How this OpenAI engineer uses Codex + ChatGPT Work to automate everything

1. 0:00 – 2:56

   Introduction to Nick Baumann

   1. NBNick Baumann0:00

      If we go back to, you know, 2022, 2023, around the re-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 it... This is crazy. I tell it one thing, and then it figures out all these other things on its own.

   2. CVClaire Vo0:22

      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?

   3. NBNick Baumann0:27

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

   4. CVClaire Vo0:30

      I'm listening. Go ahead.

   5. NBNick Baumann0:32

      Okay. There should be some Amazon receipt for s- 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 the expense report for me?

   6. CVClaire Vo0:42

      The expense task is running. It'll find the Amazon receipt and stage the Navan 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, 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."

   7. NBNick Baumann1:02

      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, five, six full threads on its own, which is great, because then you can have it do things on your behalf.

   8. CVClaire Vo1:17

      Hot take question: what do you think matters more on voice experience, latency or intelligence? [upbeat music] Welcome back to How I AI. I'm Claire Vo, product leader and AI 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.

2. 2:56 – 5:40

   What’s new in Codex

   1. CVClaire Vo2:56

      Nick, welcome to How I AI.

   2. NBNick Baumann2:59

      Hello, Claire. Thanks for having me.

   3. CVClaire Vo3:01

      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 Cod- [laughs] 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 gonna change how, how we all work?

   4. NBNick Baumann3:47

      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 are 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 can 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, 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.

   5. CVClaire Vo4:40

      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 sub-agents, but actually start completely new threads, fork threads, look through all data, look through its own memory. Um, it's, 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 five, six, was like, "I'm gonna kick off a new thread." And I was like, "You're gonna do what? Like, what now?"

   6. NBNick Baumann5:26

      Mm.

   7. CVClaire Vo5:26

      And so I do, I do feel one of the challenges with these core kind of platforms like Codex is, and ChatGPT, is people just don't know how to discover the features, and they're

3. 5:40 – 6:40

   ChatGPT Work and Heartbeats

   1. CVClaire Vo5:40

      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?

   2. NBNick Baumann5:52

      The ChatGPT Work experience, you know, people are talking about, you know, should we be using ChatGPT Work or Codex.

   3. CVClaire Vo5:57

      Mm-hmm.

   4. NBNick Baumann5:57

      I think ChatGPT Work on the web, specifically mobile, and that's where I use it mostly, is so insanely powerful. It's, one, it's, it's essentially like the Codex harness, which-

   5. CVClaire Vo6:07

      Yeah

   6. NBNick Baumann6:07

      ... 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. Um, also known as Heartbeats.

   7. CVClaire Vo6:21

      Yeah.

   8. NBNick Baumann6:21

      Um, 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. Like, make sure you grab that." And, like, 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

4. 6:40 – 13:25

   Live Codex voice demo

   1. NBNick Baumann6:40

      experience.

   2. CVClaire Vo6:41

      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 yes- 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?

   3. NBNick Baumann7:01

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

   4. CVClaire Vo7:06

      I'm listening. Go ahead.

   5. NBNick Baumann7:08

      I'm hoping you can help me handle a few logistical things right now. Can you, can you see the, uh-

   6. CVClaire Vo7:13

      Sure

   7. NBNick Baumann7:13

      ... the offsite I've got pulled up in Slack?

   8. CVClaire Vo7:16

      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 Navan this week.

   9. NBNick Baumann7:35

      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 you... 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 browse 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's like, and see if it's, if it's feasible for me to stick around?

   10. CVClaire Vo8:20

       I'll check your calendar against the offsite dates, and then look at travel options. Is this using the connectors?

   11. NBNick Baumann8:27

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

   12. CVClaire Vo8:31

       You're clear 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?

   13. NBNick Baumann8:45

       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 Navan, 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.

   14. CVClaire Vo9:06

       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.

   15. NBNick Baumann9:20

       So is this chat gonna be in... Oh, sorry. [laughs]

   16. CVClaire Vo9:24

       [laughs] It's all good.

   17. NBNick Baumann9:25

       I, I, I'm talking to, I'm talking to his Codex. Invite Claire to the Paris offsite. Put her up in the Ritz.

   18. CVClaire Vo9:32

       [laughs]

   19. NBNick Baumann9:32

       Get her in business class. [laughs]

   20. CVClaire Vo9:34

       And, and honestly, we, 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-

   21. NBNick Baumann9:41

       [laughs]

   22. CVClaire Vo9:41

       ... you know, start seeding the, the ideas here. That task is running now, comparing flights from SFO and a practical hotel for August 25th through September 2nd.

   23. NBNick Baumann9:52

       Awesome.

   24. CVClaire Vo9:52

       I'll share the suggested itinerary when it's ready.

   25. NBNick Baumann9:55

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

   26. CVClaire Vo10:02

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

   27. NBNick Baumann10:11

       Awesome. So right now it just, it just sends a message back to that task that'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 s- a, a mic I just bought recently. Um, 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?

   28. CVClaire Vo10:35

       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 Navan report, but not submit it until you confirm. I'll let you know when it's ready to review.

   29. NBNick Baumann10:52

       Awesome. So those are both running in the background. I've, I've muted our voice so we can talk without being interrupted.

   30. CVClaire Vo10:58

       Yeah. [laughs]
5. 13:25 – 14:36

   Latency vs. intelligence

   1. NBNick Baumann13:25

      be really, really effective.

   2. CVClaire Vo13:26

      Hot, hot take question.

   3. NBNick Baumann13:28

      Mm-hmm.

   4. CVClaire Vo13:29

      What do you think matters more on voice experience, latency or intelligence? If you could only pick one, I'm gonna make you pick one.

   5. NBNick Baumann13:35

      I would say when I use ChatGPT, I put it on high intelligence for voice.

   6. CVClaire Vo13:41

      Okay.

   7. NBNick Baumann13:41

      I think there's, there's like a middle ground. I think if there are good tools it can delegate to-

   8. CVClaire Vo13:45

      Yeah

   9. NBNick Baumann13:45

      ... then I care more about latency.

   10. CVClaire Vo13:47

       Yeah.

   11. NBNick Baumann13:48

       Um, so, I don't know. I gue- I, I still say latency.

   12. CVClaire Vo13:53

       Yeah. I think, I think it's the... I think it's what we're gonna be talk... And this is the Claire Vo prediction. I think it's-

   13. NBNick Baumann13:57

       Yeah

   14. CVClaire Vo13:57

       ... 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.

   15. NBNick Baumann14:23

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

   16. CVClaire Vo14:29

       Yeah.

   17. NBNick Baumann14:29

       There's gonna be delay.

   18. CVClaire Vo14:31

       Yep.

   19. NBNick Baumann14:31

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

6. 14:36 – 15:04

   Quick recap

   1. CVClaire Vo14:36

      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 five, six threads. You can delegate tasks. It can be hookup 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 super intelligence that can get nice stuff done.

7. 15:04 – 21:24

   Voice on mobile and the ChatGPT Sites workflow

   1. CVClaire Vo15:04

      You, you mentioned that a little bit earlier that you're 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? And maybe like give me an example of that.

   2. NBNick Baumann15:23

      So I put together this site, and so this is just a, an aggregation of all these-

   3. CVClaire Vo15:28

      Mm-hmm

   4. NBNick Baumann15:28

      ... really cool tweets that, you know, both people in like the Codex and ChatGPT community and also people working at OpenAI have shared with how they're using Codex ChatGPT. Um, this was done just with, 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, you know, 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 is like u- newer to like ChatGPT work, I'll just like dictate in 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.

   5. CVClaire Vo16:31

      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 like artifacts, these sites live. So can you just walk us through a little bit how, how that works or maybe we can do one, just so people can like understand the power of these sites and-

   6. NBNick Baumann16:56

      Yeah

   7. CVClaire Vo16:56

      ... and how you might use them or what their limitations are even.

   8. NBNick Baumann16:58

      Yeah. I think like for like 10-second description for the technical audience-

   9. CVClaire Vo17:03

      Yeah

   10. NBNick Baumann17:03

       ... it supports a SQL database. Um, it has S3 storage for files, and it even has environmental var- environmental variables you can put there. For the non-technical audience, it's essentially a website that you can store things on [laughs] which is great. And you can also control who sees it. You can, uh, you can filter by, 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.

   11. CVClaire Vo17:29

       Let's do it.

   12. NBNick Baumann17:29

       And, and see how that goes.

   13. CVClaire Vo17:30

       Love to build live.

   14. NBNick Baumann17:31

       Yeah. All right. Uh, 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.

   15. CVClaire Vo17:58

       Make it match the How I AI branding. We use good old AI blurple, purple, um, and black and white. And, um, let's have it, if, 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.

   16. NBNick Baumann18:26

       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 you can deploy it publicly from there if it, if it looks good.

   17. CVClaire Vo18:35

       While this is running, let me make you, make you laugh because this, um, [lips smack] two human 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. 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 phone [chuckles] 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." [chuckles] So I really do feel like people are underusing-

   18. NBNick Baumann19:22

       Yeah

   19. CVClaire Vo19:22

       ... like two-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-

   20. NBNick Baumann19:32

       Yeah

   21. CVClaire Vo19:32

       ... the system, and it doesn't just have to be you alone.

   22. NBNick Baumann19:35

       Yeah. I, I've had times where-

   23. CVClaire Vo19:37

       Right

   24. NBNick Baumann19:37

       ... you know, I need context, like with somebody I work with.

   25. CVClaire Vo19:39

       Yeah.

   26. NBNick Baumann19:40

       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, b- let's just, like, set up a meeting." And I'm like, "No, [chuckles] don't, don't do that. I don't need that. [chuckles] Just, I don't need this to be, like, pretty or anything. Just, just tell me. That's, that's fine."

   27. CVClaire Vo19:58

       So are we at, "This meeting could have been a voice note," like level?

   28. NBNick Baumann20:02

       Yeah, I think so. I mean, all I... It's, it's more like give me information that unstructured however it is-

   29. CVClaire Vo20:09

       Yeah

   30. NBNick Baumann20:09

       ... that my agent can dec- can decipher, and that's, that's good enough for me.
8. 21:24 – 32:30

   Live UGC video demo

   1. CVClaire Vo21:25

      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-

   2. NBNick Baumann21:36

      Mm-hmm

   3. CVClaire Vo21:38

      ... um, that I thought you could show, and 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, um, for the podcast. I also do a lot of this just for like general work stuff. I'm cutting a lot of videos. So, um, tell me, like, how you came to this use case, why you feel it's so useful, and then how, how easy is it to prompt kind of like video editing.

   4. NBNick Baumann22:04

      You know, I, 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, there's, there's a lot of us there, but there's more of us not there. Um, and I think explaining, you know, how you can use these tools, um, in really relatable ways, where you're explaining to look at camera, um, in like forty-five 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 gonna use. Um, but what I'll do is I'm literally just gonna drag these into ChatGPT Work. And then, so what I've done, and I'm gonna share this, but I've created a plugin called UGC Video. And if you let me, let me get the one that I use for... I made a version that has, like, OpenAI branding, but you can actually see it here. And so this basically... Af- 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 nine by sixteen, also four by five." That's great. But what I'll generally do, and I'll dictate 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. Then I show how Codex can do it for me. And then I have a closer about how this skills 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 twenty some odd like video clips. And so what Codex is gonna do, it's gonna start by Processing those clips to get just the transcripts. This will help it understand, like, the story, what we're talking about, and even like my light description will help it understand that. And then what it'll do then... Actually, it's gonna 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 that'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.

   5. CVClaire Vo25:12

      Ugh, you're gonna give me so many ideas because I have, like, deeply abandoned my once great TikTok because I guess, like, UGC's har- like, short form, ugh, short form is hard.

   6. NBNick Baumann25:23

      Yeah.

   7. CVClaire Vo25:23

      Um, 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 can 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, um, which is nice. And so I do that, and then I also do... Like, I teach, like, a three-hour-long workshop, um, 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 a three-hour Zoom clip. And I also do that to, like, clip chapters, clip shorts, do all that sort of... It's just, like, all this tedium of, of video editing. It's quite, quite good at. And then just tell us, like, what does, what does this plugin actually do?

   8. NBNick Baumann26:46

      Yeah, so the plugin's really just based on, like, all the steering I've done, uh, really this week, uh, of, like, making these videos, whether it's just, you know, describing the, 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 break points or how to do captions. Um, 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, and I was like, "Hey, can you make a plugin out of this?" And there's actually a plugin creator skill, um, 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, the happy path that I want.

   9. CVClaire Vo27:31

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

   10. NBNick Baumann27:36

       Yeah

   11. CVClaire Vo27:36

       ... that you can get?

   12. NBNick Baumann27:38

       Yeah. So here was my starting prompt.

   13. CVClaire Vo27:41

       Mm-hmm.

   14. NBNick Baumann27:41

       Again, I just dumped in a bunch of clips. And one thing I want to note, you talked about the tedious stuff.

   15. CVClaire Vo27:47

       Yep.

   16. NBNick Baumann27:48

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

   17. CVClaire Vo27:59

       Yep

   18. NBNick Baumann27:59

       ... and, and just get that off my plate. I don't want to think about it. So yeah, I, I, I started with a pretty similar prompt that I just, I kicked off with a little bit for- 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, I need 4x5 also." So I, I sent that in as, like, a steer, and it was like, "All right, got it. Updating the, updating the delivery matrix." And then this is actually where, you know, I was like, "Why are you asking me questions?" So I had to update the plugin, um, at the same time. And this is what the output looks like. So this is actually a few, few different, like, you know, back-and-forth steers. Um, here we'll... Actually, I 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, what's funny, I don't know if you can see that. It's, it even added blurs to these addresses here.

   19. CVClaire Vo28:55

       Real smart. No, I can see it.

   20. NBNick Baumann28:57

       Yeah. Um, actually I did, like, a couple of these for... Like, they were releasing, like, on Instagram next week, and there's, like, sensitive, like, release material information-

   21. CVClaire Vo29:06

       Yeah

   22. NBNick Baumann29:06

       ... in my Slack that I, like-

   23. CVClaire Vo29:07

       Yeah

   24. NBNick Baumann29:07

       ... bundled 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.

   25. CVClaire Vo29:17

       Wow.

   26. NBNick Baumann29:17

       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.

   27. CVClaire Vo29:29

       I, uh, probably six months ago coded a redactomatic for the How I 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-

   28. NBNick Baumann29:53

       Mm-hmm

   29. CVClaire Vo29:53

       ... kind of like screen shares. But-

   30. NBNick Baumann29:54

       Yeah. And actually that gets back to the, like, I don't, my, I don't even want to deal with the tedious work.
9. 32:30 – 34:04

   How I AI website results

   1. CVClaire Vo32:30

      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.

   2. NBNick Baumann32:42

      [laughs] Right.

   3. CVClaire Vo32:45

      [laughs] We also have-

   4. NBNick Baumann32:46

      Love that

   5. CVClaire Vo32:46

      ... 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.

   6. NBNick Baumann32:54

      Yeah.

   7. CVClaire Vo32:54

      Oh, I see what it is. It's the use cases. So-

   8. NBNick Baumann32:57

      Yeah

   9. CVClaire Vo32:57

      ... 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-

   10. NBNick Baumann33:08

       Yeah

   11. CVClaire Vo33:08

       ... lovely job.

   12. NBNick Baumann33:09

       If you, if you want to get really fancy, you could probably have it have different thumbnails for each clip.

   13. CVClaire Vo33:15

       Yeah.

   14. NBNick Baumann33:15

       We could even have like, use Image Gen to make like a, you know, a singular thumbnail.

   15. CVClaire Vo33:19

       Love it.

   16. NBNick Baumann33:20

       Um-

   17. CVClaire Vo33:20

       Amazing. Okay. There's good old Alex over and over and over again, and then we're gonna have three of me. It just built it. Awesome.

   18. NBNick Baumann33:28

       Yeah. And-

   19. CVClaire Vo33:28

       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.

   20. NBNick Baumann33:34

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

   21. CVClaire Vo33:38

       Mm-hmm.

   22. NBNick Baumann33:39

       Um, I can say, you know, share this. And so now you can, you can put in, you know, whoever you really want to.

   23. CVClaire Vo33:45

       Yep.

   24. NBNick Baumann33:45

       Um, it could be totally publicly available. You could add-

   25. CVClaire Vo33:47

       Yep

   26. NBNick Baumann33:48

       ... um, individual, individual email addresses.

   27. CVClaire Vo33:50

       Yep.

   28. NBNick Baumann33:51

       And it'll share with those folks.

   29. CVClaire Vo33:52

       Amazing. And then how-

   30. NBNick Baumann33:53

       So-
10. 34:04 – 41:33

    Lightning round and final thoughts

    1. CVClaire Vo34:04

       just to recap, we did a couple use cases. So we talked a little bit about voice, high bandwidth, Yappers API, um, 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, an, 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, where 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, um, 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, a huge and very annoying issue. And I'm very happy, um, personally to have seen this, this workflow and get it solved. Um, Nick, a couple questions, uh, lightning round questions for you. We will get you back to all your, all your voice chatting. Question number one 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 into 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 [laughs] how does it, how does it actually work?

    2. NBNick Baumann35:36

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

    3. CVClaire Vo36:33

       Infrastructure. Yeah.

    4. NBNick Baumann36:34

       Yeah.

    5. CVClaire Vo36:34

       I, I imagine we like press a button and like a tube comes down [laughs] around.

    6. NBNick Baumann36:39

       That would be ideal. Yeah, that's, that's what I'm, that's what I aim to operate for.

    7. CVClaire Vo36:41

       When we talk and we can 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, if people really wanted to like feel the AGI, what are, what are the things that you really think are just huge step changes in the last three 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, is the new interface? 'Cause there's so many things that you've shown here.

    8. NBNick Baumann37:16

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

    9. CVClaire Vo37:28

       Yep

    10. NBNick Baumann37:28

        ... I think a lot of people felt the AI then.

    11. CVClaire Vo37:31

        Mm-hmm.

    12. NBNick Baumann37:31

        You know, what, what AI can be became understandable. Like you understand this conception of a, a chatbot that I say things to and it intelligently says, says things back to me. That's, that's pretty cool. And then I think with the advent of code agents and like the code agent harness in particular, I think people in the developer community and like AI tinkerers, they felt this AGI moment where, wow, now, now this AI is going out and like reading files and trading files and like running commands, and this is crazy how I, I tell it to do... I, 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, like barrier to entry with that, where if you're not an engineer or you're not a tinkerer, you know, there's... This is limited to a small-ish group of people. But now, you know, with something like ChatGPT work in the web, I think we're taking a lot of the primitives, um, you know, like the code agent harness, uh, 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?" Um, which I know are, are two, you know, plugins that you can install really quickly, and just monitor those and let me know if anything stands out or anything has, has gone awry. And now they suddenly have this agent that's, you know, maybe twice a day checking their email, checking their finances, and I think that like 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 the small moments that people might kind of like... It might be like a foot in the door for a lot of people.

    13. CVClaire Vo39:17

        Okay, amazing. And then I have one last question I ask every guest, and because you speak to AI, I'm really curious to hear what, what you say. When... I, 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?

    14. NBNick Baumann39:42

        Well, it depends if I'm sitting at my desk or if I'm in my living room. [laughs] Sorry.

    15. CVClaire Vo39:47

        [laughs]

    16. NBNick Baumann39:47

        I guess the, my treatment of, of AI is different. [laughs]

    17. CVClaire Vo39:52

        [laughs]

    18. NBNick Baumann39:53

        Um, it might be all caps in the office as I like bang on my keyboard.

    19. CVClaire Vo39:58

        Yep.

    20. NBNick Baumann39:58

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

    21. CVClaire Vo40:03

        Yeah. [laughs]

    22. NBNick Baumann40:03

        Yeah, try to redirect things.

    23. CVClaire Vo40:06

        I'm just like constantly, constantly being like, "This is trash. Why? Why are you w- why are you this way?"

    24. NBNick Baumann40:13

        [laughs]

    25. CVClaire Vo40:14

        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."

    26. NBNick Baumann40:20

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

    27. CVClaire Vo40:26

        I know. I feel more upset.

    28. NBNick Baumann40:28

        People are, people are... Are you getting more upset?

    29. CVClaire Vo40:29

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

    30. NBNick Baumann40:33

        [laughs] That's interesting. Yeah. All right. Yeah.

Episode duration: 41:34