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

Summary

---

Podcast Summary: How I AI with Claire Vo

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

Date: August 3, 2026
Host: Claire Vo
Guest: Nick Bauman, OpenAI

---

Overview

This episode explores cutting-edge workflows using OpenAI’s ChatGPT Codex, focusing on voice-driven interactions, AI-controlled browser actions, the new ChatGPT Sites feature, and real-world content creation. Nick Bauman walks the audience through expert techniques to delegate tasks, automate workflows, and leverage AI both at work and in daily life—especially through seamless voice and multi-agent experiences. The tone is hands-on, energetic, and aimed squarely at tech-forward professionals and creators eager to maximize AI’s potential.

---

Key Discussion Points & Insights

1. The Evolution of AI Assistants (00:00–03:47)

• AI Moves Beyond Simple Chatbots:
  • Nick reflects on the leap from basic ChatGPT chatbots to today’s Codex powered agents capable of reading files, executing commands, and autonomously managing tasks.
    • “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 the other things on its own.” (Nick Bauman, 00:00)
• Meta Capabilities of Codex:
  • Introduction of thread management: sub-agents, forking, searching memory/context, and why these aren't widely discovered by users.
    • “I do feel like one challenge...is people just don’t know how to discover the features and they’re so rich.” (Claire Vo, 04:40)

---

2. Voice Experience & Natural AI Delegation (03:47–14:36)

• Live Voice Demo & Thread Delegation: (07:00–10:52)

  • Nick triggers Codex via hotkey, asks it to book flights/hotels, manage expense reports—all with voice, showing the assistant running multiple tasks in parallel.
    • “Could you maybe check my calendar, see what my availability is like...?” (Nick Bauman, 07:37)
    • “I’ve started that expense task...It will find the Amazon receipt and stage the Navon report, but not submit it until you confirm.” (Codex AI Assistant, 10:36)

• Why Voice Changes Everything:

  • Higher bandwidth, less friction, more like using a real assistant.
    • “It is just like such a nice delegation experience to be like, hey, can you take care of this?” (Claire Vo, 11:13)
  • AI can create new threads, manage context, and run multiple “Sole” agents simultaneously.
    • “It’s fully able to delegate and manage these...five, six sole threads on its own. Which is great because then you can have it do things on your behalf.” (Nick Bauman, 12:36)

• When/Why Voice Over Text?

  • Nick prefers voice for ideation, planning, context dumping, and high-cognitive-load tasks—less so in crowded environments.
    • “I find the like the thinking process in voice just a lot better...I could dictate for two minutes, send off a long paragraph, get back a couple long paragraphs.” (Nick Bauman, 12:36)
  • Discusses blank chat window syndrome and how voice overcomes it.

• Hot Take: Latency vs. Intelligence (13:26–14:36)

  • Claire: “What do you think matters more in voice experience, latency or intelligence?”
  • Nick: “If there are good tools it can delegate to then I care more about latency...so I still say latency.” (13:35)

---

3. ChatGPT Sites & Real-Time AI-Powered Websites (15:22–19:35)

• How Nick Uses AI to Build Dynamic Sites:
  • Aggregates community tweets and prompt tips via ChatGPT, with the assistant scraping, embedding, and deploying content.
  • On mobile, Nick can dictate updates, manage the site, and deploy—all from his phone.
• ChatGPT Sites Features (16:58–18:26)
  • SQL backend, S3 file storage, granular permissions (public, private).
    • “It supports a SQL database, it has S3 storage for files and even has environmental variables...You can also control who sees it.” (Nick Bauman, 16:58)
  • Demo: Building a public-facing, branded microsite for the podcast’s YouTube content, auto-categorized by tool and function.
• Real-World Anecdotes:
  • Nick and Claire discuss using speakerphones to “crowdsource context” (e.g., Claire helping her mom complete admin tasks by dictating through ChatGPT).

---

4. Advanced Video Editing with Codex (21:26–32:30)

• AI-Driven Content Editing Workflow:

  • Dragging dozens of raw clips into ChatGPT Work.
  • Assistant transcribes, selects best takes, assembles UGC-style (user-generated content) edits, blurs out sensitive info, and handles format guides (vertical, 4x5, captions).
    • “What CODIC is going to do is going to start by processing those clips to get just the transcripts. This will help it understand the story...then it’ll choose the best takes.” (Nick Bauman, 22:03)
  • Custom “UGC Video” plugin created by Nick adds process expertise and output reliability.

• Workflow Benefits:

  • Eliminates tedium, removes self-consciousness for creators.
    • “It’s real embarrassing to edit your own content...So I like to offload...the critique of my performance off to another model.” (Claire Vo, 30:21)

• Technical Recommendation:

  • For speed and quality in parallel video processing, Nick uses "Soul Ultra"—a multi-agent framework inside Codex.

---

5. Practical Publishing & Collaboration (32:30–33:57)

• Launching & Sharing ChatGPT Sites:
  • One-click deploy for internal or public sharing.
  • Permissioned login via ChatGPT account/email whitelist.
    • “You could add individual email addresses and it’ll share with those folks.” (Nick Bauman, 33:33)

---

Notable Quotes & Memorable Moments

• "If anybody has been lucky enough to have an assistant, this is how it gets done...such a nice delegation experience."
  — Claire Vo, 00:51
• "You can hotkey, spin up voice, it can manage these very intelligent five, six 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."
  — Claire Vo, 14:36
• "The highest bandwidth way to communicate with an LLM is just to yap out loud and context dump."
  — Claire Vo, 11:13
• "I feel like so many product assumptions...are built around there’s going to be latency...the more we shrink that the more new products will emerge."
  — Nick Bauman, 14:22
• "It's great back to...it lowers the barrier to entry for stuff like this."
  — Nick Bauman, 31:07
• "I know it’s real embarrassing to edit your own content...I do like having a neutral third party do these cuts."
  — Claire Vo, 30:21
• "In the office, as I bang on my keyboard. At home...share a few expletives, try to redirect things."
  — Nick Bauman, 39:42
• "If we go back to 2022, 2023...with the advent of Cody agents...now this AI is going out and like, reading files and creating files and running commands, and this is crazy."
  — Nick Bauman, 37:15

---

Timestamps for Important Segments

• 00:00–03:47 | Evolution of Codex and undiscovered “meta” features
• 07:00–10:52 | Voice demo—delegating travel, expenses, and real-time browser actions
• 13:26–14:36 | Latency vs. Intelligence hot take
• 15:22–19:35 | ChatGPT Sites—building and updating a site hands-free
• 21:26–32:30 | Video editing with Codex and custom plugins; content workflows
• 32:30–33:57 | Website publishing and sharing mechanics
• 35:36–36:34 | Realities (and awkwardness) of using voice in office settings
• 37:15–39:17 | What feels like “AGI” and next-level user experiences
• 39:42–40:42 | Prompting frustration & strategies when AI “doesn’t listen”

---

Takeaways & Key Skills Shared

• Voice is now a first-class modality: For both superusers and everyday tasks, voice enables high-bandwidth, natural delegation and context management—unlocking new levels of AI-powered efficiency and discovery.
• Codex’s “meta” powers are underappreciated: Thread forking, multi-agent tasking, and ambient context make AI feel like a real executive assistant.
• ChatGPT Sites bridges building and sharing: AI can not only construct full, permissioned websites but iterate them via voice or mobile dictation.
• Content creators can automate with AI: Processes like scripting, selection, editing, and redaction are AI’s sweet spot—even for highly personal content.
• Latency is often more important than pure intelligence for user satisfaction and session completion.
• Mobile + browser + voice = universal agent that’s always available, ambient, and adaptive.

---

Further Info / Contact

• Nick Bauman (@nickbauman_) on X/Twitter – open for questions about Codex, ChatGPT Work, or new OpenAI features.
• Find more episodes and resources at howiaipod.com
• Try the new workflows in ChatGPT Codex and share your use cases.

---

Transcript

[Nick Bauman]

If we go back to, you know, 2022, 2023, around the release of ChatGPT, I think a lot of people felt the AI then a chatbot that I say things to and intelligently says things back to me. I think with the advent of Kodi 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 sell one thing and then it figures out all the other things on its own.

[Claire Vo]

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

[Nick Bauman]

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

[Codex AI Assistant]

Listening. Go ahead.

[Nick Bauman]

Okay. 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?

[Codex AI Assistant]

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

[Claire Vo]

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.

[Nick Bauman]

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

[Claire Vo]

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 of successive here on a mission to help you build better with these new tools. Today we have nick Bauman at OpenAI and he's going to 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.

[Sponsor/Advertisement Voice]

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.

[Claire Vo]

Bolt is different.

[Sponsor/Advertisement Voice]

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.

[Claire Vo]

Connect Stripe or any other mcp, hook

[Sponsor/Advertisement Voice]

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

[Claire Vo]

Nick welcome to How I AI Hello, Claire.

[Nick Bauman]

Thanks for having me.

[Claire Vo]

I am going to 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 code? 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 you feel like people don't really know about or brand new that you think are completely going to change how, how we all work?

[Nick Bauman]

Yeah, I feel like, you know, with yesterday's release of voice, 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, the hotkey, you can trigger this orb that like pops in your screen and no matter where you are in your computer, you can talk to it, it'll talk back to you and it can see your screen, 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.

[Claire Vo]

Yeah, One of the things that 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 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. 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 going to kick off a new thread. And I was like, you're going to do what? Like, what now? And so I do feel one of the challenges with these core, core kind of platforms like Codexes 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

[Nick Bauman]

ChatGPT work experience, you know, people are talking about, you know, should we use a 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, gcal, like whatever you use, it's already there and then you have it all accessible on your phone so you can create these automations, also known as heartbeats. And it's already there. So 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.

[Claire Vo]

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

[Nick Bauman]

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

[Claire Vo]

I'm listening.

[Codex AI Assistant]

Go ahead.

[Nick Bauman]

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

[Codex AI Assistant]

I'll take a look. Let me check that Slack view. Yep, it's the DX team off site 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 Navon this week.

[Nick Bauman]

All right, so 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. What it did is it took an app shot. An app shot is something that you can do or whatever window you have open. You just hit command command. And it essentially takes a smart screenshot loaded with context that can use computer use or browse use on it instantly, but kind of a meta feature. Codex Voice already has that built in. I'm hoping you can help me book my flights and my hotel for the Paris off night. I'm also thinking about sticking around through the weekend and maybe a couple days after. Could you maybe check my calendar, see what my availability is like and see if it's. If it's feasible for me to stick around?

[Codex AI Assistant]

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

[Claire Vo]

Is this using the connectors?

[Nick Bauman]

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

[Codex AI Assistant]

off site 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?

[Nick Bauman]

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, 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 click book now.

[Codex AI Assistant]

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.

[Claire Vo]

So is this chat going to be in? Oh, sorry, I. I'm talking to. I'm talking to his Codex. Invite Claire to the Paris off site, put her up in the ribs, get

[Nick Bauman]

her in business class and honestly we don't. We don't really have a Paris off site scheduled yet, but so much of our DX team is French that I'm hoping that I can, like, you know, start seeding the. The ideas here.

[Codex AI Assistant]

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

[Nick Bauman]

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

[Codex AI Assistant]

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

[Nick Bauman]

Awesome. So right now 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?

[Claire Vo]

Sure, I'll take a look.

[Codex AI Assistant]

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.

[Nick Bauman]

Awesome. So those are both running in the background. I've. 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 handle in the background.

[Claire Vo]

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 and they're like what am I going to ask? What am I going to 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 Hillary 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 guessing the hypothesis here with this voice kind of experience is there's going to be like better discovery of use cases and sort of like more sprawling use cases because people can kind 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 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 full voice pilled? Like where are we?

[Nick Bauman]

Yeah, a few thoughts there. One, I think it's like this iteration itself is like kind of a new primitive in that. Yep. 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, you know, fully, you know, five, six sole threads on its own. Which is great because then you can have it do things on your behalf. Other thoughts there. I find the like the thinking process and voice just a lot better when it comes to. I could dictate for two 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 planning invoice to be really, really effective.

[Claire Vo]

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.

[Nick Bauman]

I would say When I use ChatGPT I put it on high intelligence for voice. I think there's like a middle ground. I think if there are good tools it can delegate to then I care more about latency.

[Claire Vo]

Yeah.

[Nick Bauman]

So I don't know, I still say latency.

[Claire Vo]

Yeah. I think, I think it's the, I think it's what we're going to be talking and this is the Claire vote prediction. I think it's. We're going to 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.

[Nick Bauman]

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 going to be delay, and the more we shrink that we can kind of drop those assumptions and new products will emerge.

[Claire Vo]

Amazing. Okay, so what we've seen here, just to reiterate for people who are maybe not watching or listening, is you can hotkey, spin up voice, it can manage these 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 super intelligence that can get nice stuff done. You mentioned that a little bit earlier that you're also loving like mobile and this combination of dictation and managing through mobile. Can you tell me how being able to do some of this on your phone has changed your workflow? Maybe give me an example of that.

[Nick Bauman]

So I put together a 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 ChatGPT. This was done just with ChatGPT, the ChatGPT app, where I had it use its own in app browser, go through Twitter for a couple hours and then embed these links and kind of add a little bit of description to them. 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 newer to like chatgpt work, I'll just like dictate my phone explain. Like, hey, there's this prompt for like having to manage your inbox and your finances. Can you add this to the site as well? And in terms of actually editing the site, deploying it, that can all happen from ChatGPT work on mobile.

[Claire Vo]

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. 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?

[Nick Bauman]

Yeah, I think for like 10 second description for the typical audience. It supports a SQL database, it has S3 storage for files and 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. 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, we could try building a site live. Let's do it and see how that goes.

[Claire Vo]

I want to build live.

[Nick Bauman]

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.

[Claire Vo]

Make it match the How IA 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.

[Nick Bauman]

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

[Claire Vo]

While this is running, let me make you make you laugh because this too human chat to chat GPT. I did recently with my mother and 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. 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 under using 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 the system. And it doesn't just have to be you alone.

[Nick Bauman]

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

[Codex AI Assistant]

Yeah.

[Nick Bauman]

And I'm like, please just like ramble dictate into Slack and send me like garbage. I don't care. And they're like, 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 fine.

[Claire Vo]

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

[Nick Bauman]

Yeah, I think so. I mean 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.

[Claire Vo]

This episode is brought to you by

[Sponsor/Advertisement Voice]

Hyper Agent, the platform for deploying always on agents that actually run your business with HYP. With 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

[Claire Vo]

with full account context.

[Sponsor/Advertisement Voice]

These aren't chatbots waiting for a perfect prompt.

[Claire Vo]

They're proactive.

[Sponsor/Advertisement Voice]

Learning your preferences and retaining your playbooks and getting better with every run. One user built four agents to run

[Claire Vo]

an outbound sales pipeline.

[Sponsor/Advertisement Voice]

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 IAI AI listeners get a thousand dollars in free inference to start building. Claim [e-mail] howiai okay, so this is

[Claire Vo]

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 that I thought you could show in particularly how, how you prompt it, which is codecs 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 so useful and then how, how easy is it to prompt kind of like video editing?

[Nick Bauman]

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 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 a camera in like 45 seconds is great. And so I started just kind of like going to a park, filming myself filming my camera, getting a smattering of little clips. And so this is from like this 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 get the one that I use for. I made a version that has OpenAI branding, but you can actually see it here. After having gone through a few runs of this, what I've noticed is that just having some guidance around, hey, make sure that we're not entering the safety zone with Instagram ads or let's do these formats. We want 9x16, also 4x5. That's great. But what I'll generally do and I'll stick tape 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 codas 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? 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 like video clips. And so what CODIC 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 I'll do then actually it's going to ask you 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 going to go through the takes and actually process images from them to understand what I'm showing. And then it'll choose 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 use that as guidance to know what's actually useful from these.

[Claire Vo]

You're going to give me so many ideas because I have deeply abandoned my once great TikTok because it's like UGC is hard, like short, 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 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 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 three 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 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 video editing it's quite, quite good at. And then just tell us, like, what does, what does this plugin actually do?

[Nick Bauman]

Yeah, so the plugin is really just based on like all the steering I've done, really this week of like making these videos. Whether it's, you know, describing the kind of formats I need or, you know, that we don't want to have text in certain areas, 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.

[Claire Vo]

And can you show us an app? 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?

[Nick Bauman]

Yeah. So here was my starting prompt again. I just dumped in a bunch of clips. And one thing I want to know, you talked about, like, the tedious stuff.

[Claire Vo]

Yeah.

[Nick Bauman]

Even like little things like going through and deleting bad takes or finding like the right segments. I feel like I'm so willing just to hand that over 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 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 four by five also. So I sent that in as like a steer. And I was like, all right, got it. Updating the delivery matrix. And then this is actually where 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 back and forth steers here. Actually. Haven't watched this full one, but we'll see how it looks. It's insane trying to find an apartment in S.F. 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.

[Claire Vo]

Real smart. No, I can see it.

[Nick Bauman]

Yeah. Actually I did a couple of these for. They were releasing on Instagram next week and there's sensitive release material information by Slack that bubbled up in my ChatGPT work and it did this insanely granular work of 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 out 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.

[Claire Vo]

I probably six months ago coded a redactomatic for the How I 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. I need to try it again with codecs because it's probably the one challenge we have is the blurs following kind of like screen shares.

[Nick Bauman]

But yeah, and actually that gets back to the like, I don't, my. I don't even want to deal with the tedious work. Like not only actually it's a non starter that I'm going to make blurs automatically do that manually. That's just, that's not going to happen.

[Claire Vo]

No.

[Nick Bauman]

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 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 to leave it to the chat GPT app.

[Claire Vo]

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

[Nick Bauman]

Yeah, I know it's, it's, it's great back to like the it. Like it's a lower. Is 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 three videos. I suddenly recorded the three videos over the course of like an hour and a half, couple days ago. And then I uploaded like 50 or 60 clips. Yep. And I dictated like what the different narratives those three videos were. And because I have a plugin and a task that already understands what I want, it took a while, I went to bed and I came back to it. But I had what I needed and we actually shipped one to our Instagram a couple days ago.

[Claire Vo]

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

[Nick Bauman]

Yeah, I would. In my experience, there's just so many as much as anything, just for speed. There's so many little like micro tasks 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 Soul Ultra is, is it's basically this framework for multi agent for five, six, soul. And so I find that it's just more efficient and I get better outputs when I use the Ultra. Love it.

[Claire Vo]

Okay, cool. Let's see if the How I AI website is up and running. Look at that. Black and purple and white. Just like I said. We also have AI identify which thumbnails are going to do the best. By the way, this episode, just so you know, it's all look, ma, no hands. We had some problems. 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 codecs, browser use, where I let it shop for me for my Hawaiian vacation. And it did quite a lovely, lovely job.

[Nick Bauman]

If we wanted to get really fancy, we 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.

[Claire Vo]

Love it. Amazing. Okay, there's good old Alex over and over and over again. And then we're going to hit 3andMe. It just built it. Awesome. And then this can be published. Just like remind me how it gets published, who I can share it with, how that all works.

[Nick Bauman]

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

[Claire Vo]

Amazing. And then how do you log in?

[Nick Bauman]

It's logging with ChatGPT.

[Claire Vo]

Great, easy peasy. I do have a ChatGPT account underneath that email address. So we are, 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 yappers, API, just basically like talking to a computer empowered assistant that can just go do a bunch of your work for you with access to browser and other things including just being able to screenshot whatever's on the screen and have context. We did 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. 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 models 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 one is on that topic. In this world where we're all loving our ChatGPT voice experience, is everybody in the OpenAI office just like mumbling to themselves and to their computer? How are we going to intersect all this voice capability with the realities of existing around humans that find all this chitter chatter annoying? How does it actually work?

[Nick Bauman]

I think it's like a, 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 hop into. And I see people like hopping in there for not calls or 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 better. There's a good version, and that's using voice, but it's not ideal for our current, you know, office makeup infrastructure.

[Claire Vo]

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

[Nick Bauman]

That would be ideal. Yeah, that's. That's what I'm talking about.

[Claire Vo]

Press our button and the tube. The tube goes up. Okay, we're gonna. We're gonna figure this out until we get the direct Codex to mind connection, which I'm sure will be a 2027 release. Okay, second question. If people really wanted to feel the AGI, what are the things that you really think are just huge step changes in the last three months? Maybe voice aside, what is 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

[Nick Bauman]

shown here 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 2022, 2023, around the release of ChatGPT, I think a lot of people felt the AI, then what AI can be became understandable. 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 Cody agents and the Cody 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 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 is 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 work in 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 two plugins that you can install really quickly. Just monitor those and Let me know if anything stands out or anything has gone awry. Now they suddenly have this agent that's maybe twice a day checking their email, checking their finances. I think that small thing, you know, when they first get a notification, you know, letting them know maybe the package has arrived or there's some weird charge. I think those are, like, the small moments that people might kind of like. It might be like a foot in the door for a lot of people.

[Claire Vo]

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

[Nick Bauman]

Well, it depends if I'm sitting at my desk or if I'm in my living room. I guess the. My treatment of AI is different. It might be all caps. In the office, as I bang on my keyboard. Yeah. At home, alter on dictation, maybe share a few expletives, try to redirect things.

[Claire Vo]

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

[Nick Bauman]

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

[Claire Vo]

I feel more upset.

[Nick Bauman]

People, people, are you getting more upset?

[Claire Vo]

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

[Nick Bauman]

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.

[Claire Vo]

Okay, well, Nick, this has been super fun. Where can we find you?

[Codex AI Assistant]

How.

[Claire Vo]

How can we be helpful?

[Nick Bauman]

Yeah, find me on Twitter or X My name Nick Bauman. Underscore. If you have any Questions about Codex, ChatGPT work, anything, we're releasing OpenAI. Feel free to reach out to me. DMs are open. Great to be out with you, Claire.

[Claire Vo]

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 [e-mail] See you next time.