ChatGPT Codex Voice + browser + Sites: an expert’s AI workflow | Nick Baumann (OpenAI)

If we go back to, you know, 2022, 2023 around like the release of ChatGPT, I think a lot of people felt the AI then. A chatbot that I say things to and it intelligently says things back to me. I think with the advent of coding agents and like the coding agent harness in particular, now this AI is going out and like reading files and creating files and like running commands. And this is crazy. I tell it one thing and then it figures out all these other things on its own.

I haven't gone deep with voice. I wanna see it from the pro. How should we be using it? What's cool about it?

So I'm just gonna trigger voice. I've got a hotkey for it.

I'm listening.

Go ahead.

Okay, there should be some Amazon receipt for a, a mic I just bought recently. It's for DX uses. I'm hoping you can help me expense it. Could you spin up another thread to handle taking care of that expense report for me?

The expense task is running. It'll find the Amazon receipt and stage the Navon report, but not submit it until you confirm. I'll let you know when it's ready to review.

If anybody has been lucky enough to have an assistant, this is how it gets done. And it is just like such a nice delegation. Experience to be like, hey, can you take care of this? Hey, can you fix this? Tell me what's going on.

Typically voice is great. You can like talk back and forth, but it's usually with a less strong model that is less capable. Whereas this, it's fully able to delegate and manage these fully, you know, 5, 6 threads on its own, which is great because then you can have it do things on your behalf.

Hot take question. What do you think matters more on voice experience, latency or intelligence? Welcome back to How I AI. I'm Claire Vo, product leader and AI I'm Kelsey with Obsessive here on a mission to help you build better with these new tools. Today we have Nick Baumann at OpenAI, and he's gonna show us some of the advanced use cases of ChatGPT Codex and ChatGPT Work, including how you can talk to your computer to book your flights, use ChatGPT Sites to build websites you can share with anybody or nobody, and use my favorite workflow, which is editing creator content in Codex. Let's get to it.

This episode is brought to you by Bolt.new, the AI app builder for people who have ideas and want to ship them. Most AI tools spit out code that looks great in a demo and falls apart the second you try to do anything real with it, or they lock you into their own platform with no real way out. Bolt is different. You describe what you want to build, a startup MVP, a landing page, an internal tool, a side project. And Bolt generates production-ready code in minutes.

Connect Stripe or any other MCP, hook up your domain, and deploy it live.

Founders are using Bolt to build businesses doing real revenue. Product managers are shipping prototypes their teams actually use. Designers and marketers are launching campaigns without waiting in line. Anyone can build, engineering can ship, everyone wins. You just need an idea and a weekend. Check it out at bolt.new/howiai.

Nick, welcome to How I AI.

Hello, Claire. Thanks for having me.

I am gonna make you laugh because I might be the number one Codex fan, fanboy, tech bro fanboy in the world. I am like constantly telling people, wait, but have you, have you tried Co— have you tried Codex yet? It is just my daily driver. So I'm so excited to have you on because Even though I use it all the time, and for some things that you and I think both think are valuable, I have not touched most of the new features that have come out in the last week. It's really hard to keep up. And so I'm really psyched that you're here to just show us some of the new stuff and maybe how you use Codex both for work and life. So tell us, what are the things in Codex that you feel like people don't really know about or, or are brand new that you think are completely going to change how, how we all work.

Yeah, I feel like, you know, with yesterday's release of Voice, um, the ChatGPT Codex app, it's kind of like the amalgamation of all these primitives we've been like putting together kind of quietly, and now we're super useful. So a lot of people don't know that the ChatGPT app, you can ask it to create threads, you could ask it to message your existing threads, and these threads actually talk to each other too. And it's like not super kind of forward in the app, but these are all capabilities. And now we've added this voice orchestration layer, really, where now you can, you know, with the hotkey, you can trigger this orb that like pops on your screen. And no matter where you are on your computer, you can talk to it, it'll talk back to you, and it can see your screen, it can see what you're working on. And because we have those primitives of see your existing threads, create new ones, talk to them, It can like basically manage your entire ChatGPT app for you.

Yeah. One of the things that I, I don't want people to miss before we even get into like the fancy voice stuff is I really do feel like most people do not know the meta capabilities of Codex and even like, we won't say, but like the, the other one in that like its ability to not only spin off subagents, but actually start completely new threads, fork threads, look through old data, look through its own memory. It's a really good mechanism to let the AI manage context and decide when forking off different tasks makes a lot of sense. And so I've been doing that a lot, but I actually had to discover that capability sort of organically when one day I was sitting there and it was probably 5, 6 was like, I'm gonna kick off a new thread. And I was like, you're gonna do what? Like what now? And so I do feel one of the challenges with these core core kind of platforms like Codex and ChatGPT is people just don't know how to discover the features and they're so rich. And so do you have any, you know, like we'll talk about voice, but are there any other like sort of edge features of Codex or ChatGPT that you feel like people underuse? Not just this, this thread one.

The ChatGPT work experience. You know, people are talking about, you know, should we be using ChatGPT Work or Codex? I think ChatGPT work on the web, specifically mobile, I mean, that's where I use it mostly, is so insanely powerful. It's one, it's essentially like the Codex harness, which has this incredible compaction. You have all your plugins. So if you've like already connected Gmail and Gcal, like whatever you use, it's already there. And then you have it all accessible on your phone. So you can like create these automations, also known as heartbeats, and it's already there. So like, I mean, a few times a day, I'll just get, like a notification saying, hey, like I got this email about this thing you bought. Are you sure you bought that? Or like, hey, this package is arriving. Make, make sure you grab that. And I, I'm not watching my email or my finances, but that's just kind of being monitored for me. And that's, that's a really magical experience.

Okay. I love it. All right, so let's get into ChatGPT Voice and what you, what you use it for. 'Cause I, it came out yesterday. Um, I've been super busy and around humans. We're gonna talk about that a little bit later. So I haven't gone deep with voice. I wanna see it from the pro. How should we be using it? What's cool about it?

Yeah, I, I think it's really magical. So I'm just gonna trigger voice. I've got a hotkey for it.

I'm listening. Go ahead.

I'm hoping you can help me handle a few logistical things right now. Can you, can you see the, the offsite I've got pulled up in Slack?

I'll take a look. Let me check that Slack view. Yep, it's the DX team offsite in Paris, August 26th through 28th. You're due in Tuesday with the program starting Wednesday morning and wrapping Friday afternoon. Flights and hotel are supposed to be booked in Navant this week.

All right, so I, I muted myself so that Codex doesn't hear me right now, but what happened there is it can already see my screen. You can see that I've got Slack opened up. And what it did is it took an app shot. And so an app shot is something that you can do, or whatever window you have open, you just hit Command Command. And it essentially takes like a smart screenshot loaded with context that can use computer use or browser use on it instantly. But, you know, kind of a meta feature, Codex Voice already has that built in. So I'm hoping you can help me book my flights and my hotel for the Paris offsite. I'm also thinking about sticking around through the weekend and maybe a couple days after. Could you maybe like check my calendar, see what my availability is like, and see if it's feasible for me to stick around?

I'll check your calendar against the offsite dates and then look at travel options.

Is this using the connectors?

Good question. Yeah, so this is using the plugins underneath the hood right now. So it's not having to actually go itself.

Here after the offsite through Monday, August 31st. A Tuesday, September 1st return would conflict with a late afternoon meeting. The simplest plan is returning Monday, August 31st. Do you want me to plan around that?

You know what? I'm thinking I might just take PTO on that Monday and Tuesday. I'm flying out of SFO, so why don't you just go ahead and use Navon, um, spin up another task to figure out the travel, pick a hotel that's reasonable and within our company policy. And then when it's ready, let me know and I'll, I'll click book now.

Sure. I'll sort that out. I'll find options for flying out of SFO, arriving Tuesday before the Wednesday start, and returning after Tuesday, September 1st. Then bring you choices that fit policy for you to book.

So is this chat gonna be in— oh, sorry.

It's okay.

I, I am talking to, I'm talking to his codex. Invite Claire to the Paris offsite. Put her up in the Ritz. Get her in business class.

And honestly, we don't, we don't really have a Paris offsite scheduled yet, but so much of our DX team is French that I'm hoping that I can like, you know, start seeding the ideas here.

That task is running now. Comparing flights from SFO and a practical hotel for August 25th through September 2nd. I'll share the suggested itinerary when it's ready.

Cool. So we've got this task already running. And make sure it uses my existing Chrome browser for this one.

I'll check that. I've updated the travel task to use your existing Chrome session and keep it to preparing options, not booking.

Awesome. So right now it just, it just sent a message back to that task. It's already running. But I think while we've got that going, I'm going to ask it to do another thing for me. While I've got you, I've got an email, I think. There should be some Amazon receipt for a mic I just bought recently. It's for DX uses. I'm hoping you can help me expense it. Could you spin up another thread to handle taking care of that expense report for me?

Sure, I'll take a look.

I've started that expense task and it'll use your existing Chrome session. The expense task is running. It'll find the Amazon receipt and stage the Navon report, but not submit it until you confirm. I'll let you know when it's ready to review.

Awesome. So those are both running in the background. I've muted our voice so we can talk without being interrupted. But we can already see that in Chrome, this task is using the browser. It's figuring out our flight options. It'll figure out the hotel. Frankly, this is something I just enjoy not having to do. It's nice to just have this handled in the background for me.

What I like about voice is I do think sometimes people with AI really struggle still with like blank chat window syndrome, which is like they look at it and they're like, what am I gonna ask? What am I gonna ask this brilliant AI to do? And so what I love about first, just like voice transcript to text, which a lot of people have been using, is it, it is what our beloved multi-time guest, um, Hilary calls the Yappers API, which is like the best, highest bandwidth way to communicate with an LLM is just to yap out loud and just Context dump. But what I love about this like voice-to-voice interaction is if anybody has been lucky enough to have an assistant, like this is how it gets, it gets done. And it is just like such a nice delegation experience to be like, hey, can you take care of this? Hey, can you fix this? Tell me what's going on, blah, blah, blah, blah, blah. And so I'm, I'm guessing the hypothesis here with this voice kind of experience is there's gonna be like better discovery of use cases and sort of like more sprawling use cases because people can sort of delegate in a more natural way as opposed to having to like sit there and think through how to instruct kind of in text the models. Have you found that like there are specific things that you reach for voice with that you don't, that you don't like type with your human fingers? Are you a full voice pilled?

Like, where are we?

Yeah, a few thoughts there. One, I think it's like this iteration itself is like kind of a new primitive in that Typically voice is great. You can like talk back and forth, but it's usually with a less strong model that is less capable.

Yep.

Whereas this, it's fully able to delegate and manage these, you know, fully, you know, 5, 6 SOL threads on its own, which is great because then you can have it do things on your behalf. Other thoughts there? Um, I find the, like, the thinking process in voice just a lot better. When it comes to, you know, I could dictate for, you know, 2 minutes, send off a long paragraph, get back a couple long paragraphs and read those. And it's really hard for me to get in flow. I think of like planning in voice to be really, really effective.

Hot, hot take question. What do you think matters more on voice experience, latency or intelligence? If you could only pick one, I'm going to make you pick one.

I would say when I use ChatGPT, I put it on high intelligence for voice. I think there's, there's like a middle ground. I think if there are good tools you can delegate to, then I care more about latency. Yeah. So I don't know. I guess I still say latency.

Yeah, I think, I think it's the, I think it's what we're gonna be talking, and this is the clairvoyant prediction. I think it's, we're gonna talk more and more about latency in the, in the second half of the year because I just think It's like almost the, the thing to differentiate on right now is like how real-time can these experiences really be? I see a lot of people abandon great, great AI workflows because of a spinner or because of a delay. And so like the more you can close that gap, the more I think people can discover cool things and actually pull through and get some, some stuff done.

Yeah. I mean, I feel like so many product assumptions in design and AI tooling is like built around this, like, There's going to be latency. There's gonna be delay.

Yep.

Um, and the more we shrink that, we can kind of drop those assumptions and new products will, you know, will emerge.

Amazing. Okay. So, so what we've seen here, just to, to reiterate for people who are maybe not watching or listening, is you can hotkey spin up voice. It can manage these like very intelligent 5, 6 threads. You can delegate tasks. It can be hooked up to plugins. It can use your browser. It can use AppShots. It can use all these things and it's just like a very high bandwidth, low friction way to talk to superintelligence that can get nice stuff done. You, you mentioned that a little bit earlier that you are also loving like mobile and, and this combination of like dictation and managing through mobile. Can you tell me how like being able to do some of this on your phone has changed your workflow? Maybe like gimme an example of that.

Yeah. So I put together this site. And so this is just an aggregation of all these really cool tweets that both people in the Codex and ChatGPT community and also people that work at OpenAI have shared with how they're using Codex and ChatGPT. This was done just with ChatGPT, like the ChatGPT app where I had it use its own in-app browser, go through Twitter for like a couple hours, and then embed these links and kind of Add a little bit of description to them. And now what I do is I've got a thread on my work phone that is essentially managing this site. And when I see something I like, I just drop in that link. I say add it and it does. We also have this prompts tab and I do the same thing there. If I have like an idea for how somebody could be, maybe he's like newer to like ChatGPT work, I'll just like dictate my phone. Explain like, hey, there's this prompt for like having it manage your inbox and your finances. Can you add this to the site as well? And in terms of actually editing the site, um, deploying it, that can all happen from ChatGPT Work on mobile.

And I think what people are not seeing here, which again, so many new features coming out that I think people aren't taking advantage of, is the domain here is chatgpt.site. So you can now. deploy these artifacts, these sites live. So can you just walk us through a little bit how that works, or maybe we can do one just so people can understand the power of these sites and how you might use them or what their limitations are even?

Yeah, I think for like 10-second description for the technical audience, it supports a SQL database, it has S3 storage for files, and it even has environmental variables you can put there. For the non-technical audience, it's essentially a website that you can store things on, which is great. And you can also control who sees it. You can filter by email, so it can be private, it can be fully public, that's up to you. But what we could do, if you're interested, is we could try building a site live.

Let's do it.

And see how that goes. I love to build live. Yeah. All right, so let's jump into it. So I've got an idea for a site. I'm here right now with Claire Vo. She hosts the How I AI podcast, and we're hoping that we can build a site that takes all the best tips from the videos on her YouTube channel and makes it so you can like easily filter through them and have quick links to like different timestamps on her videos.

Make it match the How I AI branding. We use good old AI blurple purple. and black and white. And let's have it, if possible, categorized by tool. So like what AI tool is being used in the workflow and also function. So if it's for designers, if it's for engineers, it's for personal productivity, any of those things. Otherwise, I'm excited to see what you come up with.

Awesome. That sounds great. And go ahead and deploy it privately. And then we'll take a look at it, you know, when it's ready, and then we can deploy it publicly from there if it, if it looks good.

While this is running, let me make you, make you laugh because this, um, 2Human chat to ChatGPT I did recently with my mother and, um, she was like stuck on an administrative task and she was like getting all frazzled about it. She's like, oh, I'm gonna have to look up all this stuff and blah, blah, blah, blah, blah, blah, blah. And I was on the phone with her and I was like, mom, just hold on one second. And I opened up ChatGPT on my desktop and I turned on voice. And then I was like, can you just please tell me what you need to do? And I turned the speakerphone off my phone and I put it up to the computer and had her like babble kind of like we did. And I asked her a couple questions and then I was like, thanks, pressed enter. And I was like, I did it for you. I did it for you. So I really do feel like people are underusing Yeah. Like 2-person voice chat. You can do it on your phone. You can use speakerphone. Like it is this really nice, again, like high bandwidth way to get requirements into the system. And it doesn't just have to be you alone.

Yeah. I, I've had times where, you know, I need context, like somebody I work with.

Yeah.

And I'm like, please just like ramble, dictate into Slack and send me like garbage. I don't care. And they're like, no, let's just like set up a meeting. And I'm like, no, don't, don't do that. I don't need that. I don't need this to be like pretty or anything. Just, just tell me. That's, that's fine.

So are we at this meeting could have been a voice note like level?

Yeah, I think so. I mean, all I, it's, it's more like give me information that unstructured, however it is, that my agent can decipher. And that's, that's good enough for me.

This episode is brought to you by HyperAgent, the platform for deploying always-on agents that actually run your business. With HyperAgent, CyberAgent, you build agents in the cloud and deploy them where your work already happens, like Slack, Telegram, or email. An agent will scan your inbox and draft replies to vendor follow-ups. Another monitors competitors and spins up rich ad kits and landing pages. A third notices a deal going cold in Salesforce and writes the save email with full account context. These aren't chatbots waiting for a perfect prompt. They're proactive, learning your preferences, retaining your playbooks and getting better with every run. One user built 4 agents to run an outbound sales pipeline, prospecting, outreach, follow-ups, CRM updates, all in a single afternoon. No local setup, no VPS bills, no fragile permissions on your laptop, just powerful agents with full control over skills, tools, and guardrails. HyperAgent was built by the team behind Airtable, and How I AI listeners get a $1,000 in free inference to start building. Claim yours at hyperagent.com/howiai.

Okay, so this is gonna go spin up. We're gonna let it kind of like whirl a little bit. Maybe we'll come back to what, what we see. But there's one other use case that both you and I really like in Codex, um, that I thought you could show in particularly how, how you prompt it, which is Codex for video editing. And for those that don't know it, I do a lot of this for, for the podcast. I also do a lot of this just for like general work stuff. I'm cutting a lot of videos. So tell me like how you came to this use case, why you feel it's so useful, and then how easy is it to prompt kind of like video editing?

You know, I do a little bit of content as part of the DX team and, you know, we're trying to reach people that might not be inside like the Twitterverse. which, you know, there's a lot of us there, but there's more of us not there. And I think explaining, you know, how you can use these tools in really relatable ways where you're explaining to like a camera in like 45 seconds is great. And so I've started just kind of like going to a park, filming myself, filming my camera, getting a, you know, a smattering of little clips. And so this is from, like, this is from yesterday. I went to the park. These are like, most of these are takes that we're not going to use. But what I'll do is I'm just going to drag these into ChatGPT Work. And then, so what I've done, and I'm going to share this, but I've created a plugin called UGC Video. Actually, let me look at the one that I use for I've made a version that has like OpenAI branding, but you can actually see it here. And so this basically, after having gone through like a few runs of this, what I've noticed is that just having like some guidance around like, hey, make sure that we're not entering like the safety zone with Instagram ads, or let's do these formats. We want 9 by 16, also 4 by 5. That's great. But what I'll generally do, and I'll stick take this. So we've got a bunch of clips here. I recorded a video for the record and replay feature. It starts with me just explaining that I'm apartment hunting and that's kind of a pain. And then I walk through and show the feature in real life. I show myself actually apartment hunting and I show how Codex can do it for me. And then I have a closer about how this skill that's been made that's been made for me, can be put on a heartbeat, and I can have Codex just search for apartments in the background. Can you go through these clips first, like pull the transcripts, find the best takes, and then kind of piece this together into a UGC-style video? So that's running. A few things that, to kind of explain how this works. So I've only submitted Like 20-some-odd video clips. And so what Codex AI is going to do is going to start by processing those clips to get just the transcripts. This will help it understand the story, what we're talking about. And even my light description will help it understand that. And then what it'll do then, actually it's going to ask me some questions. Sure, we'll do organic vertical. Let's do complete and clean.

Sure.

So it'll first get the transcript and then it's gonna go through the takes and actually like process images from them to understand what I'm showing. And then it'll choose like the best takes. And when I'm recording, I'll say things like cut, or that's a bad take, or that's a good take. And it's able to like use that as guidance to know like, you know, what's actually useful from these.

Ugh, you're gonna gimme so many ideas because I have like deeply abandoned my Once great TikTok because I guess like UGC's hard, like short form is hard. And I just have such a high bar that I'm constantly like recording these clips and being like, that was garbage. And then I get frustrated and I walk away. But you've given me this idea, which is I could just like keep recording until like there's one that feels good and then just dump it all. I don't even have to remember which one is good. Dump it all, give some voice notes about how to edit, and then And then kind of assemble it. And then I, I love this process of just having the model transcribe, look at the video, come up with like good, good cuts and put it together. I use it a lot for our trailers. So anytime I do a very long talk, like a 30 to 60 minute talk, or I do a podcast that's like 60 minutes, I dump it in and I'm like, give me a 60-second hype video with the funniest parts of The talk and like give me a little bit of buffer for, for clipping. And then it, it clips that really well. It actually has like pretty good funny taste, which is nice. And so I do that. And then I also do like, I teach like a 3-hour-long workshop every quarter on how to like transform your engineering organization to be kind of like AI engineers. It's very, very long. It's like 3-hour Zoom clip. And I also do that to like clip chapters, clip shorts, do all that sort of stuff. It's just like, All this tedium of video editing, it's quite good at. And then just tell us, like, what does this plugin actually do?

Yeah, so the plugin's really just based on, like, all the steering I've done really this week of, like, making these videos, whether it's just, you know, describing the kind of formats I need or, you know, that you don't want to have text in certain areas because it'll be cut off or natural kind of breakpoints. Or how to do captions. It's, you know, literally I just, I had this massive thread where I did a few of these videos and there was so much essentially like bespoke knowledge in this process built up that I was like, hey, can you make a plugin out of this? And there's actually a plugin creator skill in the ChatGPT app. So it's pretty easy. And then I did a few tweaks and now I just more reliably get, I guess, the happy path that I want.

And can you show us an output? I know you did one of these for yesterday. Can you show us like what, what the kind of output is that you can get?

Yeah. So here was my starting prompt. Again, I just dumped in a bunch of clips. And one thing I wanna note, you talked about like the tedious stuff.

Yep.

Even like little things like going through and deleting bad takes or finding like the right segments. I, I feel like. I'm so willing just to hand that over.

Yep.

And just get that off my plate. I don't want to think about it. So yeah, I started with a pretty similar prompt that I just, I kicked off with a little bit before. At one point, and actually I was in an Uber, I said this on my phone. I remembered, I was like, oh yeah, I need 4x5 also. So I sent that in as like a steer and it was like, all right, got it. Updating the delivery matrix. And then this is actually where, you know, I was like, why aren't you asking me questions? So I had to update the plugin at the same time. And this is what the output looks like. So this is actually a few different, like, you know, back and forth steers. Here, we actually haven't, like, watched this full one, but we'll see how it looks. It's insane trying to find an apartment in SF or New York City right now. And it's impossible to get to all the listings before they're gone. So what's funny, I don't know if you can see that, it even added blurs to these addresses here.

Real smart. No, I can see it.

Yeah. Actually, I did like a couple of these for like that we're releasing on Instagram next week. And there's like sensitive like release material information in my Slack that it like bubbled up in my ChatGPT work. And it did this like insanely granular work of like blurring out Literally lines and then following it while I'm scrolling. And it does all this like verification where it, it adds these blurs, it checks its own work, and then it like does that over and over again until it's good. And then it gives you like, you know, a good result.

I, um, probably 6 months ago coded a redact-o-matic for the How AI podcast because I had so many people being like, whoops, I left like my API key open in that like one piece of code that we were talking about and So we actually like built one. Um, I need to try it again with Codex because it's probably, I, the one challenge we have is the blurs following kind of like screen shares, but.

Yeah. And actually that gets back to the, like, I don't, my, I don't even wanna deal with the tedious work.

Yep.

Like not only, actually it's a non-starter that I'm gonna make blurs automatically do that manually. That's just, that's not gonna happen.

No.

What's even more annoying though is having to think about, all right, well how do I generate outputs that don't have confidential information? And how do I still make it seem genuine? That's also a pain that I just, I don't think about. I just, I leave it to, leave it to, leave it to the ChatGPT app.

I'm gonna give one other benefit for the content creators out there for this like AI editing of content, which is it's real embarrassing to edit your own content. It's like really embarrassing to look at yourself and watch all these videos of yourself and be like, oh yeah, I was like real cute and funny in that one and that one. I am not like, I make no sense as a human. So I, I like to offload like the critique of myself and the critique of my performance off to another model so I don't have to look at my face so much as well, especially as like a solo creator, solo founder, somebody who's like working on their own work. So I do like having a third, you know, like a neutral third party.

Mm-hmm.

Do these cuts so I don't have to sit there and like listen to my, own videos all day.

Yeah, I know. It's great. Back to like the, it like, it definitely lowers like the bar, like the barrier to entry for stuff like this. And if I just need to like go to a park, you know, I recorded like 3 videos. I sat there and recorded the 3 videos over the course of like an hour and a half a couple days ago. And then I uploaded like 50 or 60 clips. And I dictated like what the different narratives for those 3 videos were. And because I have a plugin and a task that already understands what I want.

Yep.

You know, it took a while. I, I went to bed and I came back to it, but I had, I had the, had what I needed and we actually shipped one to our Instagram a couple days ago.

Yeah.

Okay. I have one more question on this and then maybe we'll see if the, if the website is up. Do you need Sol Ultra for this? 'Cause that's what I see below.

Yeah, I would. In my experience, there's just so many, as much as anything just for speed, there's so many little like microtasks involved in checking all these frames and checking these transcripts. And there's a lot of parallel processing that can happen and a lot of like parallel judgment, if you will. And what SOL Ultra is, is it's basically this framework for multi-agent for FiveSix SOL. And so I find that it's just more efficient and I get better outputs when I use Soul Ultra.

Love it.

Okay, cool. Let's see if the How I AI website is, is up and running. Look at that. Black and purple and white, just like I said. We also have AI identify which thumbnails are gonna do the best. This, the, by the way, this episode, just so you know, it's all Look Ma, No Hands. We had some problems.

Yeah.

Oh, I see what it is. It's the use cases. So each episode is showing up multiple times. That was a very good episode about Codex browser use where I let it shop for me for my Hawaiian vacation. Um, and it did quite, quite a lovely, lovely job.

If you, if you wanna get really fancy, you could probably have it have different thumbnails for each clip. We could even have like, use ImageGen to make like a, you know, a singular thumbnail.

Love it. Amazing. Okay. There's good old Alex over and over and over again. And then we're gonna hit 3 of me. It just built it. Awesome.

Yeah.

And then this can be published. Just like remind me how it, how it gets published, who I can share it with, how that all works.

Yeah. So let's say, and let's say I wanted to like share this with you.

Mm-hmm.

Um, I can say, you know, share this. And so now you can, you can put in, you know, whoever you really want to. It can be totally publicly available. You could add individual email addresses and it'll share with those folks.

Amazing. And then how do you log in?

It's login with ChatGPT.

Great. Easy peasy.

I do have a ChatGPT account underneath that email address, so we are good to go. Just to recap, we did a couple of use cases. So we talked a little bit about voice, high bandwidth, Yapper's API, just basically like talking to a computer-empowered assistant that can just go do a bunch of your work for you, um, with access to browser and other things, including just being able to screenshot whatever's on the screen and have context. We did a, um, a ChatGPT site, which I did not know it has its own computer and memory and browser and all that stuff. So that's fun fact for Claire. Um, or you can have it actually go off and make a website, which you can share publicly or share with specific email addresses, which you just showed. And then again, my favorite use case, which is take a bunch of clips for UGC, dump them in, make it the model's problem, including doing redaction and blurring, which is for any of my fellow YouTubers out there, a huge and very annoying issue. And I'm very happy personally to have seen this workflow and get it solved. Nick, a couple questions, lightning round questions for you. We will get you back to all your voice chatting. Question number 1 is on that topic. In this world where we're all loving our ChatGPT voice experience, are— is everybody in the OpenAI office just like mumbling to themselves and to their computer? Like, how are we gonna intersect all this voice capability with the realities of like existing around humans that find all this chitter chatter annoying? Like, this is how does it actually work?

I think it's like an almost genuinely uncomfortable question because when I'm at home, I exclusively dictate. And when I'm at my desk around other people, I will sometimes whisper, but I'm more likely to use my keyboard. And, you know, we have all these meeting rooms and these like little pods people can hop into. And I see people like hopping in there for not calls more often these days. Because they're clearly going in there to use dictation or to use voice and codecs. And clearly people are adapting to this as a better experience. But frankly, I don't know if the answer is we all walk around with those masks around us that shield our voice to anybody but the agent. But it's not ideal right now. But we can tell that there's a good version. And that's using voice, but it's not ideal for our current, you know, office makeup infrastructure.

Yeah. I, I imagine we like press a button and like a tube comes down.

That would be ideal. Yeah. That's, that's what I'm, that's what I'm hoping for.

We talk and we all press our button and the tube, the tube goes up. Okay. We're gonna, we're gonna figure this out, um, until we get the direct Codex to mind connection, which I'm sure will be a 2027 release. Okay. Um, second question. If people really wanted to, like, feel the AGI, what are the things that you really think are just huge step changes in the last 3 months? Maybe, like, voice aside, what is, like, the one thing that you would tell people to try or that you're really thinking is the new interface? Because there's so many things that you've shown here.

In terms of, like, in terms of feeling the AGI, I think a lot of people like you and me have already felt the AGI. I think if we go back to, you know, 2022, 2023, around like the release of ChatGPT.

Yep.

I think a lot of people felt the AI then. You know, what AI can be became understandable. Like, you understand this conception of a chatbot that I say things to and intelligently says things back to me. That's pretty cool. And then I think with the advent of coding agents and like the coding agent harness in particular, I think people in the developer community and like AI tinkerers, they felt this AGI moment where, wow, now this AI is going out and like reading files and creating files and like running commands. And this is crazy how I tell it to do, I tell it one thing and then it figures out all these other things on its own. And that was a huge AGI moment for people. But I do think there was a certain barrier to entry with that where if you're not an engineer, Or you're not a tinkerer. This is limited to a small-ish group of people. But now, with something like ChatGPT working on the web, I think we're taking a lot of the primitives, like the coding agent harness, like having an always-on agent, and we're making them not only accessible on the web, but they're accessible to your phone. And so for people that are already using the ChatGPT app, which is a lot, They can just switch over to the work tab. They can ask a question like, hey, can you check my Gmail and also my finances, which I know are 2 plugins that you can install really quickly and just monitor those and let me know if anything stands out or anything has gone awry. And now they suddenly have this agent that's maybe twice a day checking their email, checking their finances. And I think that small thing You know, when they first get a notification, you know, letting them know maybe a package has arrived or there's some weird charge. I think those are like the small moments that people might kind of be like, it might be like a foot in the door for a lot of people.

Okay, amazing. And then I have one last question I ask every guest, and because you speak to AI, I'm really curious here what, what you say. When I saw a little bit of your prompting strategy, it's a little bit of what I do, but when AI Is not responding, when it is not doing what you want, when it is not using that plugin, what is your prompting strategy?

Do you yell?

Do you all caps?

Well, it depends if I'm sitting at my desk or if I'm in my living room. Those are, I guess the, my treatment of, of AI is different. Um, it might be all caps in the office as I like bang on my keyboard.

Yeah.

Oh, at home I'll turn on dictation, maybe share a few expletives.

Yeah.

Yeah. Try to redirect things.

I'm just like constantly, constantly being like, this is trash.

Why?

Why are you, why are you this way? Um, I used to be so polite and now my bar is so high. I'm like, you, you can do better. I believe in you.

Yeah.

I would say lately I feel like I have been less upset. Um, Things are just working better, you know?

I feel more upset.

People are— people are— are you getting more upset?

Yeah, because my bar is higher. I'm like, I know you can do this. You're not a dumb dumb.

Come on. That's interesting. Yeah. All right. Yeah. Treat it, treat it as an equal or superior and you're surprised when it doesn't come through.

Okay. Well, Nick, this has been super fun. Where can we find you? How can we be helpful?

Yeah. Find me on Twitter or X. My name, Nick Bauman underscore. Um, if you have any questions about Codex, ChatGPT work, anything we're releasing at OpenAI, feel free to reach out to me. Uh, DMs are open. Uh, great to, uh, great to bounce with you, Claire.

Yeah, thanks for being here. Thanks so much for watching. If you enjoyed this show, please like and subscribe here on YouTube, or even better, leave us a comment with your thoughts. You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review, which will help others find the show. You can see all our episodes and learn more about the show at howiaipod.com. See you next time.