24:21Greg Isenberg · Talking Head
Karpathy's autoresearch broke the internet
A 24-minute solo breakdown of the AI experiment-loop tool that went viral — and 10 businesses you can build on top of it.
March 11thThe argument in one line.
The era of separate tools for coding, documents, research, and browser automation is collapsing into a single super-app interface, and whoever masters it now has a structural productivity advantage before the rest of the market catches up.
Read if. Skip if.
READ IF YOU ARE…
- A founder or solo creator juggling vibe coding, lead magnets, research, and document creation across too many tools.
- A Claude Code or Cursor power user wondering whether Codex is worth switching to or running alongside your current stack.
- Someone who wants to see how browser use, computer use, and agent automations actually work in practice today, not in theory.
- A knowledge worker who wants to set up recurring automations and understands skills/plugins/MCPs only as marketing terms.
SKIP IF…
- You want a rigorous technical benchmark comparison of GPT 5.5 vs Claude 4 vs Gemini on specific tasks.
- You have no interest in vibe coding or document creation; the super-app thesis only matters if you do both.
The full version, fast.
Riley Brown argues Codex is the correct interface for AI agents because it unifies what every other platform splits: vibe coding, knowledge work, browser use, computer use, and scheduled automations inside one window on GPT 5.5. Skills are user-built instruction folders; plugins are OpenAI-approved integrations like Slack, Notion, Remotion, and Canva. The sleeper insight is that you can open the Codex terminal, type claude, and run Claude Code on your Anthropic subscription inside Codex, stacking both models where each excels. They close with a practical day-one starter kit: build a small game and let browser use play it, run deep research into a spreadsheet then a doc and a deck, and pick your most annoying daily workflow to convert into a recurring automation.
Free for members
Chat with this breakdown — free.
Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.
Create a free account →Who's talking.
00:00hostGreg Isenberg
01:07guestRiley Brown
Where the time goes.
00:00 – 03:22
01 · Intro and skeptic setup
Greg frames himself as a Codex non-user; Riley previews GPT 5.5, browser use, skills, one interface.
03:23 – 06:45
02 · What is Codex
Project/folder/chat structure demo. All major agent interfaces converging on the same GUI pattern.
06:46 – 10:12
03 · GUI beats the terminal for most users
Terminal era right for early adopters; business users need clean GUI. Codex combines Claude Code and Cowork in one product.
10:13 – 12:47
04 · One platform for code and knowledge work
Codex creates apps, spreadsheets, docs, and decks in one window. Critique of Claude splitting Cowork and Claude Code.
12:48 – 14:20
05 · Atlas browser inside Codex
OpenAI pivoted its standalone Atlas browser into Codex. Persistent login and full web browser coming.
14:21 – 19:27
06 · Remotion and motion graphics workflows
Built-in Remotion plugin; brand asset pipeline; launch videos with 800K+ views generated from code.
19:28 – 22:25
07 · Computer use and Chronicle
Computer use is now faster than Manus. Chronicle watches your screen for passive context.
22:26 – 31:56
08 · Plugins, skills, and automations
Plugins vs skills explained. Live demo: creates Friday recurring negative podcast report automation.
31:57 – 38:42
09 · Evals and example-driven output
AI struggles with subjective quality. Fix is a knowledge base of good reference examples.
38:43 – 40:43
10 · Hard questions: who Codex is actually for
Content creators, founders, knowledge workers doing both docs and code.
40:44 – 43:19
11 · Browser use plays itself in chess
Codex builds a chess game then uses the in-app browser to play itself to checkmate. Speed vs Manus comparison.
43:20 – 45:57
12 · Running Claude Code inside Codex
cmd+j opens terminal; type claude. Stack both subscriptions, use each model where it excels.
45:58 – 48:49
13 · GPT 5.5 cost and effort settings
Approximately 2x GPT 5.4 via API. Effort settings and when throttling pays off.
48:50 – 54:08
14 · GPT Images 2.0 and the video model landscape
GPT Images 2.0 built into Codex. Sora delisted from App Store. Seeddance, Cling, Veo landscape.
54:09 – 57:08
15 · Why most people feel overwhelmed by AI tools
Overwhelm is structural. Tinkering for 30 minutes beats optimizing for immediate productivity.
57:09 – 1:04:40
16 · Day-one projects and closing thoughts
Starter pack: build a game with browser use, research to spreadsheet to doc to deck, 3D simulation, automate your most annoying task.
Lines worth screenshotting.
- Codex, Cursor, and the Claude Code desktop app have all independently converged on the same GUI: chats left, agent center, output right.
- Plugins are OpenAI-approved integrations requiring a submission process; skills are folders with a SKILL.md file you create yourself in seconds.
- You can run Claude Code inside the Codex terminal using your existing Anthropic subscription, stacking both models without paying twice.
- GPT 5.5 costs roughly twice GPT 5.4 via the API, but it is more token-efficient so the per-task cost gap is smaller than it looks.
- Chronicle watches your screen passively to give the agent context, so you stop having to re-explain what you were working on every session.
- The chess demo is the clearest illustration: Codex built the app and then used browser use to play it to checkmate in a single prompt.
- The best way to improve agent output quality is not evals but examples: one good reference document transforms output; five make it consistent.
- Browser use has crossed from dial-up to broadband speed; the estimate is three months before it matches a human on any browser task.
- Remotion inside Codex lets you at-mention the plugin, describe a motion graphic scene, and get a render without writing a line of code yourself.
- The value of recorded screen workflows is about to spike: future Codex versions will accept uploaded videos to learn and replicate your process.
- Notion agents inside Notion make less sense than Codex agents driving Notion: use the interface you like, run the intelligence elsewhere.
- Effort settings matter; running extra high on a simple change often causes unintended scope creep.
- The tinkerers who are not afraid of looking dumb are the ones who succeed with new AI tools, not the productivity optimizers.
- Every app that can exist will exist: AI one-shotting full mobile apps in Swift has made that outcome feel inevitable.
One interface, every output, one agent.
WHAT TO LEARN
The productivity gain from AI agents scales with how few interfaces you switch between, and the race to own that single window is the defining platform battle of 2026.
02What is Codex
- Codex, Cursor, and the Claude Code desktop app have all independently converged on the same GUI: chats left, agent center, output right - that consensus is a signal, not a coincidence.
04One platform for code and knowledge work
- Skills and plugins serve different purposes: skills are folders with a SKILL.md file you build yourself in minutes; plugins are OpenAI-approved integrations that require a submission process.
- You can run Claude Code inside the Codex terminal using your existing Anthropic subscription, letting you use each model where it excels without paying for both at API rates.
08Plugins, skills, and automations
- The highest-leverage productivity habit is collecting good examples of finished work: one strong reference document transforms agent output quality, and five make it consistent across runs.
- Recurring automations follow a simple pattern: do the task once manually inside the agent, then tell it to repeat on a schedule - the agent writes the automation from the example, not a specification.
11Browser use plays itself in chess
- Browser use has crossed a functional speed threshold - the chess demo illustrates it better than any explanation: build the app, play the app, win the game, in one prompt.
13GPT 5.5 cost and effort settings
- GPT 5.5 costs roughly twice GPT 5.4 via the API, but the correct unit is cost-per-completed-task, not cost-per-token; a model that gets it right in one pass can be cheaper than a cheaper model that takes three.
15Why most people feel overwhelmed
- The way to start with any new AI tool is to spend 30 minutes doing something fun with it before trying to extract productivity; your brain needs to feel the possibility space before mapping useful workflows onto it.
- Chronicle screen-watching memory is not a gimmick; passive context that eliminates re-explaining your situation each session is a compounding time return, privacy tradeoffs aside.
16Day-one projects and closing thoughts
- The value of recorded screen workflows is about to increase: future models that accept uploaded videos to learn and replicate your process will reward people who have been documenting their work now.
Terms worth knowing.
- Codex
- OpenAI agent interface included in ChatGPT subscriptions. Unifies coding, document creation, browser use, computer use, and automations in one app running on GPT 5.5.
- Skills (Codex)
- User-created instruction sets stored as a SKILL.md file inside a folder. They give the agent reusable, personalized behavior for repetitive tasks.
- Plugins (Codex)
- Official third-party integrations (Slack, Notion, Remotion, Canva) approved through OpenAI, distinct from user-built skills.
- Chronicle
- A Codex memory layer that watches your screen to give the agent passive context, reducing the need to re-explain your situation each session.
- Atlas
- OpenAI standalone browser project now folded into Codex as the right-pane browser. Roadmap includes persistent login and a fully capable in-app web browser.
- Remotion
- A library that turns JavaScript/React code into rendered videos. The Codex plugin lets you prompt a motion graphic scene and get a video without writing code.
- Browser use
- An agent capability where the AI controls a web browser, clicking links and filling forms. The chess demo shows it now runs at near-human speed.
- Computer use
- An agent capability where the AI controls the operating system directly, moving the mouse and interacting with apps like Canva or CapCut.
- GPT 5.5
- OpenAI flagship model inside Codex. Roughly twice the cost of GPT 5.4 via the API but designed to complete tasks with fewer total tokens.
- Vibe coding
- Building functional apps through natural language prompts rather than writing code directly. Riley estimates 95% of desired coding tasks are now approachable this way.
Things they pointed at.
19:28productChronicle (Codex feature)
48:50productGPT Images 2.0
Lines you could clip.
10:35
“Vibe coding has gotten so easy that 95% of the things you want to code are as easy as creating a presentation.”
35:55
“Give an AI one good example and it is amazing. Give it five and it will do a great job every time.”
46:20
“It is not going to be how token efficient is it - it is going to be how much money and how much time does it cost to do a specific task.”
1:02:36
“The tinkerers who are not afraid of looking dumb win.”
Where the conversation goes.
00:00 – 12:47denseCodex overview and interface
14:21 – 19:27denseRemotion and motion graphics
19:28 – 38:42denseAutomation, plugins, and skills
40:44 – 45:57denseBrowser use and computer use demos
45:58 – 48:49steadyModel economics and effort settings
48:50 – 54:08steadyVideo models and AI images
54:09 – 1:04:40steadyGetting started and closing philosophy
Word for word.
Read-along
Don't just watch it. Burn it in.
See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.
analogy
00:00Some of my smartest friends are saying OpenAI's Codex is the super app for AI. They're saying you pair that with GPT 5.5 images two point o and use Codex's interface, and you are going to be unstoppable.
00:14So I called my friend Riley Brown to convince me that I should be using Codex with all these models. And in this episode, we go through everything.
00:23How to use it from a to z. How to create skills. How to connect it to Notion.
00:29How to use Remotion to create beautiful videos. If you've been meaning to get good at codec, but you haven't had a second, well, this is your episode.
00:39You're in for a treat. And if you wanna show some love to me and Riley, give this a like and comment, and I'll see you in there.
00:54We are blessed to have Riley Brown back on the pod. Riley, by the end of this episode, what are people gonna get out of this? People are gonna learn how to use the best interface to use AI agents, in my opinion.
01:07I think Codecs by OpenAI,
01:09and that means if you have a ChatGPT subscription, you have access to Codecs, which I think is the most powerful way to use AI agents. And we're gonna learn the platform, and we're gonna talk about GPT 5.5 which was released yesterday as of filming this.
01:24I don't know when this episode will be out. We'll talk a little bit about browser use. And, you know, I've been a little skeptical about AI controlling browsers.
01:33I think it's kind of slow and a little boring. This is the first time that I see it.
01:37I'm like, oh, it's actually starting to be faster and I could definitely see by the end of the year, these browser agents are gonna be as fast as humans. So we're gonna talk about that.
01:47We're gonna talk about computer use. We're gonna talk about just doing all of your knowledge work and coding work inside one single platform, which is Codex.
01:56How does that sound?
01:58This well, I I just have to be honest with you. I gotta say something.
02:02I am not on Codex today. In fact, I have never downloaded Codex. I it's just I'm not in that world.
02:11Okay? And this episode for me is a firsthand, basically, hacks, tips and tricks.
02:19By the end of this episode, I wanna be converted. I wanna be converted to Codex in that ecosystem. I hope so, but I might be wrong.
02:27I might by the end of this episode, I might be like, you know what? I'm just gonna stick with my own stack and, you know, this is
02:35there's just a lot of smoke here. So let's see. No.
02:38For sure. And you know what? And and I wanna preface this by saying like, I don't hate on anyone for using any stack.
02:44I think it's kind of dumb to do that. I think you have you should pick a stack and you should stick with it. Um, I think moving from hot tool to hot tool is actually not the right strategy.
02:54If you're using Claude code, uh, inside cursor, right, if you use cursor for all your knowledge work and that works for you, great. Just keep doing that if you want.
03:01I'm kind of permanently switching to codecs just because, you know, I work with seven engineers and all of them have switched to codecs and we agree that it's pretty amazing and you can use Claude code inside of it which is another bonus. But if you don't mind, I just kinda wanna hop into kind of an Excalidraw, kind of do a little precursor to Codex if that's cool with you.
03:22Yeah. Okay. So, yeah.
03:26So I like to start with the basics. I've been really trying to get people, uh, to understand the difference between ChatGPT and codecs.
03:35Um, and so a good way to think about codecs is it is a state of the art AI agent on your computer, which is the the Codex model or the GPT 5.5 model in a nice interface that allows you to build an app, create any type of document, control your computer, and create automations.
03:54You can see that. Right? This is the Codex interface.
03:58It looks a lot like ChatGPT. Right? This is a new chat on Codex and, um, what I like to do whenever I create a new, uh, like whenever I go to Codex and let's say I'm working on a new maybe I'm working on the startup ideas podcast landing page and then I'm also doing some market research.
04:18So we can actually create a new project and we can actually start from an existing folder and let's just call this folder, um, Greg or let's call it startup ideas podcast.
04:29And we can just create a new folder and this folder will be over here on the side.
04:35Can you see this? Maybe I'll zoom in a little bit. Mhmm.
04:38Um, and anytime I hit new chat, this chat will show up in here.
04:43As you can see here, I have all my threads over here on the side and they're all kind of organized. Notice there wasn't anything in this one and you can very easily just remove these from the side.
04:52So it's just like you have your folder and your chats within each folder which is just a project. And so like research startup ideas podcast, look at his videos.
05:08And so I have a skill which is YouTube researcher and this allows me to immediately pull transcripts from YouTube channels. So I can say like take the transcripts from his last 10 videos and tell me only what he's doing wrong.
05:29Be negative, make a report.
05:33And so then you can fire this off and what I like is it's very tailored to multitasking. So I can press command n and this interface is a little similar to Manus if you've ever used Manus before.
05:46It's very easy to see which what your agents are doing. Right? If it's done, you'll see a blue dot.
05:52As you can see here, these two are done. These are kind of like unread chat.
05:56So like it means it's done and I haven't clicked on it yet. While it's working, it kind of spins around. And so like, what is the startup ideas podcast?
06:08And so you could see here it kind of just organizes chats into threads. And what we're seeing is this is kind of the dominant interface to interact with AI agents.
06:19You can see here this is the new Claude code desktop app right here. You can see their code feature.
06:25It's very similar. You have these folders with chats underneath it.
06:30And if you've seen the new cursor interface, it's very similar. So all of these companies are deciding that this is kind of the correct interface to interact with AI agents. It just so happens that I think Codex is the best one.
06:41So let's go back to to Arc. And so the way that I see it is like in 2025, that was the year of the two e.
06:50Right? We had we had this type of interface with Cloud Code and it's kind of a it's bittersweet because I missed these early days of using Claude I loved the terminal.
07:00It was really fun and I think back to the early days when you and and a few others were talking about Vibe marketing. And I think there was so I think it was super directionally correct using AI agents to do a lot of marketing tasks. I just think I'm curious to hear what your observation was.
07:18Is this just wasn't a great interface for a lot of the people who wanted to get the benefits from it, but they didn't wanna open a terminal or create skills like in these files. I think people in business just want an easier interface, uh, to do all of these agentic workflows.
07:36And so what all these companies are deciding on is that the GUI is better. So we're moving from a terminal interface to a more clean simple interface.
07:47You have your chats on the left, your agent in the middle and then whatever the agent is working on on the right. Another way that I like to think about this is ClaudeCode or this codex is like ClaudeCode and co work in a single product but it's even better than that.
08:04And the reason why I like it more than Claude Desktop is Claude made a decision to split up CoWork and Claude Code. I would definitely try Claude more if they didn't do this.
08:16I do not like them just like they decided that people who are in business are gonna use one product, people who wanna code are gonna use this other product. They have different limitations.
08:27Right? You can't just ask co work to build an app. You you have to go to Claude Code to do that.
08:33Claude Cowork has different sets of permissions than Claude code. And you know me, I'm super hyped on vibe coding. I think vibe coding has gotten so easy that like 95% of the things that you would wanna code, it's as easy as creating a presentation.
08:49So I think and all the all the PowerPoint doc sorry if I'm kind of jumping around here, but within the, um, Codex app, right, Codex app is I can create this this app right here.
09:03So this is an app. This is a I posted this on Twitter yesterday. This is in one prompt.
09:08This is like a train simulator and it's super good at physics. And this is me just testing the model having fun and I even added a crash counter so these trains can crash into each other and it's presented by Allstate.
09:20But the point is is in the same interface, you can create an application and you can also create spreadsheets.
09:29As you can see here, it can create charts, spreadsheets. You can also create word docs. You can edit and export these word docs and you can create PowerPoint presentations and you can export them with different apps.
09:42So you can export this to Canva and this will just open it up directly in Canva so I can make further edits and they're gonna add more exporting features as time goes on. Because me as a startup founder, I'm constantly making all types of docs and I'm making a lot of landing pages, lead magnets. I want to do it all in one interface.
10:00And so that's kind of the main reasons that I use codecs. Any thoughts so far?
10:07A million thoughts, but the biggest thought I have is what you're basically saying is this codex is the fastest way to do the most amount of things, basically.
10:19Yes. It is. And it it it got all the primitives right.
10:22And okay. Actually, we can dive into some more of the the reasons that like, these are why I like Codecs over certain tools.
10:31There's a lot of reasons I like it that these things are also in Cursor and are in the Claw desktop app.
10:39But here are the things that only Codex does or Codex does better than all of them. Right? It is the only interface that does vibe coding and knowledge work in one platform.
10:49If you go to Cursor and ask for a doc, you know, it'll give you it can like create HTML file and run it in the browser, but it can't just create a doc and let you view it like a Claude artifact in one interface. You can do this on Claude desktop app, but again, you have to go to this Claude co work feature.
11:05I'm not a fan of co work at all,
11:08Which may be a narrative violation on your channel. I don't know if you've been talking about Claude Co work, but that's okay. Haven't.
11:14I haven't, but I'm intrigued with Claude Co work. Personally, I I, you know, spend most of my time in Claude Code, but I was thinking of doing a full on episode on like CoWork because it's one of one of the questions I get asked the most, which is should I be using CoWork
11:32and how how to best use it? But don't don't wouldn't you wish that Claude Code could just do what CoWork could do from the same interface? Yes.
11:42Yeah. And so to me, I don't see any good reason why you wouldn't allow Claude Code to do the stuff that CoWork could do. And so that that's just my beef with Claude Cowork and that's why I've been annoyed by it and I haven't made any videos on it.
11:55It's because every time I try and use it, I run into some sort of like limitation cause the way that they set up the the environments where the agents can do stuff, there's way more restrictions on co work which makes it super annoying to use in my opinion.
12:09Anyway, um, I think codex models are better at really complex tasks And we actually we know this for sure. Uh, we've tested this extensively as a team.
12:18You know, we're highly incentivized to, uh, write the best code and write it fastest for, uh, in the quickest amount of time and Codex just does a better job with infrastructure with really hard tasks.
12:31I've one shotted the other day I one shotted an app like Replit, a vibe coding tool that spun up sandboxes and you could vibe code web apps on your phone in one shot. It took an hour and twenty minutes to generate the code and this was on 5.4.
12:46It's pretty impressive. So if you remember last year, OpenAI started working on Atlas. I thought it was kind of I was just like, damn, they're kind of losing focus.
12:56They're they're building this Atlas feature. You know, it's a standalone browser. How many people are gonna use it?
13:02Well, recently they had like this big red alert at their company and they decided to kind of push all of their efforts into one single app which was Codex. And now what they're doing is they're just putting Atlas inside.
13:15They're basically putting Atlas inside like, this is the Atlas browser and I'm I know this by interacting with people at OpenAI.
13:25This is gonna become a full web browser. You're So gonna be able to log in, it'll remember your login info and so instead of having like a web browser with all of your tabs open and you have to decide what task you need to use, instead you'll start a chat with an AI and the browser will be there right on the right and you're you'll you'll have different windows open for the specific task.
13:47And I think that's just a better way to do knowledge work, know. Um, and you can just open up tabs directly in the app that you're creating, whatever it is that you wanna create, and you'll be able to open up Notion and you can download the Notion plugin.
13:59And so you can have your AI edit Notion and you'll have Notion open directly in the app, um, in the web browser, which I find to be pretty cool. And so that's another thing.
14:10They also have a built in Remotion plugin and because their web browser is the best, you know, I created this video the other day. Oh, boy. I've been doing a lot on here.
14:21And Remotion for those people who don't know is what?
14:25So Remotion, and by the way, in, uh, three hours, I'll be launching a video on how to use codecs for Remotion. Remotion turns code into videos.
14:36So you can create motion graphic videos with code. Well, guess what? Uh, lucky lucky for you, AI will write all that code.
14:44So you can just create, uh, you can just type out what motion graphic scene you want and it will create it.
14:52And Claude, as many people in your audience know, Claude has went on this massive run of of launches every single day.
15:01And
15:02and by the way, it's reconnecting. I think Codex is getting a lot of load right now. Like, there's just a lot of people using it.
15:08Because you're talking about it. You know? Yeah.
15:10You're about you're out there saying, you know, it's a super app. It's the best. You it's where you should be spending your time, you wanna bet on OpenAI and then all of a sudden it's reconnecting.
15:19Yeah, dude. I mean, what can I say? Well, I'll I'll try and be quiet before we shoot our next video.
15:26I'll just pin this. Ideally, it'll just work in just a second. We don't need to show it for now.
15:31But the point is you can generate really high quality motion graphic videos and Anthropic did this when they first started doing their product launches. They were just launching them with Remotion videos.
15:43And it's really good for software products where you like have something happening on a user interface. It can generate the user interface, it can generate the motion. And the thing that's really cool about Codecs is you can just search the Remotion plugin and once you enable the Remotion plugin, any chat that you use, you can say at Remotion.
16:04And you can say at Remotion, please create a video And then I created another skill which is is called Internet Image Puller.
16:15It doesn't just pull images, it pulls all of the assets for any given company from the Internet. So it might work for ten minutes.
16:22It'll pull all of a brand's assets, put it in an HTML file and then Remotion or Codecs can have all of that information for Remotion.
16:32So it can use your logo, it can use your colors, it can use your fonts in the video. You don't have to like manually tell it what to do. It'll just pull all of that information.
16:40And so that's a really fun way and, um, this is how we do a lot of our launch videos and some have gotten over a million views. Um, so this is a really useful thing.
16:49It was just really annoying to use with all of the other tools. Codex is the only one where you can just at Remotion and it opens directly in the app.
16:59Yeah. And, you know, for for people who aren't super familiar with Remotion, it's not just that it, you know, takes concepts and turns turns the videos into code or or, you know, creates videos that are code.
17:15These videos are so high quality. It is actually insane. Like, actually.
17:21Like, I've I know multiple people who've gone from zero to a 100,000 Instagram followers by doing remotion videos.
17:31Now they're high quality remotion videos and they go back and forth and back and forth. I'm not saying you one prompt it and you get the best possible,
17:38you know, videos, but these are is that remotion right here? Yeah. So this is seven seven like almost 800,000 views.
17:44This is all Remotion. You can't hear it, but like you can create motion graphic videos. Yeah.
17:51And it's really easy to just like create pretty simple videos. And I think when you're doing a launch video, if it's a good idea, should try and keep it as simple as possible, never have multiple things happening at once.
18:03Oh, k. It just popped up.
18:06It's it's testing if it's running but like this is what would run on the side of your screen and it will in just a second, but it literally creates this like cap cut like timeline. And so this is and so these are all of your compositions.
18:21And so here we have this demo that I made yesterday and this was in one shot. And the reason why I was able to generate this in one shot is I actually have this thing called brand assets.
18:37This contains all of the assets that, uh, I might want to use and so once you've generated a video with all of your brand assets, you can just reference that to your AI and you could say, hey, please use this background or use this component or use this logo and you notice here I just labeled all of these logos here.
18:56And so I can always say like, please look at the brand assets, use the x logo, the YouTube logo, the TikTok logo, the cursor logo and put it in this video in this scene.
19:06And so if you just get everything that you might want to use in here, it's easy to tell your AI to to use it later if that makes sense. Anyway, you can create videos, uh, and you can open it right here in the browser as you can see.
19:20That took a little bit because Codex is running a little slow, but this is kind of like an everything app which is which is pretty cool.
19:29And then to to, uh, to finalize why I use it over other ones is the computer use is better. It is faster than any computer use that I've used before and this means you download computer use as part of Codecs.
19:45It can literally control your computer. Not only can it control your computer, it can control multiple of your apps at the same time which is a mind blowing experience and you can see the mouse moving around on your device.
19:58I had it controlling Canva yesterday. It was moving around pretty fast, controlling Canva. It exported the right document and it fed it back into Codex.
20:07It was a really fun workflow and that's just a really cool experience. I I highly recommend trying this just to kind of see where AI is at in terms of computer use.
20:16And then as I talked about earlier, it can control the browser that's directly inside Codex. So pretty soon, we'll live in a world where an AI will be able to go to any site, open the browser, you're gonna be logged in, so it'll have all of your login information.
20:31It'll be a full browser like Atlas and it will be able to take any action. So there will be basically no limitation to what it can do.
20:38And then they released this new chronicle feature so that it kind of like remembers everything. So it'll kind of and this one might have some privacy stuff that you might want to look into if you're super big on privacy.
20:49This is my work computer and I I like testing stuff too much so I had to enable it, but it basically watches your screen for context so you don't have to explain yourself again. It just kind of knows what you're working on and it stores these as like little codex memories and it allows you to stay in flow.
21:06So you can move chats around, you don't really need to be that organized. The AI will just kind of have context over what you're doing. And these are kind of the main reasons I really like
21:16Codex. I didn't know about Chronicle. First time I've ever heard of that.
21:20Is it worth I I know there's privacy issues and security issues. I know the comment section is gonna not love it.
21:28But from a productivity standpoint, are you seeing meaningful uptick?
21:33So I they released it two days ago. So I'm not gonna lie, there's been way too many things to test. But if you go to personalization and you scroll down and go to Chronicle, I recommend learning more.
21:45This is not an endorsement. I'm using a work laptop. I test everything.
21:50I go unlimited permissions on I don't care about the privacy stuff. I'm testing everything.
21:56That's what I do. I love it too much. So by no means am I telling you to do this and that it's worth the risk.
22:01I have no idea what the risk is. Um, but you should look into it because it is an interesting technology at the very least. Right?
22:08Having an AI, assuming it's secure and everything, having an AI that understands what you're working on so that when you type something, it knows exactly what you're referencing, that is inherently useful. Whether or not it works really well, it's up up for debate.
22:23I haven't tested it long enough. Know, it came up two days ago. So what else do I need to know?
22:28Like, because I'm downloading codecs for the first time. So what are things in terms of setup?
22:34Remotion, I'm gonna add projects, understand. Plug ins.
22:41Yeah. So, yeah, let's talk about plug ins.
22:44So plug ins, you know, there's a lot of words right now. People talk about MCPs.
22:50They talk about plug ins. They talk about skills. They talk about integrations, connectors.
22:55Right? You have all of these words and if I'm being honest, the difference between them is very blurry.
23:00Right? Just kind of I clump all of those words together and I just call them skills. Um, it just makes sense in my brain.
23:07Right? You have an AI agent by default that's really smart. It can search the web.
23:11It can it can create apps. But if you don't give it any skills, then it's it's only gonna be a generic model.
23:19What you need to do is you need to give your agent access to the tools that you already use to make it useful for your workflows. And so here they call them plugins and again, skills and plugins, you can create your own skill, you actually can't build your own plugin unless you get it approved by OpenAI, so that's kind of the the difference.
23:38Plugins are more official. And so one of the plugins that I use is Slack.
23:43So it's connected to our Slack, I can ask any question. You know, we have like 30 channels as a company and I can just ask AI to summarize everything that pertains to me. And because Codex keeps memories of me and I've given it a document that I've told what I think is important, it can find the things that are important.
24:02It'll surface them to me. Um, you can also connect it to your email so it can send and, uh, receive emails or you can like tell you who emailed you if something's really important.
24:13Um, and you can connect it up to Notion, you can connect it to Sheets and you know, pretty soon you're gonna be able to do it for all of them. The expo one is pretty useful.
24:22It allows you to kind of view a mobile app, uh, preview directly inside Codex, which is really cool. Um, and then obviously Remotion and Canva, You can just connect it to your existing tools.
24:37And if you don't find the tool that you want to use in plugins, you can create your own skill and you do that simply by creating a new chat and you say, I want to create a new skill that does whatever blank.
24:54Um, and then you can also say use the slash skill wait, I think it's at skill.
25:02Oh, maybe they don't have it anymore. To reference a skill, use a slash. To reference plugins, you use the at mention, which I think is weird.
25:11I think they should combine all of them. Right? So I could say use computer use at browser use.
25:18To use a skill you do a slash and you can see all the slashes here. I don't see they used to have a skill builder skill but they don't have it.
25:28I think it's just smart enough to just say create a skill and it'll just create it. After you create a skill, it'll show up here in this tab.
25:35And here are all the skills that I've created.
25:38I've created It's so confusing. Right? Because like you create a skill and then it puts it into the plugins tab.
25:45Well, no. No. A skill is in the skills tab.
25:48Oh, yeah. Yeah. Yeah.
25:49You're right. It's in the plugins tab. It has plugins and skills.
25:53And so I think this is super messy. Right? That's why I think they should just combine it all into skills or pick one and just stick with it because it is super confusing.
26:02And the fact that they have different like, you have an at for, um, plugins and then you have a slash for skills, I find to be like kind of annoying.
26:16Yeah. But I will say I've tried all of these tools. This is the simplest version that exists yet.
26:22Okay. And then in the simplest way possible, what is the difference between a skill and a plugin?
26:30Honestly, I think plugins are just like a deeper integration.
26:35I I would be lying to you if I knew the technical thing. I just know that like if you're a company and you wanna create an official plugin, you go to OpenAI and you you create it with them. It's similar to you remember the apps SDK Yeah.
26:47On ChatGPT? It's more of an official process. Right?
26:50There's a reason why, you know, we can't just we couldn't spend the rest of this video making the the Greg Eisenberg plugin and then get it approved right after this video, you'd have to reach out to OpenAI. You know, I'm sure they have thousands of companies trying to create plugins and you can only imagine the value of showing up here on the plugins tab.
27:09Right? So this is kind of their more official integration and then skills are like what you create and these are just again, all of these skills are mostly just like a folder that is stored somewhere in here and then there's a skill dot m d file in that folder that has specific instructions.
27:29And AI is really good at creating skills. So all you have to do is just say, hey, any repetitive tasks that you have in Codec, say, hey, I wanna create a skill so we can do this faster next time. And then the AI will be like, okay, cool.
27:40Like, it may ask you some follow-up questions and then it'll just create the skill. And then it'll show up here. Yeah.
27:45One thing you might wanna do is,
27:48you know, if you're downloading Codecs for the first time, maybe you connect it to your Google Calendar and you basically say like, here's what I do on a given week and, you know,
28:00help me create a set of skills that can help me do my job better. Absolutely. Yeah.
28:05I think I think one of the best ways to do it is just to like literally speak into your phone. I just I tell everyone to do this, just yap about everything that you do on a day to day basis.
28:14Like go through every task, don't skip any details, take twenty minutes to just speak about everything, get it in a document and then just look at it and be like, okay, what parts could I automate with something? Anytime there's an automatable process and you can convert it into instructions that could be completed on a computer, that is a skill that you could create on Codecs.
28:37Uh, one really cool thing is right. So we just created this report using my YouTube researcher skill and it looked at the Startup Ideas Podcast Negative Only Content Report.
28:51And The cheer slowly goes down my cheek. I love this. Let's let's
28:57Alright. The show is drifting away from I I I meant to do it as a joke. I'm not actually trying to to nitpick your channel.
29:04But will say that as uncomfortable as it is to get AI to critique you, it is a useful activity. I've done it before, know, like sometimes you can't turn a blind eye, you know, and it can an AI will actually find, um, it can search other channels and see what they're doing right and then compare it to what you're doing wrong.
29:21It's like this channel is doing this right. That's why they're getting more views than you. Right?
29:25And these exercises are good. It puts you should spend more time on what you're doing wrong than what you're doing right in my opinion and just focus on improving it every time. Now let's say that this was the most useful report you've ever seen.
29:38Right? Let's say we go through it and we're like, oh my god, like we need to we need to do this more often. One thing that you can do is you'll notice here we have this automations tab.
29:46I want you to do this every single Friday.
29:53Actually, every yeah. Let's do every single Friday for the videos of that week.
30:02I want to know what I'm doing wrong. Please create an automation.
30:12Oops. I don't know why I didn't pick up on that. Oh, it's because I have my AirPods in.
30:18Create automation. 9AM on Fridays.
30:25And so it really is that easy to create an automation. You just type in that you want this to happen. This is how I normally set up automations.
30:32People sometimes wanna create an automation before they do it. So, like, do it once and then tell the agent to do that every time on this day.
30:41And that's a kind of a good workflow. And you can see here that it shows created weekly startup ideas podcast Fridays at 9AM. If you click on it, it opens up right here.
30:50And it shows you the status, is active, which is good. The next run is on 05/01/2026. The last run is nothing because it hasn't run before.
31:01And there you go. It tells you what project. And then you'll notice here there's now a two on automations and it shows up right here.
31:08And if you wanna test it, all you have to do is come up here and hit run now and it will run that automation. And that's how you can kind of test to see how good it is. And then if you notice that something's wrong, you can press edit and you can edit the automation.
31:22And I recommend doing that a few times like whenever you're setting up an automation, you wanna make sure it works. And that's how you set up these recurring tasks. And some recurring tasks that I'm seeing a lot of people have in the AI space or just people in business is they just have AI analyze their Slack and their email like twice a day and it sends them an email summary.
31:45So they just they get it very concise and they all have links to to relevant chats or emails. So it's really easy to navigate.
31:54I found that to be a really useful one for me as well. And, you know, you one shotted that negative report.
32:00So if I, let's say I'm not happy with the output for whatever reason to refine that, how do I do that?
32:08Yeah. I mean, say like,
32:10hey, by the way, the report you gave me was too long.
32:17I want more concise. Put and make it a slash.
32:25And by the way, this document is a skill by default that that is called Word docs.
32:32So I just say make it a Word docs instead of markdown. And then then you can see I'll use the doc skill here.
32:44I'll do two things, convert the markdown into concise docs and update the Friday automation. You see, was gonna have it recreate the doc and then I would say, okay, now update the automation, but it decided that it was just gonna do it for me, which is cool, which is actually not how I would wanna do it.
33:00And one thing is in skills, you can always include references with skills. So or in in your automation.
33:10So you could actually include the document that it creates, uh, inside the automation.
33:16You could say, hey, it should look like this document. Right? And you can give it an example.
33:21I I always tell people that really good instructions are good but giving it a really good example is great. Right?
33:28You give an AI one good example, it's amazing. You give it five good examples, it's just gonna do a great job every time.
33:34That's kinda how I think about it. So is there the concept of an eval on output?
33:40Meaning, you know, an eval basically in evaluation, short for short for evaluation.
33:46Basically, this is a nine on 10 output, 10 on 10 output, and it keeps going until it gets good output. Is there that concept within Codecs?
33:54I mean, you could set it up yourself. The the you know, this is g p t 5.5.
34:02It'll run for as long as you want it to run. And so you could just tell it, say like, hey, I want you to evaluate it. The problem is, I think in that case it would probably be useful to have examples of really good output so it knows what you want.
34:16You know, the AI, they struggle with these, uh, subjective tasks. Right?
34:21Coding is very, um, you know what a good output is because the app looks good and it fully works. So it's easy to verify whether it's good or not, but a report, you know, my my startup ideas podcast.
34:34So this is another problem that Codecs has. Oops. That's kind of annoying is like the bullets are all weird.
34:42Like so this is one thing. This is another example of something you can fix, like fix the bullets, they're weird formatting.
34:54What was I saying before the weird formatting?
34:58Before the bullets completely threw you off? You're saying those bullets are I don't blame Those bullets the bullets will throw anyone off.
35:09Yeah. Yeah. Honestly.
35:13But, yeah, you could just create these these don't remember what I was saying.
35:18You were saying, I don't I don't remember. The bullets really took us for a left turn.
35:27We're talking about skill.
35:29I think you're talking about the, you know, the right outputs, examples.
35:35Yeah. Yeah. Yeah.
35:36Yeah. The number one thing that you can do in a company right now and we're talking to a lot of companies who are trying to implement AI is just collect as many good examples as possible.
35:48This allows your agents to have examples that they can reference, store them in a knowledge base that's easy to to find. Right? If you store them in in like a Notion database for example, AI is really good at going to a Notion database, scouring the Notion database, finding the right document to use as the example and and that way you can just kind of give it all of your documents as long as you keep it organized.
36:09It's it's gonna be able to use it pretty well. Um, and so collecting examples is a really useful thing.
36:16And I've noticed a lot more companies are even recording their screen a lot more in order to capture workflows because I've heard rumors that the future versions of OpenAI, their newest model and version of Codecs, you're gonna be able to upload videos to it.
36:33And so it can watch the video, see exactly how you do it and then it will be able to control the computer just like you. And that's gonna be a whole new world. And so I'm kind of preparing for that world because most of my workflows as a creator or like I'm in marketing, a lot of my workflows require using an interface or using a tool like CapCut, like Canva, and AI will pretty soon get to a point where it can do that.
36:59And just a side note, you know, if that's the case that, you know, these super apps are gonna allow recorded videos to be uploaded to them, You gotta think that the value of recorded content is going to go up in in the AI age.
37:17So just from a startup idea perspective,
37:21there's a lot there. Yeah. Mean, and why do you think you hear rumors of Meta and Microsoft employees now required to record their screen and do certain tasks?
37:30And it's kind of like, you know, it's become a meme in that, you know, a lot of people who are anti AI where like, oh, when they start recording your screen, like it's over, like they're trying to replace your workflows. And yeah, it is kind of scary in a corporate setting, but like if you run a small business and you want to accomplish more with like a small group of people, like you want to be able to offload some tasks that you wouldn't normally do to an AI that can just kind of handle these tasks.
38:00Let me see here.
38:05Did it fix it? There you go. So, yeah, you can create any sort of document in here.
38:14Recording your screen will be big.
38:16So the number four negative if you go back to that doc, one of the things that I get wrong in this podcast apparently according to Codex is my interviews are way too soft.
38:27So it says my guests get a friendly runway. There's not enough pressure on failure modes, cost, security churns, customer acquisition, or who should not use the product.
38:36So I'd like to take this opportunity to take the Canadian out of me and not be so friendly and ask you the question with respect to codecs, You know, who should use the product?
38:52Cost, securities, churn, customer acquisition, like, you know, what are the hard questions I'm not asking that I should be asking about Codex? You know what I respect about you is you got feedback and you are
39:05applying that feedback ten seconds later, which I admire. That's great. You know, who should use the product?
39:15I think that if you're constantly I think content creators should use this platform.
39:23You know, like I I'm a content creator first. That's how my brain thinks. You know, I'm constantly creating lead magnets which require vibe coding and if and yeah, I find that to be super useful and I'm also creating documents.
39:36So if you're creating websites and documents, you might as well do it in the same platform because ultimately, like, the websites that I create have to do with the documents that I create. I don't want them to be in separate platforms. I wanna be able to create a document, do research, outline my thinking, and then convert it into a landing page seamlessly, and that's what you can do inside Codex.
39:55So so as much as I want to help you give good feedback, I think there's a reason why, uh, these companies are racing to create the super app is because they think that everyone in knowledge work will use these platforms and I truly believe that that's where we're going.
40:12I'm not saying you need to use Codex. I have no vested interest in Codex. I'm not an investor in OpenAI.
40:16I've never been paid by them. I just like their platform and I think it's the best right now and I see a clear path to it being the best over time.
40:25So that's why I'm trying to prepare now because it's it's only 10% as good as it will be maybe once these AI gets really good at controlling a browser. That's what I'm really excited about. So for all those reasons, you should use it.
40:41But again, don't use it if you don't want to. Anything else on this platform that's just a must know in terms of getting the most out of it?
40:49Honestly, you know what? I I I I would maybe should have started this, but so yesterday in my video, I posted this video. I wanted to test browser use.
40:57And so I had it make this chess game and then I said I said, okay, use at browser use and play yourself in chess, uh, one move at a time like earlier.
41:18So what you're gonna see here, hopefully, if Codecs operates properly and by the way, we're using 5.5 on medium intelligence, which, uh, I will talk about that right after.
41:32But let's see if this AI plays itself using the browser. And I think this is just like a good way to kind of get an idea of like how the browser use works.
41:42I recommend just having fun with it at first. I think people try to do like oh, see? You can see the mouse.
41:49You see that? So it's literally playing itself in chess as both teams and look at how fast that's like working.
41:59Right? Like, you know, a few months ago this was way slower than this.
42:04Don't know if you tested any of the browser use stuff, but this is like pretty seamlessly playing.
42:09Yeah. It felt like like with Manus, for example, it was really cool that browser use was even possible, but it really felt like it was on a dial up modem.
42:21And this this feels like it's broadband.
42:24100%. Yeah. I just checkmated black.
42:26So white just checkmated black. White wins by checkmate. I played it through the in app browser one move at a time alternating white and black.
42:34Final result, white wins by checkmate. And here we can see the full sequence. And so in my video, it did this in one prompt.
42:42I said build a chess game then use browser use to test the game and play yourself until one team wins. And that's what it did in one shot which I mean that's pretty insane, you know, like it it we're we're desensitized to it now but like that's insane if you if you think about where we were even a year ago and then you think about where we will be a year from now, you know, it may just create its own Canva a year from now and then use that.
43:08It might find it might be like, oh, it'd be way faster for me to just create my own tool because Canva doesn't have this little feature and it can't add it. Like it might as well just make its own feature and then add it and then control it.
43:19And that So are you not using Cloud Code at all anymore? This is like your daily driver?
43:25Okay. Two things I forgot to cover. That's one of them.
43:29Command j opens the terminal. Type Claude.
43:33I have it set up to automatically run-in, uh, dangerously skip permissions mode. Anytime like I can say redesign the chess app to make it the anthropic vibe.
43:46Boom. Congratulations. You're using Claude code inside Codex and you're using it with the Claude subscription, so you are getting you're benefiting from that same the same savings.
43:56Right? Another reason why you wanna use these models in these platforms directly, like in Claude or in Codex is you just save so much money because they're subsidizing like, you get thousands of dollars of tokens for your $100 per month or $200 per month plan because you're using their platforms.
44:14So, like, for me, there's no really good argument on not using these platforms, if I'm being honest, because you get so many tokens as a as a user.
44:25And you can also just use Claude code directly inside Codex and it'll work. So that's one thing. Also, another thing is, uh, you know, Theo and, uh, some other people have been talking about how they like to use 5.5 on low and medium effort for most tasks.
44:44Right? If you ask it to make a simple change and you use extra high, it'll often like really try and put a ton of effort into it and it might go off and like do unintended things. And so that's one thing to look out for.
44:56I'm not very good at discipline enough at doing that. I end up using I end up just on extra high just running it over and over again. But that's what I've been hearing other people say.
45:07And you can also if it feels like it's going too slow, you can turn it to fast. Just know that this will be
45:14more expensive. You'll run out of credits faster. I also think it's worth mentioning that 5.5 is an expensive model.
45:21Right? Yes. It's if you use it via their API, let's see here.
45:27Look at that. So Cloud Code just changed the chessboard. Right?
45:31And then you can just throw it away. The only thing is if you use if you use Codecs in the app, you get that like spinning animation and you can see when it's done.
45:39That does not happen when you use it in the browser. They're kind of like separate things.
45:44So just keep that in mind, but like look at how easy that was. Now people like, oh, but Claude's way better at design. So it's like just make the whole app and then tell Claude to design it.
45:51Like, that's what I say. It's like, it's that easy.
45:55What did you just ask right before this?
45:58I I just I was just saying that I you know, you should should be noted that 5.5 is a more expensive Yeah.
46:06If you use it via the API, it's twice as expensive as, uh, the recent model which is, uh, GPT 5.4. It's twice as expensive, but what you'll find is that the model is actually more efficient.
46:23So it'll get the job done and get the job done better with less tokens. And I think that's where I think the benchmark thing will be a year from now.
46:33It's not gonna be how token efficient is it. It's going to be how much money and how much time does it cost to do a specific task. You know, the same way you would hire a contractor or or a human employee, you're not like you don't think about it in terms of token efficiency.
46:49You're like, you know, you just think about how expensive is it to get a task done. And so like if you were what this model does is it really thinks about your intent more and so it'll go more directly towards what it is that you want.
47:03And so you may find that it actually gets things done better and faster. But yeah, it definitely can cost more money when using it on the API. I haven't noticed my credits going down twice as much when using it in the app.
47:16So that's hard to say. Um, and then it's also 20% more expensive than Opus 4.7. So that's one thing to consider.
47:23So it is pretty expensive.
47:25You said that there were two things that you wanted to cover. One was terminal. One
47:30was the models and the second was using Cloud Code in the terminal. And again, this is a full terminal. So if you're technical, like you can do anything in here.
47:39And I think, yeah, I mean, you can create any type of document. I'm still learning this right now.
47:45So for example, you can leave comments on the the browser.
47:52This is similar to Cursor has this feature as well. So you can just comment directly on this and say like, this should say, uh, Greg Jess.
48:03Jess. And what you'll see once you press enter, you see that one annotation enters the the chat. Let me close out of this.
48:10And you can say and then you can add another one. You can say like, the pieces should be bigger.
48:20And you can just say bigger. And so you can add three annotations and then just say make these changes. That's kinda how I do it, uh, for a lot of the design changes and it's super useful.
48:33And so, yeah, I mean, this is a very complete product. You can also full screen it. One thing that you can do is you can full screen and then you can kind of message it here.
48:41It's kind of in a more immersive way to, uh, do some vibe coding tasks or if you wanna just focus on the document that you're working on. I find this to be incredibly useful.
48:50Have you been using Codex a lot with Images two point o
48:55Yes. When it comes launch? 100%.
48:58So, um, great question. Codex has g p t image two, which is the best image model in the world.
49:05And again, this is not like up for debate. I'm not again, I'm really not trying to shill anything.
49:09You notice here that it's making changes and it's using browser use to test stuff. I didn't even ask for that. So I just wanted to put that out there.
49:17Yeah. The GPT image model is actually insane. It's better across every single category and it's built into Codecs.
49:23And so you can ask it to create websites, you can ask it to create 10 different versions of thumbnails and Codecs will just prompt GPT image two and then it can generate images and then it can put those images in in a Word doc, you can put them in a presentation or a website or anything.
49:42So yeah, it's a super useful feature and I think there might be a skill for it. It's slash image or g p t.
49:54No. Okay. You can just ask it to use g p t image and it'll just do it.
49:58And they also have Sora built in too. Like Sora is an official plugin.
50:03And I believe Yeah. But are you gonna use Sora? No.
50:06Yeah.
50:07No. God, no. Sora, I don't even have it installed.
50:11I just, you know, some people out there, you know, they might wanna create some brain rot videos or whatever they're doing. Yeah. I think the people that listen to this
50:19like, most people here are, like, I wanna start a company where I are I have a company, and I want product market fit, and I wanna scale it.
50:27And they're looking at how can I use this tool to just supercharge my productivity?
50:34And so I think that with respect to Sora, you know, Sora is now delisted from the App Store.
50:41Right?
50:42Yeah.
50:43It's it doesn't exist anymore. Doesn't exist anymore. So it's like it's interesting.
50:47It's fun. But I think the people listening to this are way more interested in using Remotion.
50:53Totally. But but remind you, that's not like a reference to the app, the the plugin. It's it's it's the video model.
50:59And Sora is not the best video model right now. So that's why it's not interesting. And I think that's what OpenAI realized.
51:04They're like, oh, it's gonna take so much effort to create the best state of the art video model. Like, that's what people want to use. So you can create a skill that connects to FAL to use the best video models and you can attach it to this app.
51:17And you could have those videos show up inside the Remotion thing. You can put videos inside of the Remotion video that play in the video itself.
51:27So if you wanted to create a talking head video of you, I've seen you've you've have used AI video before, I'm certain.
51:34You could easily set that workflow to work directly inside Codex and you could add subtitles directly in it. I'm sure there's gonna be a company that only builds like an AI video editor like Remotion that shows up inside Codex and they're gonna make a killing.
51:49Right? Um, that's all coming.
51:51And so you'll be able to just edit, create videos directly inside Codex because any interface that you can possibly think of that would be on the Internet will show up here because it's a full web browser. So And
52:03with, you know, working with FAL, you know, is the best video model?
52:09Is it Cdance two point o? Is there something else that you you use? Yep.
52:13For whatever reason, I've like completely lost interest in AI videos. Maybe it's gotten so good.
52:19For me, I just focus so much more on like the I find coding and and agents so much more interesting than video models. I'm not up to date. I would love in the comments if someone could let us know what the current state of the art model is.
52:31I'm I'm really curious. Uh, I've heard Seeddance, Cling and a few others are are really good.
52:39I'm curious where Google is. Have you heard anything about Vio? Like is that still a good model?
52:44Is it Three? Was that the latest one? I think it was the latest.
52:47Maybe like 3.1 or something. Yeah. I mean,
52:51I had PJ Ace on, I don't know, three, four months ago, and the stuff that he was able to show me in terms of creating commercials using Vio three point o, I believe, was incredible.
53:08Haven't heard of a a big launch from Google since But I I loved I loved what I loved what he showed me.
53:18I also played with Sea Dance two last week, I was also like very very impressed.
53:28Yeah. I always try it and I'm like, this is awesome. And then I'm like, what am I gonna use this for?
53:32Like for me, I make educational content. I like talking. I you know, it's it's hard for me and I've just been using Remotion a lot because very similar to you, in the first, you know, one to two minutes of my long form videos, I use graphics to kind of outline the you know, I saw I watched one of your Open Claw videos recently and you have a really cool graphic of like Open Claw with a spotlight coming down on the Open Claw.
53:53It's just a very good opening graphic and that's how I use. I use it as as overlays over my long form content. That's what I'm excited about.
54:01I just have been using it not at all for for AI generated video. But also PJ is a legend, by the way.
54:07I love Absolute that legend.
54:09I think a part of what's what's daunting for a lot of people in AI in general is they hear about something like codex and they're overwhelmed with how do I actually make this a part of my life.
54:25I just had coffee right before this with a friend of mine, and I was like, dude, are you on, you know, Codex?
54:33How are you using Claude? How are you using Gemini?
54:36And he was just like, to be honest, I use Notion and Notion AI, and, like, I ping pong with, you know, ChatGPT and Gemini sometimes, but that's, like, basically it. And I was like, well, what's stopping you from setting up some automations and creating some skills and this and that?
54:52And he's like, I'm just overwhelmed and I don't know.
54:56Yeah. Yeah. I mean, Notion first of all, Notion's done a great job, honestly.
55:00I I you know, I think they're I don't use Notion much anymore because the platform got a little too overwhelming to onboard other people onto.
55:11Like, if you don't know how to use Notion, it's becoming a little annoying to, like, teach people how to use Notion. It's it's kind of overwhelming a little bit, um, but they have a really good agent system built in. And if you wanna go deep in Notion AI and learning how to build agents, do it.
55:25Like, you know, it's great. I just personally want to create other types of documents and, um, I find codecs.
55:33Like very soon you'll be able to connect like Notion will just show up in the browser. Because right now you can't sign in to anything and have it stay signed in.
55:43It's not persistent. Uh, so that's but I know for a fact that they're releasing a full browser.
55:50And so there is a Notion skill already. You'll be able to control Notion. And so you're gonna be able to use these models for cheaper inside Codecs to use AI inside Notion.
55:59To me it doesn't make much sense to use the agents within Notion. Makes sense to use the agents within Codex
56:05and then use the interface of Notion if you like it. That's how I that's how I see it. But if you say you use Notion as your second brain, I'm I'm sure there's a plugin, a Notion plugin that connects.
56:16Yeah. Right? Yeah.
56:17Absolutely. Plugin,
56:19Notion. I have it set up. I use Notion for one specific thing and that is for all of my videos, I create one Notion page and I drop in you can actually upload videos to it and like I can comment on parts of the script and include attachments on the videos.
56:36It's niche use case. So I use Notion and I set it up with one click. And if you actually go to Notion, actually, we don't need to get into this, but it's super easy to like choose what, uh, TeamSpaces has access for codecs.
56:52So when you go to Notion, can very easily like set up permissions, like, and you can only give it access to one database if you want. Um, if you're if you're worried about it messing up messing with your Notion or privacy concerns, it's you can give it access to only specific databases, which I find really useful.
57:10I wanna end on this note.
57:14I wanna end on for someone who's just getting started with Codecs, if there's three or four things that they should do once they've got it installed, what would those things be?
57:27It's very funny. And by the way, we didn't plan this. I put this right before the podcast.
57:31I was like, if there's projects to get started to test, uh, I actually wrote them down, um, and we covered one of them. I I think the first thing that you should do is you should have fun on all these platforms.
57:42I think the worst thing that people do when they when they show up on the platform is to like expect to get productivity out of it right away without kind of like play around for thirty minutes. Take an hour to just do fun projects and that this gives you an idea of like the possibilities and then hone it down and get very specific and get disciplined.
57:59And so I think one of the best things that you can do is like make a game, uh, and have browser use play a game against itself. Just use the browser use test it.
58:07It'll get your brain thinking about where this is going in the future and how this will be useful in the future which may actually change how you set up your documentation now for all of your different tasks.
58:19Like maybe it'll maybe you can start preparing for it now because this is not a year from now. This is like three months away AI will be able to control any browser like as good of a human. And this is something I can't convey by explaining it.
58:31You have to try it out. So that's why I recommend trying it out. Another thing that you should do is, um, tell AI to do in-depth research and say, uh, put it on max effort and say, want you to research this topic and, um, put it all organize all of the information you find into a spreadsheet.
58:48Then when you're done, turn that into a document and presentation and just get the sense that you can create a in-depth research report. You can put it in a spreadsheet.
58:58You can create a document and a presentation. Right? So once you do these two things, you now understand browser use and all the types of documents it can create.
59:06And then I said make a three d simulation. This one's more just for fun. Um, if you want to, you can also try and build a mobile app in Swift.
59:13If you have a company website and you're like, oh, you've always wanted to create a mobile app, um, you can literally download the code to your to your web app or website, upload it and say, hey, I want you to build a mobile app in Swift. For this, for now, you still need to have a Mac and you need to have Xcode downloaded, but it can one shot mobile apps like full mobile apps.
59:34If there's a few things that you need to learn, but you'll be mind blown at what it can create in one shot to the point where it's actually gotten scary for me. Like, I'm like, oh my god, every app that can exist will exist.
59:47That's how good AI is getting at creating mobile apps. And then like the main thing after you've kind of played around, like I said, list out all of the things that you do on a day to day basis, pick the most annoying thing that you do every day and then, um, try and do it with computer use or just try to create a workflow that accomplishes it.
1:00:06Maybe you use plugins and then tell your agent to turn it into an automation. Just tell your agent to turn it into an automation and, you know, if you can create one useful automation in a couple of hours, that might be worth it.
1:00:18You know? Um, and so those are just some projects that you can get started with right now that will give you an overarching view of what this tool can do.
1:00:26And I think by then you'll be like, okay, I understand.
1:00:29And by then you'll be like, that Riley Brown guy, he was right about that codec thing. Yeah.
1:00:34Like, and you might have doubt now. Like, you you can only convey so much information by talking or even showing. Like, you gotta feel with AI, I think to a large degree you have to feel it.
1:00:43You do these things. If you're still not sold, message me. I I I don't think you you'll exist.
1:00:49Um, I I don't think that person will exist. Just
1:00:52I'll include links for where to find Riley in the show notes in the description. Riley my phone number.
1:00:57I want a direct line. No. I'll include Riley's phone number.
1:01:02Actually, careful what you text Riley because he's got Chronicle set up. So, you know, whatever you text him might just show up on the Internet.
1:01:10It goes it goes straight to Sam Altman. Yeah. Riley, thanks so much for coming on the show.
1:01:18Do you have one last words word of wisdom to leave people after this Codex Masterclass?
1:01:26Honestly, just get out there and experiment. Right now is the best time to experiment and what I've noticed, you know, in being in San Francisco, I've noticed that the people who have been like really successful creating startups are people who just like want to experiment and tinker and they don't have so many people who are like type a want to get an immediate benefit after thirty minutes of using a tool and I don't think that's where the benefits come.
1:01:50I think the benefits come from tinkering, messing around with tools And and when you get when you have this weird inclination of you're like, okay.
1:01:57Wait. What is a model? Why is this model different than the DeepSeek v four model?
1:02:01It's like go down that rabbit hole. Use AI. Learn about it.
1:02:04And then through that process, you'll you'll learn the things you need to learn to, like, start or grow your business. I think all of the magic in AI happens in these like rabbit holes and then once you find something just like go all in on it.
1:02:17That's that's kind of my my final advice and I think Codex is a great kind of surface to do it on. You're totally right by the way. I lived in San Francisco for, you know, almost nine years and
1:02:30I think it's not just so much that the the tinkerers win is that people the tinkerers who aren't afraid of looking dumb win.
1:02:42Right? So I think when you're when you're trying some of these tools, you might feel dumb initially.
1:02:50And it's because you aren't a master of it yet. But the only way to become a master is to actually put in the time and work. So I think the the reward is infinite.
1:03:04Right? The ability to use these tools really well like codecs and be able to create you know, for me, this isn't just a tool that's helpful for content creators.
1:03:14Like, this is helpful for literally anything that, you know, you can dream of. Lead magnets, you use one example.
1:03:20Lead magnets, content, of course, but, you know, ideas for products that you want to create, businesses you want to create, automating your personal life, automating dream team for, you know, a business that you're starting.
1:03:36Just, you know, and everything in between. So, yeah, keep keep playing.
1:03:40Just stop listening to this, but, you know, also like and comment for for us that, you know, I wanna I want this episode to to get a lot of love so Riley comes back on. But, yeah, get your hands dirty. On,
1:03:54dude. This is my fifth time on the show, man. I mean, I'll I'll I'll come back on anytime.
1:03:58Even if it gets 10 views. You came you came on when we were just a little show and Dude, honestly, there's an argument to be made that I put you on the map. No.
1:04:06I'm just playing. The the the video, the first vibe coding video, it's funny. I I actually someone a lot of people bring that up.
1:04:13They're like, oh, I first saw you on Greg Eisenberg's podcast when I was struggling through that first episode.
1:04:18And that's why we that's why we do this. Right? Like, you know, I hope I hope so, yeah, thanks again for coming on.
1:04:25I hope someone learned one, two, three, four, five things that just gave them not just the creative juices to to actually use these tools, but the motivation to keep going.
1:04:35So thanks a lot, Riley. Appreciate you having me on. This is awesome.
The Hook
The bait, then the rug-pull.
Greg Isenberg opens by confessing he has never downloaded Codex, then invites Riley Brown to convert him in real time. What follows is 64 minutes of live screen-sharing that doubles as the argument: either the era of separate tools for coding, documents, and research is ending, or it is just expensive hype.
How they asked for the click.
MENTIONED ON CAMERA
FROM THE DESCRIPTION
PRIMARY CTAWhere the creator wants you to go next.
OTHER LINKSAlso linked in the description.
