already, but I want you to just ignore them because I want to do it from scratch and see what else comes out of this. But the basic idea of turnaround is the value of SaaS is not in building the first version. It's in doing the maintenance. And we need a way to help people who are running SaaS apps display the maintenance that they're doing,

which is basically the turnaround time from when someone requests a bug fix and the bug is being fixed, or just overall the number of commits. You want to see that commits are happening all the time on this app. And I want a little, like, beautiful badge that gets displayed that you can put on your About page or something like that that validates that this app is being actively maintained and worked on. Sort of like what GitHub does, but it should look good.

It should look cool. It should look like sort of AI and Fiorit. futuristic and we should have a way where anyone can sign up for it. You can put the badge on your website, but our job is to be the people that are sort of validating on the back end, like how many issues in GitHub you're taking down, stuff like that. And it should work with any sort of data source. So if you use linear, you use Notion, whatever, can you use CEIDA and CE brainstorm to help me figure out how this should work? And the sound effect is from monologue, which is our speech to text app that we've made. It's operating on my other monitor so you can't see it,

but you can see the output and hear the sound. What should we talk about while that's running? I mean, from your just experience building with 5-6, you said it wasn't exactly fable-like. Yeah. Pretty close. When you say close, are we saying like 80%, 90%, like a fable's at 100%. just trying to get a sense of like where we're at. I think Fable's like an S tier, S plus tier model. Like it's so good that it's illegal. And this is like an A tier model, you know?

So you're not going to hack the NSA with 5-6, but, or like you're not going to like you're not going to like. You might. I mean, I'm not. You might not successfully hack the NSA. Like with Fable, I was, we were like literally the, our bug backlog was emptied out. You could just set it off and it was emptied out as long as you're willing to spend the money. And with five, six, it's not really like that. Like you have to do some thinking to fix bugs, for example.

Yeah. But it's close. So it's like 60, 70% is this other thing. It's because it's so, it's also so slow and it's so. expensive, that it's really only meant for essentially like people who are doing machine learning or are orchestrating like fleets of agents, which is just a skill that most people don't have yet. Cool. All right.

First product fork. What should the badge promise prospective customers, alive, responsive, or dependable? Hmm. I will say, by the way, dependable. I like that there's a recommended option. It's pretty good, right? Yeah, that's pretty good.

Like, you know, that was sort of a miss in prior models is like it just it would make, it would just, it wouldn't have a taste in terms of, I don't want to say the word taste because I, that you shouldn't use that word.

But it didn't have a point of view. An opinion, yeah. An opinion. Yeah. And I just like these as, and part of this is, I'm using this, our compound engineering plugin.

So part of this is the combat engineering plugin. But I just think that these are good options. Like 5, 6 just has good, I'm going to say it again, taste. And I like the different vectors that it's, is it alive, responsive, or dependable? I like alive. For it to be credible, what happens when activity stops? Yeah, state changes automatically. Actually, yeah, state changes automatically.

Let's say that. But it's not judgmental. It's like, it's just like one commit in the last 30 days or whatever we get to, you know, something like that. From a speed perspective, five, six, what do you think? I think it's great. It's so fast. And it's very to the point.

Like, it doesn't write too much. I think that I like to, because it has more, it has more concrete details. but I also don't like the idea of necessarily saying it's alive versus like dead versus it's not. Like it should just use the concrete details to tell you what's going on so you can see it. In a second, I'm just going to like set it off and see what it does. All right. I want you to make the best possible decisions and just use LFG to and a goal to just make this thing. And show me what it would look like for let's say Cora and.

monologue. So show me on a on a on a page. So what is LFG and what is goal? So LFG is again, this is our compound engineering plugin. It's a plugin by Kieran Klasen who runs Cora which is just he's like an insanely good AI engineer and he's just taking all of the stuff that he knows and put it into a plugin. And LFG it basically just loops through the whole cycle of plan like execute work, review the work, review the compound the learnings and then just keep going until it's until it's made and then goal is Codex's version of like give it like give the model a high level

long term goal that it just like keeps going until it's achieved like for example one of the things I'm doing I told you I was doing model training I'm training a model to do copy edits and this goal is for it's it's It's been going for four hours, and I just let it go. But four hours is honestly very short. Like, over the weekend, I had one or two that went for like 20 hours each. And so it's just a really nice thing to be able to say, here's where I want you to get to.

Here's verifiable criteria that would tell me that you are actually done with this. I'm going to go do something else. And, or theoretically, I'm going to go do something else. What I've actually found, I don't know if you have this, but I've actually found that I'm incredibly addicted to just like watching the stream, which I hate. But I just, I just am like that for whatever reason. So anyway.

This is another nice thing about 5.6 that's pretty new is it does this like design checkpoint. So it's really they're trying to make it better at design. And I think it's it's not perfect. Like it always wants. do warm paper backgrounds for some reason. I don't know why. So it's, it's like better, but it's not perfect. I give it like a B, you know, where previous models were like a C or D. So, yeah. Well, at least it asks, right? At least it asks. At least it asks. Yeah. At least it's thinking about warm paper. And I could be like, no, I want cool paper, you know. Yeah. Yeah. Yeah. I think in the past

it just, you know, it jumps to conclusions and then that's when you have, you know, the same looking website as everyone else. So I think what they're probably doing is they're giving you an opportunity to add more context before they continue. Yeah. So while this is going,

I think the, one of the things I wanted to say about SaaS and all that kind of stuff and building, I think there's a huge opportunity for Codex native SaaS apps. So think of any SaaS tool that you use. So like we made proof, which is document editing, but like there's email, there's CRMs, there's, you know, any of that stuff. Any software that you use every day would be better if it was built to be used inside of something like this, inside of something like Codex, where you can bring your agent to it and your agent has all the context on you, on who you are and what you do. And it's not, you're not designed. it so that it's a CLI and the agent just like you're just delegating it and the agent is in using the CLI without you. It's designed for you and the agent to be working on it together inside of Kodex. You want to be able to bring your agent to the software that you use and have you and the agent

collaborating on the same surface. And this is what programmers already know about the best way to build apps. Like the reason the internet browser is a thing is you want by when you were building an app, you want to be able to use the local app that you're going to be able to use the local app that you're you're making in the same place that your agent uses it. So the feedback loop is shorter. Same thing is true for any kind of knowledge work. And I think there's a massive opportunity for anyone that understands that to just like make apps that are built that way because most apps are not designed for that. And do you think that customers are going to be looking for these agent native apps? If they're smart. So I think it's, I think that there is a crew of early adopters that is starting to

figure it out. And it will take a while for it to be totally mainstream. But to me, that is the opportunity is to start establishing yourself as making an app that's Codex Native for this, for a particular category so that when it is really mainstream, you're like, you're the, you're the place people go. Like I would start trying to rank for that and, you know, having landing pages around using it inside of codex and all that kind of stuff because you know, having a lens into all these companies, I think a lot of the model companies and just general, like, big AI companies, like, see this as a trajectory that things are starting to go. And, yeah, it's going to be a big deal.

And one of the cool things about it is most SaaS companies are, they're like, now they're installing agents in their, in their products. So they have to pay token costs. In this world, you're just a SaaS provider. You're just hosting software. So there's no token costs. And so your margins are back to being a regular software business instead of being an AI business, which I think is great.

Yeah. I mean, it's also great for the people who want to take the non-venture-backed route. Totally. I think there's a lot of us who are kind of like, you know, hey, I'd love to build a business that makes $10 million a year and the cost are low and stuff like that. And I think a lot of people were looking at SaaS and these agent native SaaSes

and they're like, okay, wow, great, this company's making $80 million a year in revenue, but they're spending $60 million a year in tokens. And it's just like, you know, for some people that's interesting, but some others not. So I do agree that these codec specific or apps are probably going to do well. The only thing I'm thinking about is from a distribution perspective,

it's not similar to the mobile era when you had the App Store. I remember I built an app in 2013 and we were featured on the App Store and we were getting 25,000 downloads a day just from the features on the App Store. I think what would be really cool is if the Codexes and the Clods of the World start promoting these apps that are specific to making the experience better. I bet that they will. Like OpenAI has launched already like three or four different app stores, literally. Every year they have a new app store play because I think they realize that playbook works

really well. It's incredible to have an app store because then you have an ecosystem and you have people building an ecosystem and it's not just about stuff you can build. It's about the value you unlock for everyone else building on your platform. and I bet you within a year, the opening eyes and the Anthropics, the world will have app stores for apps that are built specifically to be used inside of these services. Maybe even cursor two. I don't have any insight on any of this.

It's just too good of a business opportunity. And it's just a logical thing if you grew up in the app era and saw how good the app store was to want to bring that to the agent era. All right. see warm paper background turn around let's go interesting your inbox again what are we looking at so this is its take on this is the thing is they've they have improved the design here but it's a certain kind of design that this sort of flat aesthetic i don't think is quite right for this but anyway so what we're looking at is a mocked up version of the embeds that we were talking about,

where you can see, okay, on the core about page, 26 commits, last 30 days, and you can see, like, how active it is.

I don't know if commits is really the right word. And especially if we're going to call it turnaround, that's kind of an interesting one. But it's essentially like a, it's a status page for the vibe code era to show you, okay,

yeah, there's a lot of activity happening in this. in this project or not. And I don't quite like the initial visual implementation, but you can kind of see what it's getting at. Totally. Yeah, I think it's like 75% of the way there. Yeah.

It's enough that I can kind of see it. And I might be able to, like, I could probably publish a landing page that's like sort of like this. But to be honest with you, at this point, I would probably, I would go to Claude for the actual design and then poured it back in here because I still think that Claude has a better sense, especially Fable RIP,

but even 4-8 would be better at this. And I think for a product like this, being able to see it at a glance and understand what it is is like the most important thing. And I still think that Opus and just Claude in general is ahead on that one. And while we're waiting for this, like, what are your thoughts on, you know, using, for example, cursor or codex and having local models as well play a role?

You know, there's this whole new wave to local models. Are you like a, you know, token maxi where you're just like, I use OpenAI and I use Anthropic and that's it or, you know, how do you think about it? I have a feeling that open source models are going to be very important to the way that I work. Currently, they are not. One is I just as a person and as like what we cover, it's like we're very, I just want to be at the frontier. Like I just want to be like fable maxing all the time. But we're starting to get to a point where even for me,

model advances in raw intelligence are to some degree hard to consume. You know, like I can't use Fable for everything. There's not, I don't have a big enough problem to use Fable for. I do use it, but not for everything. And so I think as we start to get toward that ceiling where I can't consume extra advances in model power, then speed and cost and efficiency is going to be more important. and at that point I will be interested in incorporating more open source models into my workflow. And like I said, I've been doing some model fine tuning.

In that case, you have to use open source models because none of the major model companies, or at least open and anthropic, don't really do fine tuning anymore. And I think that's a huge area of potential opportunity because there's still, you know, for us, These models can't do copy edits. They can't do copy edits like a copy editor can. And it's weird because copy editing shouldn't be that hard. At least copy editing to like 70% or something like that. And so for us, we have all this internal data of we've made tens of thousands, if not more, hundreds of thousands of copy edits over the last five or six years.

We should be able to turn that into a trained model and then sell that. And I think that there's a lot of organizations that have that same underlying data source that they can turn into like a product or capability. All right. What do we get here? Neutral badge, core monologue previews, blah, blah, blah. Okay, but like, okay, but how would it be implemented? Like, how would I install this so that it would be updated? See if it's trying to get around, get around the hard problem.

Let's see. Open to read me. I see. This version validates the badge, public record, visual identity, and core measurement language accounts, authentication, persistence, billing, blah, blah, GitHub ingestion, and generated embed code. Okay. I probably should have spent a little bit more time pushing it to get the best out of it. But we're, I would say we're 70% there. I need a little bit more cooking on the exact design language. And then we need an implementation to, um, to actually hook it into your GitHub or your linear. Yeah. And like, you know, I think people would be interested in knowing, like, how does Dan Shipper take a vibe coded project from 70% to 100% with codex and 5.6? Good question. Well, what I just said is do it. Because, you know, I was like, here's what I need to do.

And I was like, yeah, just do the full V1, man. I think what's interesting about me, I have this, I make this distinction between two different types of people in the AI age or two different types of builders between pirates and architects. So a pirate is like, I'm just going to get it to 70%. I'm just going to explore the field of possibilities and build something that just works enough for me to tell is this valuable. and I think an architect is really good at being like, this thing is valuable, but it's not thought through well. How can I make it into a well-oiled machine that really works well? And so what I do is because I know that I'm like this.

I'm like, oh, I have this idea. Like, I'm going to go build stuff. I'm going to go train this model over the weekend or I'm going to go, like, make this little app or whatever. Because I know that I'm like that, I pair myself with an architect who, who just, it's usually, it's always now someone who works internally, but someone who is good at that and likes to get some energy from feeding off me being like, oh, I've got this like really exciting new thing, but is good at being like, taking some pleasure in taking that 70% formed thing and turning it into something that's really polished. And I think that's a new and interesting divide where before we were like, I need a technical, co-founder. And that's not really it anymore because everyone can code. I think it's about your

set of sensitivities and desire to make something new and go fast versus make something polished and really high quality. And both are really, really important. And so I think I think about pairing myself up with someone who can do that other part. Fair enough. While this is still working, I know you showed the email example. What are other, you know, how else does Dan Shipper use Codex live in Codex? How else do I use Codex? Well, we've got emails. We've got, you know, I have these different pulses.

So a pulse is just, it runs every day or it runs every day or a couple times a day and gathers all the information, puts them into cards. I also I have this thing that I built called Mailroom which is it basically gives my codex an email address

that rides on top of my email so you know the plus format in emails or it's like you know you can do Greg plus codex at gmail.com so it basically uses the plus format to register itself

in email inside of your email so I have Dan plus codex and there's like a random string so you can't just email it. And then I can give that. And then what it does is I have this router thread that checks that email inbox regularly every like five or 15 minutes or so. And then I can give that email out. For example, we have an internal agent in our Slack.

I can give the agent that email. So when someone asks me to do something because I'm generally not as good at like opsy types type thing type things, they know to ask the Slack agent and the Slack agent knows to email my codex instead of emailing me. And I see what it's doing, but it just takes care of it for me. So, you know, just having your codex hooked up to to an email address, whether it's using Mailroom or something else, having it hooked up to an email address, I think is super, super powerful and underrated.

And generally like this router thread, like learning how, okay, heartbeat, how heartbeats work, where the thread gets activated every once in a while or a, or. router like how router threads work where an email comes into this thread because this is checking my email all the time and then this is routing it to okay does it go to my inbox does it go to my company pulse does it go to whatever um so that's that's another i think really good pattern for using codex well i wish there was a way i can just copy dan chipper's like way that he uses codex and just like duplicate it versus like i know i can go and throw the transcript of this video into codex and it would probably figure it out but I wish there was an easier way.

That's a good idea, honestly. Let's make it. New codex thread. No, I really love that. And I think generally like this 10 thing that I showed you is part of an attempt to do that. But yeah, there's all these other, there's all these other little things of like routers and, you know, and heartbeats and all that kind of stuff. Which I could definitely, definitely package up. So I think this is this is probably not going to turn into like a big

Holy shit thing. Because the thing that it's building now is it's just the back end to this, you know, which if it works great. But like how are we going to even show that really is the question. So, you know. So we can move. We can move on. Yeah.

Yeah. Is there anything else? Like this is. Yeah. Is there anything else that you want to show that people need to know about Codex and 5-6? Like if people, you know, people are listening to this and they're like, yeah, I want to run my business or my personal life on Codex. Like what are the must to do things that they need to get started? Well, I just think that people, they think it's Codex, so it's for coding and it's not.

and they're like, what I already use chat GPT and it's like, this is totally different. It's not the same thing at all. And so the first step is just download it. Just download it. Second step is give it access to your computer. Third step is profit. No, one of the things that you can do,

one of the things I love is just be like, it's just be like, can you propose for me things you can do for me based on how I use my computer? Like one of the interesting things about Codex is it has this thing called Chronicle, which is it automatically takes screenshots of your computer and locally turns it into

locally turns it into a feed that gives it context on who you are and what you're doing. So over time, it's like building up this, like, it's building up this feed of, okay, Dan's working on, he's working in Slack, he's talking to Brandon about this thing, or he's on with Greg and they're talking about, you know, topics for his episode or whatever. And that improves its responses. And I think that there's something really powerful about you have an agent. It's on your computer.

It is hooked up to everything that you're hooked up to. And it's also, I mean, I think people can find it creepy that it's like taking screenshots or whatever. You can turn this on and off. I think it's chronicle is a research preview, so it's optional. But I have it on because it's all local. And generally, I would prefer it to have more context on me. So the responses can be better.

But yeah. And they're also just, they're pushing stuff to it all the time. like they just launched this thing that I've actually never used so I can't I can't speak to it personally but it looks really cool which is it's called the review and record plugin something like that and the way it works is you can just you just start it by saying can you just watch me do this and it will record your screen as you do a task and then turn that automatically into a skill to do it in the future and I think stuff like that. that is sick. So yeah, I just think about it as any kind of repetitive task, absolutely do inside

a codex. And whenever I'm, whenever I'm doing work on my computer and not in it, I'm like, how could I do it in here? Because there's a mindset shift from doing the work yourself and managing the system that does the work for you. And this is the same shift that, like, managers go through or honestly founders go through when they're when they hire employees like all that kind of stuff and it's a specific skill to work well in this era is not for every piece of work that you do but for a certain amount of work that you do switching your mindset to be it's actually not about any individual email it's about the system that does my email and that's my job cool so basically from uh you know if someone's listening to this

wants to start using Codex, envious of Dan Schiffer's set up, don't blame you. Basically, what you should do, download Codex, give it context about who you are, what you do on a day-to-day basis, ask it to do the work of setting some of the stuff up for you. I'd never heard of that, like, sort of watch me do something plug-in. Yeah. So that's really interesting. I think like we all record and replay. Okay, record and replay.

We'll include in the show notes in the description. That is really interesting because that's how I think about optimizing my life on, you know, codexes and cloud code, which is I have a set of, you know, SOPs standard operating procedures. Yeah. where I basically just like put those into these these these apps and I have it basically you know if this happens sort of respond this way or do this thing and I think that's like the key and the whole unlock for me for a lot of these operating systems AI operating systems is just have it do boring tasks in a high degree. And if you can do that, that's, that's wonderful. I agree. And I also would, I also say, don't look at my setup or your setup and be like, oh, I've got to go build that whole thing. You'll just end up spending a bunch of time making a setup that doesn't work.

What you should do is start with one simple thing that makes your life better and that you're interested in. And just do that and then build it up over time. I'm like, I didn't start out like this. I just started out with, here's a thing. Here's a problem I have. Let me see if I can solve it. And I solved it. And then I sort of built from there.

And everyone's system is going to look a little different. And if you're someone who's been around software for a long time, you'll recognize a lot of this from, you know, the way people were using notion five years ago or Rome or anything like that, where there's always this temptation with productivity software to work to work more on the system than the work and make this gigantic, complex thing. And what's generally better is to, yeah, maybe you end up having a complex system over time, but just to start with something simple and build the things that you need to, like, do the main thing that you want to do instead of making the side thing the main thing. A hundred percent. Yeah. I mean, we are the biggest nerds, me and you. So, you know, we are obviously pushing things to the extreme. And because of that, it's fun. Like people like listening to us, I think, sometimes. because they can see like the breadth of what we can do. But I think that it could also be super overwhelming for people because they look at it and they're like, oh my God, I'm never going to be able to get like all those things set up.

And the truth is what might even work for us might not even work for you, right? Like you might find ways to automate your life and business in a completely different way than we do. And it and it's three things or four things and it's good enough, you know? Totally. Totally. And I would, and I think there's also this thing that happens where you see something like this and you're like, you have this overwhelming fomo. And I think that's actually generally never the right way to get into new technology. It's much better to get into something like a new AI tool because you're genuinely curious.

And you have a, you have something that you genuinely want from it, not like I just, I'm afraid of being left. behind. Yeah. And so I highly recommend just finding something that you're actually excited about to use codex for rather than trying to use it because you're like, I don't, I don't want to be left behind and I don't want to miss out. Dan Shipper, you've been generous with your time, your screen chair, everything. You open the kimono. I appreciate that about you. I'll include links for where to follow Dan and every. in the his publication in the show notes and descriptions highly recommend it and dan anything you want to leave people with nope thank you for having me this is great always a pleasure and i'll see you next time