WEBVTT
00:00:01.520 --> 00:00:08.160
Many people talking about the new ChatGPT voice are calling it their AGI moment.
00:00:08.960 --> 00:00:11.199
And I don't disagree.
00:00:11.439 --> 00:00:20.800
Yeah, it's changed how I work in the short amount of time that it's been out, but there's usually at least a handful of updates every quarter that do that.
00:00:20.960 --> 00:00:26.480
But this update from ChatGPT Voice changes how I think about work.
00:00:26.800 --> 00:00:32.560
And that has rarely happened in the nearly four years I've been doing the everyday AI show.
00:00:32.719 --> 00:00:38.560
It's like if you've ever seen Iron Man, ChatGPT Voice is literally like having your own Jarvis.
00:00:38.880 --> 00:00:52.000
Whether you're in front of your computer or across the country, like I was the past couple of days, you can ramble hands-free and natural language, and the desktop version of ChatGPT will literally just control itself.
00:00:52.079 --> 00:00:59.119
It'll do anything on your computer that any skilled human could do, but you don't have to be there doing any of it.
00:00:59.359 --> 00:01:08.799
And I really put this through its paces yesterday as I took about an hour-long walk in controlling my home computer through my iPhone.
00:01:08.879 --> 00:01:26.159
And my computer at home was creating documents, using other desktop programs like Claude Code, organizing my cloud storage, triaging emails and drafting replies, and planning this very show by transcribing YouTube reviews and, say, bookmarks that I just didn't have time to get to, creating images, all that stuff.
00:01:26.319 --> 00:01:29.280
I just gave commands and the work was just done.
00:01:29.519 --> 00:01:39.760
So obviously, OpenAI can't call this thing Jarvis mode, but you can see how that might be a more fitting description than the moniker of Chat GPT voice.
00:01:39.840 --> 00:01:46.319
But I will say this I've used literally thousands of AI tools and features over the past four years of doing everyday AI.
00:01:46.480 --> 00:01:52.079
And Chat GPT voice has instantly become the number one most useful ever.
00:01:52.799 --> 00:01:55.280
So, what is this ChatGPT voice thing?
00:01:55.359 --> 00:01:56.879
And why is it so special?
00:01:56.959 --> 00:01:59.040
And why haven't you used it yet?
00:01:59.200 --> 00:02:05.359
Well, we'll break all those down as we put AI to work on Wednesdays on Everyday AI.
00:02:05.599 --> 00:02:07.680
All right, here is the big picture.
00:02:07.920 --> 00:02:12.240
ChatGPT voice became an agent management interface.
00:02:12.479 --> 00:02:24.719
So this just came out, it hasn't even been out a full week since OpenAI announced it, and it lives inside of the desktop version of Chat GPT Work and Codex, which is the same thing, by the way.
00:02:24.879 --> 00:02:28.800
So ChatGPT Voice is powered by the new GPT Live model.
00:02:29.120 --> 00:02:30.879
A little confusing, but we'll break it down.
00:02:31.039 --> 00:02:40.719
And that somewhat confusing rollout, I think, made for this being the undisputed most criminally underhyped release in AI ever, right?
00:02:40.879 --> 00:02:49.680
Sometimes you see these like little releases come out, and everyone's talking about it, like, oh my gosh, this thing's gonna, you know, break how we all work, it's gonna take away all these jobs, it's gonna do all these things, right?
00:02:49.840 --> 00:02:57.599
Uh, Chat GPT voice uh, I don't think people are talking about it, right?
00:02:57.759 --> 00:03:06.639
I'm very uh ears to the ground uh when it comes to these kind of things, and people should be talking about this and using this more, and that's why we're gonna be going over it on today's show.
00:03:06.719 --> 00:03:09.439
So stick with me for the next 25-ish minutes.
00:03:09.520 --> 00:03:10.800
And here's what you'll learn.
00:03:10.879 --> 00:03:19.520
You're gonna know how the ordinary voice mode differs from the new uh Chat GPT voice launched inside work or codex.
00:03:19.759 --> 00:03:29.280
You're gonna know which evidence and approval rules that you need to keep authoritative sounding updates accountable because you can't just trust the voice and never go back to it.
00:03:29.439 --> 00:03:38.560
And I'm gonna give you the seven advanced chat GPT voice uses that you're gonna want to start using and apply to your workflows immediately.
00:03:38.800 --> 00:03:39.599
Let's get into it.
00:03:39.759 --> 00:03:41.120
Welcome to everyday AI.
00:03:41.199 --> 00:03:44.080
My name's Jordan Wilson, and well, this thing's for you.
00:03:44.240 --> 00:03:53.840
This is your daily live stream podcast and free daily newsletter, helping everyday business leaders like you and me not just keep up with AI, but how you can use all of these updates.
00:03:54.000 --> 00:03:55.039
I tell you what matters.
00:03:55.199 --> 00:03:57.919
You go put it to work, grow your company and your career.
00:03:58.080 --> 00:04:06.240
So please, if you haven't already, subscribe to the podcast on Apple, Podcasts, or Spotify, and make sure you go to our website at your everydayai.com.
00:04:06.400 --> 00:04:14.479
We're gonna be not only highlighting the big uh takeaways from today's show, but also giving you all of the other AI news you need to know to stay ahead.
00:04:14.719 --> 00:04:16.800
All right, so let's get into it.
00:04:17.040 --> 00:04:21.199
So um on Wednesdays, we put AI to work on Wednesday.
00:04:21.360 --> 00:04:24.800
So the latter half of this will be kind of demo based.
00:04:24.879 --> 00:04:25.920
So FYI.
00:04:26.079 --> 00:04:40.879
Uh, if you do want to see the video version of this, it will obviously be somewhat visual because uh if everything goes correctly, which for an unedited, unscripted demo um of a super smart AI taking over my computer, who knows what could go wrong, right?
00:04:40.959 --> 00:04:49.680
But you can always catch the video version of this on our website at your everydayai.com or on LinkedIn, YouTube, Twitter machines.
00:04:49.839 --> 00:04:50.240
All right.
00:04:50.399 --> 00:04:54.399
Uh, but let's first start with the two basic settings that you have to understand.
00:04:54.480 --> 00:05:00.639
It's kind of settings slash uh, you know, getting your mindset right on what's named what.
00:05:00.800 --> 00:05:11.040
And this is important um because there's a lot of confusion on this, because most people are like, okay, well, yeah, uh Chat GPT voice, I know it's it's not new, right?
00:05:11.120 --> 00:05:13.759
I can just I've been able to talk to Chat GPT for a while.
00:05:13.839 --> 00:05:14.800
So yes and no.
00:05:14.879 --> 00:05:21.839
Uh I I essentially want to take you through four different phases or buckets of using your voice to interact with Chat GPT.
00:05:21.920 --> 00:05:23.279
All right, so number one, dictation.
00:05:23.360 --> 00:05:24.959
That's been around for a very long time.
00:05:25.120 --> 00:05:28.079
Literally, some people think that that's what this is, that's not.
00:05:28.240 --> 00:05:29.600
So dictation, right?
00:05:29.680 --> 00:05:37.680
You can click the little uh microphone button um on the chat GPT interface, and it will you can talk and it's just gonna turn your speech into text.
00:05:37.759 --> 00:05:39.759
That's dictation, that's not what we're talking about.
00:05:39.920 --> 00:05:44.720
Then there's the old voice mode, uh, which was technically called advanced voice mode.
00:05:44.800 --> 00:05:46.800
There was a different voice mode before that, all right.
00:05:46.879 --> 00:05:49.920
But that was more of the walkie talkie, uh, right?
00:05:50.000 --> 00:05:53.680
That's the turn by turn uh conversation uh mode.
00:05:53.920 --> 00:05:57.519
So that was what you know, a month ago, that's what OpenAI had.
00:05:57.600 --> 00:05:59.439
That's what Claude has today.
00:05:59.600 --> 00:06:04.240
Nothing wrong with that, but that's not what we really want out of a voice mode.
00:06:04.480 --> 00:06:09.040
What we want is, well, the actual engine driving this, and that is GPT Live.
00:06:09.199 --> 00:06:13.680
So that is what is called this kind of full duplex voice mode.
00:06:13.920 --> 00:06:16.720
So that means, and you'll see an example of this.
00:06:16.879 --> 00:06:22.879
Um, the voice mode, GPT Live, um, can talk and listen at the same time.
00:06:23.040 --> 00:06:29.120
Uh, it can, as it's talking to you, it's using another model in the background to call tools, look up information on the internet.
00:06:29.439 --> 00:06:35.360
You know, maybe it's running a little bit of code to give you an answer to something that's not as easy to find as you might think.
00:06:35.519 --> 00:06:35.759
All right.
00:06:35.839 --> 00:06:38.480
So that's that natural, interruptible conversation.
00:06:38.560 --> 00:06:42.720
It's just like talking with a real human, but not like walkie-talkie style.
00:06:42.800 --> 00:06:43.519
Uh, right.
00:06:43.920 --> 00:06:48.000
So, not to be confused, but that's not what we're talking about here, right?
00:06:48.079 --> 00:06:51.519
That came out two weeks ago, and maybe you've already used that and it's really good.
00:06:51.680 --> 00:06:52.399
This is different.
00:06:52.480 --> 00:06:54.079
This is Chat GPT voice.
00:06:54.240 --> 00:07:04.560
So, this is essentially that voice model, that full duplex GPT live voice model um that has been available in Chat GPT for about you know two and two or three weeks now.
00:07:04.800 --> 00:07:09.120
Now that lives inside of Chat GPT work or codex.
00:07:09.279 --> 00:07:13.040
So this is the um the version that you download on your computer.
00:07:13.199 --> 00:07:17.839
So there is no chat GPT voice when you go to chat GPT.com.
00:07:18.000 --> 00:07:19.360
I know that's confusing.
00:07:19.439 --> 00:07:21.600
That's going to be using the GPT live.
00:07:21.680 --> 00:07:27.199
So Chat GPT voice is available on the desktop version, all right.
00:07:27.360 --> 00:07:32.000
And that's kind of where your um the thing that's Jarvis mode, right?
00:07:32.079 --> 00:07:39.680
Where it can literally access all of your data, it can use your computer, it can do literally anything that a human sitting down in front of your computer can't.
00:07:39.759 --> 00:07:45.040
Whereas, you know, the normal GPT live, the new smarter thing, it's cool to chat with, right?
00:07:45.120 --> 00:07:46.720
But it's not going to actually do your work.
00:07:46.879 --> 00:07:54.399
Now we all finally have a super smart uh you know co-worker sitting down that we can literally just talk to like a real person.
00:07:55.120 --> 00:07:55.600
All right.
00:07:55.759 --> 00:08:00.879
So that's kind of the uh the iteration of the different types of voice inside of Chat GPT.
00:08:00.959 --> 00:08:04.800
All right, so basic setting number two, which I kind of talked about it.
00:08:04.879 --> 00:08:13.759
So chat GPT voice itself is just the GPT Live model, plus bringing in this agenc execution layer.
00:08:13.839 --> 00:08:22.800
Um, so aside from it being able to actually complete work for you, which the GPT Live can't really do, at least not fully, uh, right.
00:08:22.959 --> 00:08:29.839
The difference here is it has access to all of your data and connectors, which GPT Live doesn't, right?
00:08:30.000 --> 00:08:35.440
So that's the one thing that is missing from GPT Live that I was using it, uh, right.
00:08:35.600 --> 00:08:42.879
If you want to say, hey, check my email, or if you have some MCP servers connected inside of ChatGPT, you know, it can't access those.
00:08:42.960 --> 00:08:51.279
Um, it can you can upload a file to GPT Live and it will be able to go through and talk about that file, but it can't access all of your dynamic data.
00:08:51.440 --> 00:09:02.080
As an example, I probably have not a ton, uh, right, because my tech stack is not super fat, but I probably have at least 30 different either connectors or MCPs.
00:09:02.240 --> 00:09:18.639
So now with ChatGPT voice on the desktop version of ChatGPT work or codex, I can instantly talk and grab data from any of those, but also I can output or have the agent output work for me, but I can just command it all via Jarvis mode, right?
00:09:18.879 --> 00:09:20.639
So here's how it works.
00:09:20.879 --> 00:09:29.679
All right, you uh the the Chat GPT voice can listen, it can speak and coordinate all at the same time and actually do your work.
00:09:29.919 --> 00:09:32.639
All right, so there is a little button, right?
00:09:32.720 --> 00:09:35.440
So if you hover over it, it just says start voice chat.
00:09:35.519 --> 00:09:41.600
So not to be confused uh with the button on the left, which is just the microphone button, which is the dictate button.
00:09:41.759 --> 00:09:45.120
All right, so you're gonna start a voice chat and this little orb, right?
00:09:45.279 --> 00:09:46.720
This little chat GPT orb.
00:09:46.799 --> 00:09:48.080
I don't know if there's an official name for it.
00:09:48.159 --> 00:09:52.559
I just call it the, you know, you can call it the voice visualization or just the orb.
00:09:52.639 --> 00:09:54.080
So I'm just gonna call it the orb.
00:09:54.159 --> 00:09:54.480
All right.
00:09:54.559 --> 00:09:59.279
So that's when this uh kind of chat GPT voice mode is um working.
00:09:59.519 --> 00:10:01.440
So also a little confusing.
00:10:01.519 --> 00:10:06.559
That's the same orb that comes on if you're just using GPT Live inside of chat GPT.com.
00:10:06.639 --> 00:10:11.279
All right, so you just gotta be using this if you're trying to follow along at home, which I encourage you to do.
00:10:11.440 --> 00:10:20.559
Uh, you know, make sure you're obviously using the desktop version of ChatGPT work or codex, which again, a little confusing, is the exact same app.
00:10:20.639 --> 00:10:24.960
There's just a drop down at the top because people are always like, wait, I don't have codex.
00:10:25.200 --> 00:10:26.639
Yes, you do, it's chat GPT work.
00:10:26.799 --> 00:10:28.399
And people are like, I don't have ChatGPT work.
00:10:28.480 --> 00:10:30.960
And it's like, yes, you do, it's codex, it's the same thing.
00:10:31.120 --> 00:10:37.519
All right, so you have to be doing this inside of that download, uh, the downloadable program on your computer.
00:10:37.759 --> 00:10:39.600
And well, it's just neural.
00:10:39.679 --> 00:10:45.039
It's going to be able to listen and run these models in the background and literally do anything that you can do on your computer.
00:10:45.519 --> 00:10:56.879
So uh there's multiple layers, and kind of the biggest differentiator that I think uh versus uh ChatGPT voice and GPT Live, uh, the voice layer just talks.
00:10:57.039 --> 00:11:05.360
Now we have this new layer that we're combining it with all of the capabilities um of codecs, is it just is going to work, right?
00:11:05.519 --> 00:11:07.440
It's gonna execute your work for you.
00:11:07.600 --> 00:11:14.159
And just for ease of uh not saying the wrong thing too many times, from here on out, I'm just gonna say codex, all right.
00:11:14.240 --> 00:11:16.960
Um, but it's the same thing as chat GPT work, right?
00:11:17.120 --> 00:11:19.600
But there's too many uh Chat GPTs flying around.
00:11:19.679 --> 00:11:21.039
So I'm just gonna say codex, right?
00:11:21.120 --> 00:11:24.799
That is the uh version that you download and run on your computer.
00:11:25.279 --> 00:11:25.919
All right.
00:11:26.240 --> 00:11:35.919
So let's quickly go into the seven advanced chat GPT voice uses, uh, and then we're gonna go straight into the demo and hopefully it all works.
00:11:36.000 --> 00:11:40.799
Um, but I'm gonna be doing some of these advanced uh use cases as we go along.
00:11:40.960 --> 00:11:44.000
But these are also kind of best practices as well.
00:11:44.240 --> 00:11:50.320
So number one, and this is uh a difference in how these threads work.
00:11:50.559 --> 00:11:58.159
So you cannot go and pick up an old thread and start a new Chat GPT voice conversation in there.
00:11:58.320 --> 00:11:58.720
All right.
00:11:59.039 --> 00:12:00.559
You can't do it, unfortunately.
00:12:00.720 --> 00:12:01.919
That would be great if you could.
00:12:02.080 --> 00:12:08.720
Um instead uh you are going to uh start a new chat, okay?
00:12:09.039 --> 00:12:17.840
So whether that's inside of a current project, or if you just go down and start a new chat that's not attached to a project.
00:12:18.000 --> 00:12:26.080
So um you can start any new chat um by just clicking the uh start new voice chat button.
00:12:26.240 --> 00:12:28.240
Um, and that's how you start.
00:12:28.399 --> 00:12:30.000
But here's the thing, right?
00:12:31.039 --> 00:12:33.600
It knows everything, right?
00:12:33.679 --> 00:12:35.440
And it controls everything.
00:12:35.919 --> 00:12:36.240
All right.
00:12:36.320 --> 00:12:41.600
And that is just I can't emphasize how big that is, right?
00:12:41.679 --> 00:12:44.000
I've done this many times, I've done live demos of it.
00:12:44.080 --> 00:12:45.600
I just checked again, right?
00:12:45.919 --> 00:12:48.639
Code, uh, let's let's talk about Claude Code, right?
00:12:49.039 --> 00:12:55.279
Claude code doesn't know anything within what's happening under its own roof, right?
00:12:55.440 --> 00:13:01.120
Unless it just happens to commit something to its memory, um, which it just does that haphazardly.
00:13:01.279 --> 00:13:02.960
Otherwise, it knows nothing, right?
00:13:03.120 --> 00:13:08.240
So all of those conversations, you know, let's just say that you're talking about Claude Cowork, right?
00:13:08.399 --> 00:13:16.000
All of those conversations, unless it just commits something to memory, which, you know, maybe it does one to two percent of the content in there.
00:13:16.240 --> 00:13:25.440
If you start a new chat, it knows absolutely nothing, which makes something like Claude Desktop, in my opinion, extremely useless, right?
00:13:25.600 --> 00:13:26.879
That's why I don't really use it.
00:13:26.960 --> 00:13:30.559
I mean, I use it to audit things that I build inside codecs, right?
00:13:30.639 --> 00:13:35.840
Uh, but the big thing with this new voice mode is it can understand any thread anywhere.
00:13:36.000 --> 00:13:36.399
All right.
00:13:36.480 --> 00:13:41.840
So you can direct it to, hey, go look in this project, uh, right, find this project folder.
00:13:42.000 --> 00:13:46.080
So it can research any thread, see what was done, understand it.
00:13:46.159 --> 00:13:49.279
Um, it can send a message to any of those threads.
00:13:49.519 --> 00:13:58.559
So it is just absolutely crazy how a voice mode, because the old advanced voice mode couldn't do that.
00:13:58.799 --> 00:14:00.720
Um, right now you can't.
00:14:00.799 --> 00:14:05.519
And this is again combining the power of codex uh with this technology, right?
00:14:05.600 --> 00:14:09.039
So I'll just walk you through how I was using this on my walk this morning.
00:14:09.120 --> 00:14:11.840
I know the name of most of my projects inside codex.
00:14:12.080 --> 00:14:21.039
And I just said, hey, walk me through every single major thread in these, you know, project folders one by one at the end.
00:14:21.200 --> 00:14:25.519
Um, you know, give me a brief update and what next steps may be.
00:14:25.679 --> 00:14:36.320
If you're not sure of a next step, suggest one for me based on, you know, what you know about me, what's in my uh agents MD file for that folder or for you know, codex in general.
00:14:36.399 --> 00:14:39.039
So it knows my overarching goals and it knows the project goals.
00:14:39.120 --> 00:14:43.759
And then it's gonna go in there, it's gonna look at all that context and then just make me make decisions, right?
00:14:43.919 --> 00:15:00.799
This is why I think on my walk uh uh sorry, yesterday, um, I was more productive in that one hour on my phone, just talking in my earpods, than I would have been probably in three or four hours doing the exact same thing in front of my computer.
00:15:00.960 --> 00:15:02.639
I talk about this all the time.
00:15:03.360 --> 00:15:05.600
The internet is made to distract you, right?
00:15:05.679 --> 00:15:10.399
And even for me, it can be distracting working in codecs, right?
00:15:10.480 --> 00:15:13.600
Because I have all my browser tabs open inside codecs.
00:15:13.759 --> 00:15:23.679
Um, so something about just the combination of rambling and being able to control any of these threads um and just having that real focused time.
00:15:24.159 --> 00:15:25.519
I got so much done, right?
00:15:25.600 --> 00:15:26.639
And in that one hour walk.
00:15:26.799 --> 00:15:38.320
But, anyways, uh kind of advanced tip number one is know that you can with your voice, any new chat can understand, read, write, and do anything to any thread.
00:15:38.399 --> 00:15:41.919
So it doesn't really matter for me from an organizational perspective.
00:15:42.080 --> 00:15:46.399
I would really like to just be able to go into a certain thread and pick it up from there, right?
00:15:46.480 --> 00:15:50.240
I have all these uh chief of staff threads inside of each project folder.
00:15:50.399 --> 00:15:54.080
That would be preferable for me because I like things to be a little organized, right?
00:15:54.159 --> 00:16:02.799
And then you have this chat that's down there in your recense, but overall it's okay because when it does make changes, it will actually go in there and send a message in those chats.
00:16:02.879 --> 00:16:04.240
So it's not like it gets lost.
00:16:04.320 --> 00:16:07.279
And I do have another advanced tip later that can help with this.
00:16:07.440 --> 00:16:17.039
All right, so uh number two, GPT Live can't use connectors and codecs with Chat GPT Live can't.
00:16:17.200 --> 00:16:22.799
So I already referenced this, but this is huge because GPT Live by itself, it's great.
00:16:22.879 --> 00:16:26.159
Um, right, it's more of I think an advanced party trick.
00:16:26.240 --> 00:16:47.519
And I do hope, um, and I know the team has alluded to this online that they are going to eventually bring connectors to GPT Live, but at least for me and how I want to use um, you know, Chat GPT, I need it to be connected to those, you know, 30 or so uh, you know, connected integrations and MCP servers, right?
00:16:47.600 --> 00:16:52.720
If not, it's just you know a better way to browse the internet, um, which is fine, right?
00:16:52.799 --> 00:16:54.720
But I really want to use this to get work done.
00:16:54.879 --> 00:16:58.399
And that is why this combination inside codex is amazing.
00:16:58.480 --> 00:16:59.600
And I don't know why.
00:16:59.759 --> 00:17:03.279
I literally didn't see anyone talk about this or reference this, right?
00:17:03.360 --> 00:17:10.960
I, you know, I follow the the chatter and you know, I've watched a couple of videos of people giving their uh opinions on this, and no one is mentioning this, right?
00:17:11.119 --> 00:17:25.519
This is the biggest unlock right there to be able to go and go through your entire inbox, to go through your uh, you know, everything in Slack and to be able to talk about it and just say, yes, send this, yes, draft this, uh, no, save that to my Google Drive, right?
00:17:25.680 --> 00:17:27.839
Just to be able to go through all those things.
00:17:27.920 --> 00:17:31.119
Uh is it's this is what people have been wanting for so long.
00:17:31.279 --> 00:17:33.039
This is the Jarvis, right?
00:17:33.119 --> 00:17:34.079
Hey, what's important?
00:17:34.240 --> 00:17:46.880
Go look in all of, you know, go look in my in my CRM, uh, go look in my uh I don't know, ERP, alphabet soup, whatever you want to say, my my my drive, my linear, whatever programs you're using that are connected inside codecs.
00:17:47.039 --> 00:17:52.799
Go through all those, triage those, ask me what you want, you know, what are the most important decisions I need to make.
00:17:52.880 --> 00:17:55.359
And if you have read, write access, right?
00:17:55.519 --> 00:18:00.720
You can just start making those decisions in codecs and actually just go do the work in those programs for you.
00:18:01.039 --> 00:18:01.359
All right.
00:18:01.440 --> 00:18:02.400
So that's number two.
00:18:03.119 --> 00:18:05.599
Connectors is a big unlock.
00:18:06.079 --> 00:18:10.640
All right, number three, um, you can schedule, right?
00:18:11.359 --> 00:18:14.960
The same way that you would um inside of ChatGPT.
00:18:15.440 --> 00:18:28.000
So yeah, this is another one of those things that you can't overlook just that you're using voice mode, you can't overlook just the normal power of ChatGPT, right?
00:18:28.160 --> 00:18:38.400
So one of the things um if you use Chat GPT online or uh the ChatGPT work online um is you can have repeatable tasks.
00:18:38.480 --> 00:18:39.839
So even when you're talking, right?
00:18:39.920 --> 00:18:40.880
I did this a couple of times.
00:18:40.960 --> 00:18:43.519
I'm like, ah, I'm gonna keep missing this thing, right?
00:18:43.680 --> 00:18:49.759
So, you know, I said, hey, you know, every you know, Monday at 7 a.m., you know, run this task.
00:18:49.839 --> 00:19:02.720
This thing that we just did together that, you know, me and uh ChatGPT just collaborated on via this uh ChatGPT voice, that needs to be run, you know, every Monday morning or every Friday afternoon or you know, every day at 4 p.m.
00:19:03.119 --> 00:19:10.079
This that what we just did, let's turn that into a skill and then let's uh have this be a scheduled run.
00:19:10.160 --> 00:19:11.839
So another big uh thing.
00:19:11.920 --> 00:19:17.920
So, you know, as an example, maybe every single day you want to go and through and see any new lead that's come in via HubSpot.
00:19:18.079 --> 00:19:23.440
Uh, you want to enrich that data with clay, and then you know, use the condo MCP.
00:19:23.519 --> 00:19:29.440
That's one I use to help manage my LinkedIn messages to see if you have a LinkedIn connection with those people, right?
00:19:29.519 --> 00:19:32.640
So you can literally do that all via voice first.
00:19:32.799 --> 00:19:38.640
It's gonna learn how to do it all, and then you can say turn that into a skill, run that every single day at 9 a.m.
00:19:38.960 --> 00:19:44.160
Um, and then you can literally, once it's done, go and talk and be like, hey, what happened here?
00:19:44.319 --> 00:19:44.640
Right.
00:19:44.880 --> 00:19:51.119
That process right there, as an example, going into your hub spot, seeing who's new, going in, enriching all that in clay.
00:19:51.200 --> 00:19:54.000
Um, and then, you know, seeing which of these people, right?
00:19:54.079 --> 00:19:58.160
If especially if you're in B2B enterprise sales or SaaS sales, right?
00:19:58.240 --> 00:20:01.119
You know, and you have a big LinkedIn network, you know, like I do.
00:20:01.279 --> 00:20:04.720
That's something that takes a lot of time to do all those things manually, right?
00:20:04.799 --> 00:20:06.240
That might be every single day.
00:20:06.319 --> 00:20:10.000
I don't know if you're an SER, BDR, that might be a third of your day.
00:20:10.160 --> 00:20:11.519
It can be done for you, right?
00:20:11.680 --> 00:20:14.160
Set it up once in ChatGPT voice, set it up as a schedule.
00:20:14.240 --> 00:20:18.400
And then every day you can also be like, hey, check in, walk me through, give me a game plan on this.
00:20:18.640 --> 00:20:25.759
And, you know, in a 10-minute uh ChatGPT voice conversation, you've already done what would have normally taken you three hours and 10 minutes.
00:20:26.000 --> 00:20:27.519
All right, let's go next.
00:20:27.680 --> 00:20:31.359
Number four, uh, stack multiple tasks at once.
00:20:31.519 --> 00:20:33.440
Yeah, you don't just have to give one.
00:20:33.599 --> 00:20:39.359
Uh, you can just kind of ramble on and just keep giving more and more assignments, you know, as you are going back and forth.
00:20:39.519 --> 00:20:42.480
Remember, sometimes Chat GPT will interrupt you.
00:20:42.640 --> 00:20:47.200
You can interrupt it, which is actually fine because that's how a normal conversation goes, right?
00:20:47.519 --> 00:20:51.039
Normal business conversation, sometimes you just interrupt each other, right?
00:20:51.119 --> 00:21:06.640
You might not do that in a big business meeting or if you're meeting with the president of the company, but if you're working with colleagues or people on your team, you probably interrupt each other all the time because if you see someone's going down the wrong path, you don't necessarily want to give them 30 seconds or three minutes to keep going down that path.
00:21:06.799 --> 00:21:08.400
You're like, oh no, no, wait, hold up.
00:21:08.480 --> 00:21:09.680
That's not what I was talking about.
00:21:09.839 --> 00:21:11.519
Let's let's rewind a little bit, right?
00:21:11.599 --> 00:21:22.799
You can do the exact same thing, uh, but also just stack those multiple tasks and the voice will just only return when it needs more uh information from you or when it has updates.
00:21:23.119 --> 00:21:27.279
All right, the big unlock here, use your iPhone.
00:21:27.359 --> 00:21:27.839
My gosh.
00:21:27.920 --> 00:21:33.119
But it's a little tricky because remember, all right, uh Codex doesn't have an app.
00:21:33.200 --> 00:21:34.640
It is in the ChatGPT app.
00:21:34.720 --> 00:21:36.079
So confusing part here.
00:21:36.240 --> 00:21:44.480
If you go into the ChatGPT app and you're looking for that uh little button I told you to push, that's just gonna launch GPT live, which is not what you want.
00:21:44.720 --> 00:21:56.400
So you're gonna go onto your iPhone, you're gonna click remote, then at the bottom of the screen, uh you're gonna click that um that button to start a um Chat GPT voice.
00:21:56.480 --> 00:21:56.880
All right.
00:21:56.960 --> 00:21:59.839
So don't just open your uh Chat GPT app.
00:22:00.240 --> 00:22:03.359
On your iPhone and click the voice chat button.
00:22:03.519 --> 00:22:08.400
You need to first click remote because that's essentially then at that point, and this is what I was doing today.
00:22:08.559 --> 00:22:11.279
That's how you are literally on the phone, right?
00:22:11.359 --> 00:22:13.119
For me, quite literally hands free.
00:22:13.200 --> 00:22:21.279
I had an AirPod, you know, one AirPod in my ear, and I was literally controlling my entire computer, working on multiple projects, right?
00:22:21.359 --> 00:22:34.000
Going through all those folders, and it was downloading, uploading, opening programs, changing things, doing the things that I would normally be doing, doing it all hands-free, just giving uh you know my my Jarvis instructions.
00:22:34.160 --> 00:22:34.559
All right.
00:22:34.720 --> 00:22:38.480
All right, number six, a spoken update is not proof.
00:22:38.559 --> 00:22:38.720
All right.
00:22:38.799 --> 00:22:40.160
And I talked about this earlier.
00:22:40.319 --> 00:22:42.240
You should require a durable artifact.
00:22:42.319 --> 00:22:42.960
What does that mean?
00:22:43.119 --> 00:22:47.920
All right, when you go back, especially right, and this is something I really found yesterday morning.
00:22:48.000 --> 00:22:53.519
Um, I was looking back through the the um transcript of what I said, and I'm like, wait, how did we get this done?
00:22:53.599 --> 00:22:53.839
Right.
00:22:53.920 --> 00:22:58.160
Because sometimes all you get is what you said and what ChatGPT said.
00:22:58.240 --> 00:23:12.799
So, you know, one thing I would encourage you to do in this voice conversation, or you know, you can leave this in your um agents MD file inside of any project folder is just say, hey, always require written evidence when you're done, right?
00:23:12.960 --> 00:23:17.839
Or you know, build a, you know, an outline every single time that you complete the tasks.
00:23:17.920 --> 00:23:24.960
Uh, you know, make sure you outline what was done, or maybe you have a folder, um, a file, you know, whether it's locally, et cetera.
00:23:25.119 --> 00:23:35.440
Every time you um, you know, complete a run, complete a task, complete a project, upload this file and say exactly what was changed, what was done, where the file location is, et cetera.
00:23:35.599 --> 00:23:36.799
Um, that's huge.
00:23:36.960 --> 00:23:43.920
You always need written evidence because, yeah, it's nice to be able to just flow with voice mode, but sometimes you need that data.
00:23:44.079 --> 00:23:45.119
You need that data, right?
00:23:45.200 --> 00:23:55.279
Maybe you want it in a markdown file, maybe you want it uploaded to your Google Drive, maybe you just want it in line in the in the thread inside codecs, right, as a bullet point, but you need that written proof.
00:23:55.440 --> 00:24:09.279
And then last but not least, and this one's really cool, another one that I haven't seen many people mention, but there's literally on the desktop version, if you click that little orb, you can drag it.
00:24:09.440 --> 00:24:09.759
All right.
00:24:09.920 --> 00:24:13.759
And you don't even have to have codex kind of active or open on your screen.
00:24:13.839 --> 00:24:17.519
This is one thing I'll hope I'll be able to uh to kind of demo.
00:24:17.680 --> 00:24:22.559
Um, but all you have to do is pull the little orb uh away, right?
00:24:22.799 --> 00:24:25.519
Which it's kind of hidden, right?
00:24:25.599 --> 00:24:27.200
You don't even know that you can do it.
00:24:27.359 --> 00:24:28.240
A lot of times, right?
00:24:28.319 --> 00:24:35.359
One thing I do when there's new features, I just click around because you know, open AI is known for you know hiding little fun Easter eggs.
00:24:35.440 --> 00:24:38.880
Uh, you know, if you're talking about like codex pets or anything like that.
00:24:39.039 --> 00:24:43.519
Um, but yeah, I just clicked and I was like, huh, you can drag this thing, right?
00:24:43.599 --> 00:24:46.160
Um, and then I saw maybe one or two other people mention this.
00:24:46.240 --> 00:24:58.240
But yeah, for the most part, you can just have that little orb just chill on your desktop and you have this omnipresent agent that's just gonna chill, it's gonna do absolutely nothing until you tell it to, right?
00:24:58.319 --> 00:25:02.799
So one little uh little uh, I guess not cheat code, but best practice for this.
00:25:02.960 --> 00:25:10.079
Um, especially right, I like to listen to music a lot, and you can't really do that because it's listening for any word, right?
00:25:10.160 --> 00:25:21.039
So I will just have an AirPod in listening to music, and then on my Mac, I just you know set the output to my AirPod so I could still listen to music or be on a call with a colleague, right?
00:25:21.119 --> 00:25:21.839
Something like that.
00:25:22.000 --> 00:25:29.759
And then I can still, you know, I can still mute the mic, but um, if it's just me in front of my computer, that's all I really need to do.
00:25:29.920 --> 00:25:37.599
I can listen to my music in uh in airpod and use my my um my computer microphone to then talk to the orb, right?
00:25:37.680 --> 00:25:39.440
That sounds weird talking to an orb.
00:25:39.599 --> 00:25:43.119
All right, but it just uh allows you to have that omnipresent agent.
00:25:43.440 --> 00:25:44.079
All right.
00:25:44.640 --> 00:25:46.079
My gosh, what could go wrong?
00:25:46.240 --> 00:25:46.880
Here we go.
00:25:47.039 --> 00:25:48.319
Let's go live.
00:25:48.559 --> 00:25:50.160
I'm not I'm not gonna lie.
00:25:50.319 --> 00:25:59.359
Sometimes, especially because I I have a lot of uh more uh kind of uh private, uh you know, uh personal private information in my codex.
00:25:59.599 --> 00:26:11.680
You know, sometimes when I'm like, oh, I gotta share my my entire codex, I'm you know, sweating bullets a little bit, but I I always want you guys to see, you know, see how this uh goes live and kind of uh see how it works.
00:26:11.920 --> 00:26:14.880
All right, let's try this live live stream audience.
00:26:14.960 --> 00:26:17.759
If you could let me know if you can see my screen.
00:26:19.039 --> 00:26:22.720
All right, and hopefully we'll be able to hear the audio as well.
00:26:24.400 --> 00:26:38.559
So uh as a reminder, this is the and yeah, if you do want to see the video version of this, if you're listening on the podcast, in the show notes, there's always a link to the episode page on our website, and you can go watch the video version.
00:26:38.799 --> 00:26:42.880
So just skip to uh, you know, I don't know, about 26 minutes or so.
00:26:43.440 --> 00:26:49.039
Okay, so at the bottom here, you'll see um there's a normal microphone.
00:26:49.200 --> 00:26:50.000
Don't click that.
00:26:50.160 --> 00:26:51.279
That is the dictation.
00:26:51.440 --> 00:26:54.240
Uh, the other one is to start a new voice chat.
00:26:54.400 --> 00:26:56.000
All right, so let's just go ahead.
00:26:56.079 --> 00:27:01.279
I'm gonna go to um make this an unattached chat thread.
00:27:01.359 --> 00:27:03.839
Um, and then I'm just gonna riff a little bit here.
00:27:04.000 --> 00:27:04.400
All right.
00:27:04.559 --> 00:27:17.519
Um, so if you hear me talking, I might hit the pause, uh, the mute button so I can keep talking to you all and explain what's going on, but otherwise assume that I'm just talking from here on out uh to Chat GPT.
00:27:17.599 --> 00:27:18.720
So let's get it going.
00:27:18.880 --> 00:27:36.160
I'm gonna actually uh work on a project that I wanted to do because I put a lot of work into a recent um speech that I did, and there were some things that happened in there that I'm like, huh, I should probably pull that um and do do something more with that speech that I did.
00:27:36.319 --> 00:27:39.440
So uh let's go ahead and get started here.
00:27:50.799 --> 00:27:52.319
Gotta love the live demos.
00:27:52.400 --> 00:27:57.200
I've literally never seen this uh this screen come up before where it said voice chat couldn't start.
00:27:57.359 --> 00:27:58.319
Oh, that's funny.
00:27:58.480 --> 00:28:00.079
All right, let's try it again.
00:28:02.400 --> 00:28:06.400
Uh hey, what would you like to try again?
00:28:06.720 --> 00:28:07.440
All right, cool.
00:28:07.599 --> 00:28:09.759
No, so uh can you look?
00:28:09.920 --> 00:28:15.279
It's maybe in my downloads folder, but uh maybe from like two or three weeks ago.
00:28:15.440 --> 00:28:22.400
Um I did this presentation for a firm and uh there's probably like a PowerPoint.
00:28:22.640 --> 00:28:24.799
It was about um ChatGPT work.
00:28:25.039 --> 00:28:26.480
Let me know if you can find it.
00:28:27.200 --> 00:28:31.119
I'll check your recent presentation files for that.
00:28:31.519 --> 00:28:37.599
All right, so ChatGPT work PowerPoint in your downloads so you can open it from the file card on your screen.
00:28:38.000 --> 00:28:39.440
Oh, cool, great.
00:28:39.759 --> 00:28:44.720
So can you just kind of go through and bullet point what I talked about and what I didn't?
00:28:44.880 --> 00:29:00.079
Um, and then while you're doing that, can you also open uh Chrome and then go to YouTube and find the live stream that OpenAI did a couple of weeks ago for the Chat GPT uh work announcement?
00:29:00.240 --> 00:29:14.000
It's probably like two weeks ago or so, um, and then copy that link from that open AI live stream and then use computer use um and open up an app on my computer.
00:29:14.079 --> 00:29:15.119
It's called Parrot.
00:29:15.599 --> 00:29:17.279
Um, it's an app that I built.
00:29:17.359 --> 00:29:27.039
And then I want you to take that YouTube uh URL from the OpenAI live stream and I want you to paste it into Parrot and create a transcription.
00:29:27.119 --> 00:29:33.440
Um, and I want you to look at that transcription, which will tell you, you know, what they talked about in that 30 or so minute live stream.
00:29:33.680 --> 00:29:45.920
And essentially, I want you to look and find um what I did not cover um in my affirm presentation that was covered in the open AI live stream.
00:29:46.000 --> 00:29:49.200
So uh just take take your time and start working on that.
00:29:50.240 --> 00:29:51.599
I'll get started on that.
00:29:52.640 --> 00:29:59.039
I'm comparing your affirm deck with the open AI work launch stream now, using Chrome and Terry for the transcript.
00:30:00.880 --> 00:30:01.440
All right.
00:30:03.119 --> 00:30:07.759
So I just put this on mute, so you'll probably still hear Chad GPT.
00:30:07.920 --> 00:30:08.880
Oh, it's not on mute.
00:30:11.519 --> 00:30:12.160
All right.
00:30:14.400 --> 00:30:15.039
There we go.
00:30:15.119 --> 00:30:16.720
I think I think I'm on mute now.
00:30:17.839 --> 00:30:19.759
I'm not, I have no clue what's going on.
00:30:20.000 --> 00:30:22.480
Okay, that's that's weird another time.
00:30:22.799 --> 00:30:33.680
Um this it's it's it's showing the the transcript here, but uh obviously I'm talking to the live stream audience now, not Chad GBT, even though it's still uh transcribing.
00:30:33.759 --> 00:30:36.160
So uh hey chat, are you still listening to this?
00:30:41.519 --> 00:30:41.839
Okay.
00:30:42.880 --> 00:30:43.839
Interesting.
00:30:44.480 --> 00:30:50.480
Love love doing these um love doing these these live streams um here.
00:30:50.960 --> 00:30:58.160
Um because I I always run through and do the demo, and then I always get these weird things that that happen that didn't happen before.
00:30:58.319 --> 00:31:06.400
So uh it was muted, but it was still um dictating what I was saying, which uh didn't happen in all of my testing.
00:31:06.559 --> 00:31:15.920
Anyways, so let me explain what I did and what's happening now because it's already opened up this program that I created called Parrot.
00:31:16.720 --> 00:31:23.920
Uh right, just this uh awesome program that I've you know built up over the past uh however long.
00:31:24.319 --> 00:31:28.079
So I told it, go find this presentation I did two weeks ago.
00:31:28.240 --> 00:31:36.559
I don't remember what was in it, uh, because I literally had to build it, like rebuild it the night before because it was right when OpenAI announced ChatGPT Work.
00:31:36.640 --> 00:31:40.799
And I didn't remember if I got everything from the live stream into that presentation.
00:31:41.039 --> 00:31:49.759
And I thought that maybe at some point I'll do an entirely new course or something like that on Codex or ChatGPT Work.
00:31:49.839 --> 00:31:54.559
Um, so I'm like, well, I put together a lot of work in this presentation and I thought it was pretty good.
00:31:54.640 --> 00:31:57.359
Uh, but there's probably some things I didn't get to.
00:31:57.440 --> 00:32:03.759
Uh so what's already happened is uh Codex went in or ChatGPT voice inside codex went in.
00:32:03.920 --> 00:32:06.240
It opened up this program that I built.
00:32:06.319 --> 00:32:11.279
Um, it grabbed the um the URL and it went in and pasted it.
00:32:11.359 --> 00:32:13.359
It looks like it has the transcript up.
00:32:13.440 --> 00:32:16.160
Um, and we'll see what's what's happening here.
00:32:18.400 --> 00:32:23.279
The parent transcript is captured, so I could ground this in what they actually covered.
00:32:23.440 --> 00:32:24.400
Here's the quick take.
00:32:24.640 --> 00:32:28.720
Your deck focused on the desktop agent and agents MD workflow.
00:32:28.880 --> 00:32:32.799
The stream emphasized connected workflows and shareable outcomes.
00:32:32.960 --> 00:32:36.799
Those connectors across Slack, Calendar, and Excel to PowerPoint to Slack.
00:32:37.119 --> 00:32:39.920
Can you maybe just give me can you maybe just give me bullet points?
00:32:40.400 --> 00:32:41.039
Didn't cover.
00:32:42.000 --> 00:32:52.319
Can you maybe just give me bullet points of the biggest things that I did not cover in my affirm presentation that was in the live stream?
00:32:53.759 --> 00:32:54.319
Sure.
00:33:00.640 --> 00:33:16.720
The biggest things you didn't cover were connected work across tools like Slack, Gmail, and calendar, end-to-end finance workflows like Excel to PowerPoint reporting, interactive sites for dashboards or internal tools, starting tasks on mobile continuously.
00:33:16.960 --> 00:33:17.359
That's a good point.
00:33:18.079 --> 00:33:26.880
I think that there was a new update a couple like uh maybe it was Thursday, but I don't even think OpenAI put anything on their website about it.
00:33:26.960 --> 00:33:28.240
It was something in sites.
00:33:28.480 --> 00:33:34.319
Um, so see if you can look up maybe their uh change log for codecs or sorry for sites.
00:33:34.480 --> 00:33:37.119
Um, I think it was something about there's some new analytics.
00:33:37.279 --> 00:33:38.799
Can you look that piece up?
00:33:39.519 --> 00:33:41.200
Yeah, I'll check that.
00:33:41.839 --> 00:33:47.599
Um, also look in my uh transcripts for your everyday AI.
00:33:48.000 --> 00:33:55.119
Um, because I, you know, every Friday and Monday uh we go over kind of like new features and new updates.
00:33:55.200 --> 00:33:57.039
Uh so can you just check this?
00:33:57.200 --> 00:34:04.079
Uh, the last week's um shows because I think there were a couple other uh codex updates in there.
00:34:04.160 --> 00:34:16.559
So you can just, you know, open that up, or I think there's a folder um on my desktop if you want to, or not my desktop, maybe in documents if you want to use computer use, or you can just go to our website and look at the transcript there.
00:34:16.719 --> 00:34:22.960
Um, because sometimes they only update their uh kind of change log like once a week.
00:34:23.119 --> 00:34:26.159
Um, so we obviously put out shows, you know, every day.
00:34:26.320 --> 00:34:29.039
So just go um specifically on sites.
00:34:29.119 --> 00:34:31.039
I want you to get more information on that.
00:34:31.679 --> 00:34:32.159
Got it.
00:34:32.320 --> 00:34:38.159
I'll check the official notes, the sites docs, and your recent transcripts for anything site specific.
00:34:38.480 --> 00:34:38.719
Okay.
00:34:38.880 --> 00:34:56.800
And while you're doing that, um, or maybe first, can you just uh create a very simple um document and then just download it and save it to my computer uh that just shows kind of what I talked about in the affirm presentation and then what I did not cover.
00:34:56.960 --> 00:35:01.920
Um, and just kind of download that to my computer, but also save it to my Google Drive just so I have it.
00:35:02.000 --> 00:35:06.079
And then, you know, name it so it's easy for me to see and understand what's in there too.
00:35:06.719 --> 00:35:07.199
Got it.
00:35:07.360 --> 00:35:09.920
I'll put that together and save it both places.
00:35:12.559 --> 00:35:12.880
Okay.
00:35:13.280 --> 00:35:16.639
So I realize what I did wrong now, guys, earlier.
00:35:16.719 --> 00:35:23.039
Um, when I'm like, wait, I it's still catching me speak, even no, that was a human error.
00:35:23.119 --> 00:35:29.360
Um, I accidentally uh turned off the speaker um instead of the microphone.
00:35:29.519 --> 00:35:30.400
So that was my fault.
00:35:30.480 --> 00:35:32.239
So right now I have both muted.
00:35:32.400 --> 00:35:37.760
So uh, you know, uh Chad GPT is still talking to me, but um, it's not super important.
00:35:37.920 --> 00:35:54.880
You know, essentially I just wanted to show you those capabilities because what just happened, even though I kind of fumbled through that demo quite a little bit, um, right, this is something I was gonna do because I knew I put together, like I said, a lot of good information for this uh AFEM presentation, just going over some of the features.
00:35:55.039 --> 00:35:58.000
You know, I had some good visuals, some good content, all that stuff.
00:35:58.079 --> 00:35:58.480
Uh, right.
00:35:58.559 --> 00:35:59.840
So why would I start from scratch?
00:36:00.000 --> 00:36:02.159
But I knew that there was new things that needed to be updated.
00:36:02.320 --> 00:36:07.519
I didn't have 35 minutes to go re-watch the um, you know, ChatGPT live stream.
00:36:07.760 --> 00:36:16.719
So I just had it literally uh use its built-in browser, go find the YouTube channel for OpenAI, find that live stream, take that link.
00:36:16.880 --> 00:36:20.480
It opened up a program that it wasn't even pinned to my desktop.
00:36:20.559 --> 00:36:21.280
So it just found it.
00:36:21.360 --> 00:36:32.960
It opened up the program that I built, it transcribed it, and then it compared uh kind of everything that was in that PowerPoint that it opened in its file browser um to the transcript um from the open AI live stream.
00:36:33.119 --> 00:36:40.400
Now, right now, it's putting it together and it's already, it just told me that it's uh put that document together and it's done.
00:36:40.639 --> 00:36:41.360
So that's good.
00:36:41.440 --> 00:36:44.000
And it also said it confirmed the missing sites update.
00:36:44.079 --> 00:36:47.599
So all right, I I do want to show maybe one or two other things quick.
00:36:47.679 --> 00:36:54.079
So I'm gonna start a new voice chat and here we go.
00:37:00.480 --> 00:37:13.199
Hey, can you um use the Beehive MCP and look at my uh poll from yesterday um and tell me what the results from the poll were.
00:37:15.039 --> 00:37:18.800
Yeah, I'll check yesterday's Beehive poll results quickly.
00:37:22.320 --> 00:37:29.679
All right, so I just muted chat, but uh what I'm showing for our live stream audience here is I'm actually minimizing.
00:37:29.760 --> 00:37:36.400
Uh I'm gonna minimize codex here, and you'll see here kind of this little orb uh floating around on my desktop.
00:37:38.639 --> 00:37:42.639
OpenAI's mu Jarvis Live Mode is leading with 32.
00:37:42.880 --> 00:37:47.360
Claude Opus 5 hands-on has 21, and six people picked other.
00:37:48.320 --> 00:37:48.639
Okay.
00:37:49.039 --> 00:37:51.039
Uh could you just start that over?
00:37:51.119 --> 00:37:52.320
I missed the beginning.
00:37:53.119 --> 00:37:53.679
Sure.
00:37:54.239 --> 00:37:58.159
Yesterday's AI Working Wednesdays poll has 59 votes.
00:37:58.400 --> 00:38:02.000
OpenAI's new Jarvis Live Mode is leading with 32.
00:38:02.239 --> 00:38:06.719
Claude Opus 5 hands-on has 21, and six people picked other.
00:38:08.880 --> 00:38:09.920
Uh cool.
00:38:10.159 --> 00:38:16.639
Can you tell me um what my open rate was um yesterday?
00:38:16.719 --> 00:38:22.400
Uh or sorry, on Monday, July 27th versus the Monday before that.
00:38:22.480 --> 00:38:26.320
I just want to see kind of what the open rates were over those last ones.
00:38:27.920 --> 00:38:28.239
Okay.
00:38:28.480 --> 00:38:31.199
I'll pull up both Mondays and compare them.
00:38:31.519 --> 00:38:39.119
So essentially what I'm doing right now, I just muted both is well, I got rid of codecs, and now I just have this little floating orb here.
00:38:39.199 --> 00:38:39.440
Right.
00:38:39.519 --> 00:38:41.119
So I'm dragging it around my screen.
00:38:41.280 --> 00:38:42.960
I can put it literally anywhere.
00:38:43.039 --> 00:38:47.199
Um, it's showing me, even though I haven't muted, uh, what the open rate was.
00:38:47.360 --> 00:38:56.000
It says um this yesterday or two days ago, it was about 55%, and uh the Monday before it was 58%.
00:38:56.320 --> 00:39:00.079
That's still because you know, opens keep uh trailing in a couple of the days after.
00:39:00.239 --> 00:39:01.280
So uh pretty cool.
00:39:01.440 --> 00:39:04.000
You can see right there, uh some of the basic things.
00:39:04.079 --> 00:39:11.920
So I went through showing you uh multiple tasks at once, kind of stacking those using different connectors and MCPs, right?
00:39:12.079 --> 00:39:15.360
I used my uh you know, Google Drive that's a connector.
00:39:15.519 --> 00:39:22.320
I used an MCP, which is a model context protocol for my newsletter because it doesn't have an official Chat GPT connector.
00:39:22.480 --> 00:39:30.480
I, you know, did things like browsing the web, um, you know, pulling, you know, uh opening other programs on my computer.
00:39:30.559 --> 00:39:32.559
And, you know, it was clicking around, you know.
00:39:32.639 --> 00:39:38.000
Uh you probably saw it, it happened very quickly because computer use is very fast inside GPT 5.6 soul.
00:39:38.320 --> 00:39:42.559
So that's a wrap for the demo portion.
00:39:42.719 --> 00:39:45.519
It didn't go too bad, right?
00:39:45.599 --> 00:39:48.320
Uh maybe we'll see how this actually turns out.
00:39:48.400 --> 00:39:50.400
Hopefully, it recorded all that audio.
00:39:50.559 --> 00:39:53.679
Um, but here's the uh takeaway, right?
00:39:54.320 --> 00:39:59.920
This is a completely uh new way to work, right?
00:40:00.960 --> 00:40:04.320
In almost a new way to think about work, um, right?
00:40:04.480 --> 00:40:06.960
Because even before, right?
00:40:07.840 --> 00:40:20.320
Honestly, like even just 10 days ago before this update came out, for the most part, when I wanted to be the most productive, I was still sitting in my chair and you know, clicking around, right?
00:40:20.480 --> 00:40:22.960
Which is not bad necessarily, right?
00:40:23.199 --> 00:40:26.559
But distraction, overwhelm.
00:40:26.800 --> 00:40:35.920
And sometimes what I found is when you're not actually looking at a screen and when you're able to just kind of ramble and yap, right?
00:40:36.400 --> 00:40:43.199
Um, sometimes you get much better results because you can communicate things sometimes in a much clearer way.
00:40:43.440 --> 00:40:45.360
Because sometimes, especially if you're typing, right?
00:40:45.440 --> 00:40:50.400
Not everyone can, you know, especially if you work in an open office, you can't always ramble, uh, right.
00:40:50.480 --> 00:40:57.519
Or if you're working on something private, maybe you work at home and you can't, you know, talk about certain things, you know, with other people around.
00:40:57.760 --> 00:41:11.760
Um, this is something that for me, I'm not saying I I've struggled to adjust how to work, um, but I've I've had to rethink what it means to work, right?
00:41:11.920 --> 00:41:14.639
And I had a great day working, right?
00:41:14.719 --> 00:41:15.920
I had a great day working yesterday.
00:41:16.079 --> 00:41:34.639
Went out and, like I said, took an hour walk, and it was not only being able to go get outside and touch grass here in Chicago, but I actually think that I got a lot more done in that one hour than I would have gotten done two or three hours doing something very similar using codecs or even ChatGPT voice in front of my computer with all my screens because it's distraction.
00:41:34.719 --> 00:41:38.480
And then I would have said, Oh, I I have to go do all these other things, right?
00:41:38.639 --> 00:41:43.840
Um, so it is definitely the new ChatGPT voice is like having a Jarvis.
00:41:44.079 --> 00:41:54.079
And at least for me, I'm even though I've been Codex pilled since the day it came out, sometimes I still find myself still doing some of the work, right?
00:41:54.239 --> 00:42:13.840
And this has been a refreshing uh change in that because I'm actually just using my brain and thinking a little bit more, uh, trying to think more strategically and creatively, um, and you know, being able to communicate things in a different way and you know, being able to describe all the nuance and you know, having Chat GPT voice sometimes poke holes in my plan.
00:42:14.079 --> 00:42:23.280
So it's been for me a lot more talking and iterating and working through my voice, which for me is really easy, and maybe it will be for you.
00:42:23.360 --> 00:42:25.360
But I hope this episode was helpful.
00:42:25.519 --> 00:42:40.800
Uh, maybe this won't be for you, but there's a good chance that using the new Chat GPT voice is could be the biggest paradigm shift in how you've worked since maybe Chat GPT came out, or even more so than that.
00:42:41.039 --> 00:42:43.039
So uh thank you for tuning in.
00:42:43.119 --> 00:42:47.840
If you haven't already, again, please go to your everydayai.com, sign up for the free daily newsletter.
00:42:48.000 --> 00:42:48.559
Thanks for tuning in.
00:42:48.639 --> 00:42:51.199
We'll see you back tomorrow and every day for more everyday AI.
00:42:51.280 --> 00:42:52.320
Thanks, y'all.
00:00:01.520 --> 00:00:08.160
Many people talking about the new ChatGPT voice are calling it their AGI moment.
00:00:08.960 --> 00:00:11.199
And I don't disagree.
00:00:11.439 --> 00:00:20.800
Yeah, it's changed how I work in the short amount of time that it's been out, but there's usually at least a handful of updates every quarter that do that.
00:00:20.960 --> 00:00:26.480
But this update from ChatGPT Voice changes how I think about work.
00:00:26.800 --> 00:00:32.560
And that has rarely happened in the nearly four years I've been doing the everyday AI show.
00:00:32.719 --> 00:00:38.560
It's like if you've ever seen Iron Man, ChatGPT Voice is literally like having your own Jarvis.
00:00:38.880 --> 00:00:52.000
Whether you're in front of your computer or across the country, like I was the past couple of days, you can ramble hands-free and natural language, and the desktop version of ChatGPT will literally just control itself.
00:00:52.079 --> 00:00:59.119
It'll do anything on your computer that any skilled human could do, but you don't have to be there doing any of it.
00:00:59.359 --> 00:01:08.799
And I really put this through its paces yesterday as I took about an hour-long walk in controlling my home computer through my iPhone.
00:01:08.879 --> 00:01:26.159
And my computer at home was creating documents, using other desktop programs like Claude Code, organizing my cloud storage, triaging emails and drafting replies, and planning this very show by transcribing YouTube reviews and, say, bookmarks that I just didn't have time to get to, creating images, all that stuff.
00:01:26.319 --> 00:01:29.280
I just gave commands and the work was just done.
00:01:29.519 --> 00:01:39.760
So obviously, OpenAI can't call this thing Jarvis mode, but you can see how that might be a more fitting description than the moniker of Chat GPT voice.
00:01:39.840 --> 00:01:46.319
But I will say this I've used literally thousands of AI tools and features over the past four years of doing everyday AI.
00:01:46.480 --> 00:01:52.079
And Chat GPT voice has instantly become the number one most useful ever.
00:01:52.799 --> 00:01:55.280
So, what is this ChatGPT voice thing?
00:01:55.359 --> 00:01:56.879
And why is it so special?
00:01:56.959 --> 00:01:59.040
And why haven't you used it yet?
00:01:59.200 --> 00:02:05.359
Well, we'll break all those down as we put AI to work on Wednesdays on Everyday AI.
00:02:05.599 --> 00:02:07.680
All right, here is the big picture.
00:02:07.920 --> 00:02:12.240
ChatGPT voice became an agent management interface.
00:02:12.479 --> 00:02:24.719
So this just came out, it hasn't even been out a full week since OpenAI announced it, and it lives inside of the desktop version of Chat GPT Work and Codex, which is the same thing, by the way.
00:02:24.879 --> 00:02:28.800
So ChatGPT Voice is powered by the new GPT Live model.
00:02:29.120 --> 00:02:30.879
A little confusing, but we'll break it down.
00:02:31.039 --> 00:02:40.719
And that somewhat confusing rollout, I think, made for this being the undisputed most criminally underhyped release in AI ever, right?
00:02:40.879 --> 00:02:49.680
Sometimes you see these like little releases come out, and everyone's talking about it, like, oh my gosh, this thing's gonna, you know, break how we all work, it's gonna take away all these jobs, it's gonna do all these things, right?
00:02:49.840 --> 00:02:57.599
Uh, Chat GPT voice uh, I don't think people are talking about it, right?
00:02:57.759 --> 00:03:06.639
I'm very uh ears to the ground uh when it comes to these kind of things, and people should be talking about this and using this more, and that's why we're gonna be going over it on today's show.
00:03:06.719 --> 00:03:09.439
So stick with me for the next 25-ish minutes.
00:03:09.520 --> 00:03:10.800
And here's what you'll learn.
00:03:10.879 --> 00:03:19.520
You're gonna know how the ordinary voice mode differs from the new uh Chat GPT voice launched inside work or codex.
00:03:19.759 --> 00:03:29.280
You're gonna know which evidence and approval rules that you need to keep authoritative sounding updates accountable because you can't just trust the voice and never go back to it.
00:03:29.439 --> 00:03:38.560
And I'm gonna give you the seven advanced chat GPT voice uses that you're gonna want to start using and apply to your workflows immediately.
00:03:38.800 --> 00:03:39.599
Let's get into it.
00:03:39.759 --> 00:03:41.120
Welcome to everyday AI.
00:03:41.199 --> 00:03:44.080
My name's Jordan Wilson, and well, this thing's for you.
00:03:44.240 --> 00:03:53.840
This is your daily live stream podcast and free daily newsletter, helping everyday business leaders like you and me not just keep up with AI, but how you can use all of these updates.
00:03:54.000 --> 00:03:55.039
I tell you what matters.
00:03:55.199 --> 00:03:57.919
You go put it to work, grow your company and your career.
00:03:58.080 --> 00:04:06.240
So please, if you haven't already, subscribe to the podcast on Apple, Podcasts, or Spotify, and make sure you go to our website at your everydayai.com.
00:04:06.400 --> 00:04:14.479
We're gonna be not only highlighting the big uh takeaways from today's show, but also giving you all of the other AI news you need to know to stay ahead.
00:04:14.719 --> 00:04:16.800
All right, so let's get into it.
00:04:17.040 --> 00:04:21.199
So um on Wednesdays, we put AI to work on Wednesday.
00:04:21.360 --> 00:04:24.800
So the latter half of this will be kind of demo based.
00:04:24.879 --> 00:04:25.920
So FYI.
00:04:26.079 --> 00:04:40.879
Uh, if you do want to see the video version of this, it will obviously be somewhat visual because uh if everything goes correctly, which for an unedited, unscripted demo um of a super smart AI taking over my computer, who knows what could go wrong, right?
00:04:40.959 --> 00:04:49.680
But you can always catch the video version of this on our website at your everydayai.com or on LinkedIn, YouTube, Twitter machines.
00:04:49.839 --> 00:04:50.240
All right.
00:04:50.399 --> 00:04:54.399
Uh, but let's first start with the two basic settings that you have to understand.
00:04:54.480 --> 00:05:00.639
It's kind of settings slash uh, you know, getting your mindset right on what's named what.
00:05:00.800 --> 00:05:11.040
And this is important um because there's a lot of confusion on this, because most people are like, okay, well, yeah, uh Chat GPT voice, I know it's it's not new, right?
00:05:11.120 --> 00:05:13.759
I can just I've been able to talk to Chat GPT for a while.
00:05:13.839 --> 00:05:14.800
So yes and no.
00:05:14.879 --> 00:05:21.839
Uh I I essentially want to take you through four different phases or buckets of using your voice to interact with Chat GPT.
00:05:21.920 --> 00:05:23.279
All right, so number one, dictation.
00:05:23.360 --> 00:05:24.959
That's been around for a very long time.
00:05:25.120 --> 00:05:28.079
Literally, some people think that that's what this is, that's not.
00:05:28.240 --> 00:05:29.600
So dictation, right?
00:05:29.680 --> 00:05:37.680
You can click the little uh microphone button um on the chat GPT interface, and it will you can talk and it's just gonna turn your speech into text.
00:05:37.759 --> 00:05:39.759
That's dictation, that's not what we're talking about.
00:05:39.920 --> 00:05:44.720
Then there's the old voice mode, uh, which was technically called advanced voice mode.
00:05:44.800 --> 00:05:46.800
There was a different voice mode before that, all right.
00:05:46.879 --> 00:05:49.920
But that was more of the walkie talkie, uh, right?
00:05:50.000 --> 00:05:53.680
That's the turn by turn uh conversation uh mode.
00:05:53.920 --> 00:05:57.519
So that was what you know, a month ago, that's what OpenAI had.
00:05:57.600 --> 00:05:59.439
That's what Claude has today.
00:05:59.600 --> 00:06:04.240
Nothing wrong with that, but that's not what we really want out of a voice mode.
00:06:04.480 --> 00:06:09.040
What we want is, well, the actual engine driving this, and that is GPT Live.
00:06:09.199 --> 00:06:13.680
So that is what is called this kind of full duplex voice mode.
00:06:13.920 --> 00:06:16.720
So that means, and you'll see an example of this.
00:06:16.879 --> 00:06:22.879
Um, the voice mode, GPT Live, um, can talk and listen at the same time.
00:06:23.040 --> 00:06:29.120
Uh, it can, as it's talking to you, it's using another model in the background to call tools, look up information on the internet.
00:06:29.439 --> 00:06:35.360
You know, maybe it's running a little bit of code to give you an answer to something that's not as easy to find as you might think.
00:06:35.519 --> 00:06:35.759
All right.
00:06:35.839 --> 00:06:38.480
So that's that natural, interruptible conversation.
00:06:38.560 --> 00:06:42.720
It's just like talking with a real human, but not like walkie-talkie style.
00:06:42.800 --> 00:06:43.519
Uh, right.
00:06:43.920 --> 00:06:48.000
So, not to be confused, but that's not what we're talking about here, right?
00:06:48.079 --> 00:06:51.519
That came out two weeks ago, and maybe you've already used that and it's really good.
00:06:51.680 --> 00:06:52.399
This is different.
00:06:52.480 --> 00:06:54.079
This is Chat GPT voice.
00:06:54.240 --> 00:07:04.560
So, this is essentially that voice model, that full duplex GPT live voice model um that has been available in Chat GPT for about you know two and two or three weeks now.
00:07:04.800 --> 00:07:09.120
Now that lives inside of Chat GPT work or codex.
00:07:09.279 --> 00:07:13.040
So this is the um the version that you download on your computer.
00:07:13.199 --> 00:07:17.839
So there is no chat GPT voice when you go to chat GPT.com.
00:07:18.000 --> 00:07:19.360
I know that's confusing.
00:07:19.439 --> 00:07:21.600
That's going to be using the GPT live.
00:07:21.680 --> 00:07:27.199
So Chat GPT voice is available on the desktop version, all right.
00:07:27.360 --> 00:07:32.000
And that's kind of where your um the thing that's Jarvis mode, right?
00:07:32.079 --> 00:07:39.680
Where it can literally access all of your data, it can use your computer, it can do literally anything that a human sitting down in front of your computer can't.
00:07:39.759 --> 00:07:45.040
Whereas, you know, the normal GPT live, the new smarter thing, it's cool to chat with, right?
00:07:45.120 --> 00:07:46.720
But it's not going to actually do your work.
00:07:46.879 --> 00:07:54.399
Now we all finally have a super smart uh you know co-worker sitting down that we can literally just talk to like a real person.
00:07:55.120 --> 00:07:55.600
All right.
00:07:55.759 --> 00:08:00.879
So that's kind of the uh the iteration of the different types of voice inside of Chat GPT.
00:08:00.959 --> 00:08:04.800
All right, so basic setting number two, which I kind of talked about it.
00:08:04.879 --> 00:08:13.759
So chat GPT voice itself is just the GPT Live model, plus bringing in this agenc execution layer.
00:08:13.839 --> 00:08:22.800
Um, so aside from it being able to actually complete work for you, which the GPT Live can't really do, at least not fully, uh, right.
00:08:22.959 --> 00:08:29.839
The difference here is it has access to all of your data and connectors, which GPT Live doesn't, right?
00:08:30.000 --> 00:08:35.440
So that's the one thing that is missing from GPT Live that I was using it, uh, right.
00:08:35.600 --> 00:08:42.879
If you want to say, hey, check my email, or if you have some MCP servers connected inside of ChatGPT, you know, it can't access those.
00:08:42.960 --> 00:08:51.279
Um, it can you can upload a file to GPT Live and it will be able to go through and talk about that file, but it can't access all of your dynamic data.
00:08:51.440 --> 00:09:02.080
As an example, I probably have not a ton, uh, right, because my tech stack is not super fat, but I probably have at least 30 different either connectors or MCPs.
00:09:02.240 --> 00:09:18.639
So now with ChatGPT voice on the desktop version of ChatGPT work or codex, I can instantly talk and grab data from any of those, but also I can output or have the agent output work for me, but I can just command it all via Jarvis mode, right?
00:09:18.879 --> 00:09:20.639
So here's how it works.
00:09:20.879 --> 00:09:29.679
All right, you uh the the Chat GPT voice can listen, it can speak and coordinate all at the same time and actually do your work.
00:09:29.919 --> 00:09:32.639
All right, so there is a little button, right?
00:09:32.720 --> 00:09:35.440
So if you hover over it, it just says start voice chat.
00:09:35.519 --> 00:09:41.600
So not to be confused uh with the button on the left, which is just the microphone button, which is the dictate button.
00:09:41.759 --> 00:09:45.120
All right, so you're gonna start a voice chat and this little orb, right?
00:09:45.279 --> 00:09:46.720
This little chat GPT orb.
00:09:46.799 --> 00:09:48.080
I don't know if there's an official name for it.
00:09:48.159 --> 00:09:52.559
I just call it the, you know, you can call it the voice visualization or just the orb.
00:09:52.639 --> 00:09:54.080
So I'm just gonna call it the orb.
00:09:54.159 --> 00:09:54.480
All right.
00:09:54.559 --> 00:09:59.279
So that's when this uh kind of chat GPT voice mode is um working.
00:09:59.519 --> 00:10:01.440
So also a little confusing.
00:10:01.519 --> 00:10:06.559
That's the same orb that comes on if you're just using GPT Live inside of chat GPT.com.
00:10:06.639 --> 00:10:11.279
All right, so you just gotta be using this if you're trying to follow along at home, which I encourage you to do.
00:10:11.440 --> 00:10:20.559
Uh, you know, make sure you're obviously using the desktop version of ChatGPT work or codex, which again, a little confusing, is the exact same app.
00:10:20.639 --> 00:10:24.960
There's just a drop down at the top because people are always like, wait, I don't have codex.
00:10:25.200 --> 00:10:26.639
Yes, you do, it's chat GPT work.
00:10:26.799 --> 00:10:28.399
And people are like, I don't have ChatGPT work.
00:10:28.480 --> 00:10:30.960
And it's like, yes, you do, it's codex, it's the same thing.
00:10:31.120 --> 00:10:37.519
All right, so you have to be doing this inside of that download, uh, the downloadable program on your computer.
00:10:37.759 --> 00:10:39.600
And well, it's just neural.
00:10:39.679 --> 00:10:45.039
It's going to be able to listen and run these models in the background and literally do anything that you can do on your computer.
00:10:45.519 --> 00:10:56.879
So uh there's multiple layers, and kind of the biggest differentiator that I think uh versus uh ChatGPT voice and GPT Live, uh, the voice layer just talks.
00:10:57.039 --> 00:11:05.360
Now we have this new layer that we're combining it with all of the capabilities um of codecs, is it just is going to work, right?
00:11:05.519 --> 00:11:07.440
It's gonna execute your work for you.
00:11:07.600 --> 00:11:14.159
And just for ease of uh not saying the wrong thing too many times, from here on out, I'm just gonna say codex, all right.
00:11:14.240 --> 00:11:16.960
Um, but it's the same thing as chat GPT work, right?
00:11:17.120 --> 00:11:19.600
But there's too many uh Chat GPTs flying around.
00:11:19.679 --> 00:11:21.039
So I'm just gonna say codex, right?
00:11:21.120 --> 00:11:24.799
That is the uh version that you download and run on your computer.
00:11:25.279 --> 00:11:25.919
All right.
00:11:26.240 --> 00:11:35.919
So let's quickly go into the seven advanced chat GPT voice uses, uh, and then we're gonna go straight into the demo and hopefully it all works.
00:11:36.000 --> 00:11:40.799
Um, but I'm gonna be doing some of these advanced uh use cases as we go along.
00:11:40.960 --> 00:11:44.000
But these are also kind of best practices as well.
00:11:44.240 --> 00:11:50.320
So number one, and this is uh a difference in how these threads work.
00:11:50.559 --> 00:11:58.159
So you cannot go and pick up an old thread and start a new Chat GPT voice conversation in there.
00:11:58.320 --> 00:11:58.720
All right.
00:11:59.039 --> 00:12:00.559
You can't do it, unfortunately.
00:12:00.720 --> 00:12:01.919
That would be great if you could.
00:12:02.080 --> 00:12:08.720
Um instead uh you are going to uh start a new chat, okay?
00:12:09.039 --> 00:12:17.840
So whether that's inside of a current project, or if you just go down and start a new chat that's not attached to a project.
00:12:18.000 --> 00:12:26.080
So um you can start any new chat um by just clicking the uh start new voice chat button.
00:12:26.240 --> 00:12:28.240
Um, and that's how you start.
00:12:28.399 --> 00:12:30.000
But here's the thing, right?
00:12:31.039 --> 00:12:33.600
It knows everything, right?
00:12:33.679 --> 00:12:35.440
And it controls everything.
00:12:35.919 --> 00:12:36.240
All right.
00:12:36.320 --> 00:12:41.600
And that is just I can't emphasize how big that is, right?
00:12:41.679 --> 00:12:44.000
I've done this many times, I've done live demos of it.
00:12:44.080 --> 00:12:45.600
I just checked again, right?
00:12:45.919 --> 00:12:48.639
Code, uh, let's let's talk about Claude Code, right?
00:12:49.039 --> 00:12:55.279
Claude code doesn't know anything within what's happening under its own roof, right?
00:12:55.440 --> 00:13:01.120
Unless it just happens to commit something to its memory, um, which it just does that haphazardly.
00:13:01.279 --> 00:13:02.960
Otherwise, it knows nothing, right?
00:13:03.120 --> 00:13:08.240
So all of those conversations, you know, let's just say that you're talking about Claude Cowork, right?
00:13:08.399 --> 00:13:16.000
All of those conversations, unless it just commits something to memory, which, you know, maybe it does one to two percent of the content in there.
00:13:16.240 --> 00:13:25.440
If you start a new chat, it knows absolutely nothing, which makes something like Claude Desktop, in my opinion, extremely useless, right?
00:13:25.600 --> 00:13:26.879
That's why I don't really use it.
00:13:26.960 --> 00:13:30.559
I mean, I use it to audit things that I build inside codecs, right?
00:13:30.639 --> 00:13:35.840
Uh, but the big thing with this new voice mode is it can understand any thread anywhere.
00:13:36.000 --> 00:13:36.399
All right.
00:13:36.480 --> 00:13:41.840
So you can direct it to, hey, go look in this project, uh, right, find this project folder.
00:13:42.000 --> 00:13:46.080
So it can research any thread, see what was done, understand it.
00:13:46.159 --> 00:13:49.279
Um, it can send a message to any of those threads.
00:13:49.519 --> 00:13:58.559
So it is just absolutely crazy how a voice mode, because the old advanced voice mode couldn't do that.
00:13:58.799 --> 00:14:00.720
Um, right now you can't.
00:14:00.799 --> 00:14:05.519
And this is again combining the power of codex uh with this technology, right?
00:14:05.600 --> 00:14:09.039
So I'll just walk you through how I was using this on my walk this morning.
00:14:09.120 --> 00:14:11.840
I know the name of most of my projects inside codex.
00:14:12.080 --> 00:14:21.039
And I just said, hey, walk me through every single major thread in these, you know, project folders one by one at the end.
00:14:21.200 --> 00:14:25.519
Um, you know, give me a brief update and what next steps may be.
00:14:25.679 --> 00:14:36.320
If you're not sure of a next step, suggest one for me based on, you know, what you know about me, what's in my uh agents MD file for that folder or for you know, codex in general.
00:14:36.399 --> 00:14:39.039
So it knows my overarching goals and it knows the project goals.
00:14:39.120 --> 00:14:43.759
And then it's gonna go in there, it's gonna look at all that context and then just make me make decisions, right?
00:14:43.919 --> 00:15:00.799
This is why I think on my walk uh uh sorry, yesterday, um, I was more productive in that one hour on my phone, just talking in my earpods, than I would have been probably in three or four hours doing the exact same thing in front of my computer.
00:15:00.960 --> 00:15:02.639
I talk about this all the time.
00:15:03.360 --> 00:15:05.600
The internet is made to distract you, right?
00:15:05.679 --> 00:15:10.399
And even for me, it can be distracting working in codecs, right?
00:15:10.480 --> 00:15:13.600
Because I have all my browser tabs open inside codecs.
00:15:13.759 --> 00:15:23.679
Um, so something about just the combination of rambling and being able to control any of these threads um and just having that real focused time.
00:15:24.159 --> 00:15:25.519
I got so much done, right?
00:15:25.600 --> 00:15:26.639
And in that one hour walk.
00:15:26.799 --> 00:15:38.320
But, anyways, uh kind of advanced tip number one is know that you can with your voice, any new chat can understand, read, write, and do anything to any thread.
00:15:38.399 --> 00:15:41.919
So it doesn't really matter for me from an organizational perspective.
00:15:42.080 --> 00:15:46.399
I would really like to just be able to go into a certain thread and pick it up from there, right?
00:15:46.480 --> 00:15:50.240
I have all these uh chief of staff threads inside of each project folder.
00:15:50.399 --> 00:15:54.080
That would be preferable for me because I like things to be a little organized, right?
00:15:54.159 --> 00:16:02.799
And then you have this chat that's down there in your recense, but overall it's okay because when it does make changes, it will actually go in there and send a message in those chats.
00:16:02.879 --> 00:16:04.240
So it's not like it gets lost.
00:16:04.320 --> 00:16:07.279
And I do have another advanced tip later that can help with this.
00:16:07.440 --> 00:16:17.039
All right, so uh number two, GPT Live can't use connectors and codecs with Chat GPT Live can't.
00:16:17.200 --> 00:16:22.799
So I already referenced this, but this is huge because GPT Live by itself, it's great.
00:16:22.879 --> 00:16:26.159
Um, right, it's more of I think an advanced party trick.
00:16:26.240 --> 00:16:47.519
And I do hope, um, and I know the team has alluded to this online that they are going to eventually bring connectors to GPT Live, but at least for me and how I want to use um, you know, Chat GPT, I need it to be connected to those, you know, 30 or so uh, you know, connected integrations and MCP servers, right?
00:16:47.600 --> 00:16:52.720
If not, it's just you know a better way to browse the internet, um, which is fine, right?
00:16:52.799 --> 00:16:54.720
But I really want to use this to get work done.
00:16:54.879 --> 00:16:58.399
And that is why this combination inside codex is amazing.
00:16:58.480 --> 00:16:59.600
And I don't know why.
00:16:59.759 --> 00:17:03.279
I literally didn't see anyone talk about this or reference this, right?
00:17:03.360 --> 00:17:10.960
I, you know, I follow the the chatter and you know, I've watched a couple of videos of people giving their uh opinions on this, and no one is mentioning this, right?
00:17:11.119 --> 00:17:25.519
This is the biggest unlock right there to be able to go and go through your entire inbox, to go through your uh, you know, everything in Slack and to be able to talk about it and just say, yes, send this, yes, draft this, uh, no, save that to my Google Drive, right?
00:17:25.680 --> 00:17:27.839
Just to be able to go through all those things.
00:17:27.920 --> 00:17:31.119
Uh is it's this is what people have been wanting for so long.
00:17:31.279 --> 00:17:33.039
This is the Jarvis, right?
00:17:33.119 --> 00:17:34.079
Hey, what's important?
00:17:34.240 --> 00:17:46.880
Go look in all of, you know, go look in my in my CRM, uh, go look in my uh I don't know, ERP, alphabet soup, whatever you want to say, my my my drive, my linear, whatever programs you're using that are connected inside codecs.
00:17:47.039 --> 00:17:52.799
Go through all those, triage those, ask me what you want, you know, what are the most important decisions I need to make.
00:17:52.880 --> 00:17:55.359
And if you have read, write access, right?
00:17:55.519 --> 00:18:00.720
You can just start making those decisions in codecs and actually just go do the work in those programs for you.
00:18:01.039 --> 00:18:01.359
All right.
00:18:01.440 --> 00:18:02.400
So that's number two.
00:18:03.119 --> 00:18:05.599
Connectors is a big unlock.
00:18:06.079 --> 00:18:10.640
All right, number three, um, you can schedule, right?
00:18:11.359 --> 00:18:14.960
The same way that you would um inside of ChatGPT.
00:18:15.440 --> 00:18:28.000
So yeah, this is another one of those things that you can't overlook just that you're using voice mode, you can't overlook just the normal power of ChatGPT, right?
00:18:28.160 --> 00:18:38.400
So one of the things um if you use Chat GPT online or uh the ChatGPT work online um is you can have repeatable tasks.
00:18:38.480 --> 00:18:39.839
So even when you're talking, right?
00:18:39.920 --> 00:18:40.880
I did this a couple of times.
00:18:40.960 --> 00:18:43.519
I'm like, ah, I'm gonna keep missing this thing, right?
00:18:43.680 --> 00:18:49.759
So, you know, I said, hey, you know, every you know, Monday at 7 a.m., you know, run this task.
00:18:49.839 --> 00:19:02.720
This thing that we just did together that, you know, me and uh ChatGPT just collaborated on via this uh ChatGPT voice, that needs to be run, you know, every Monday morning or every Friday afternoon or you know, every day at 4 p.m.
00:19:03.119 --> 00:19:10.079
This that what we just did, let's turn that into a skill and then let's uh have this be a scheduled run.
00:19:10.160 --> 00:19:11.839
So another big uh thing.
00:19:11.920 --> 00:19:17.920
So, you know, as an example, maybe every single day you want to go and through and see any new lead that's come in via HubSpot.
00:19:18.079 --> 00:19:23.440
Uh, you want to enrich that data with clay, and then you know, use the condo MCP.
00:19:23.519 --> 00:19:29.440
That's one I use to help manage my LinkedIn messages to see if you have a LinkedIn connection with those people, right?
00:19:29.519 --> 00:19:32.640
So you can literally do that all via voice first.
00:19:32.799 --> 00:19:38.640
It's gonna learn how to do it all, and then you can say turn that into a skill, run that every single day at 9 a.m.
00:19:38.960 --> 00:19:44.160
Um, and then you can literally, once it's done, go and talk and be like, hey, what happened here?
00:19:44.319 --> 00:19:44.640
Right.
00:19:44.880 --> 00:19:51.119
That process right there, as an example, going into your hub spot, seeing who's new, going in, enriching all that in clay.
00:19:51.200 --> 00:19:54.000
Um, and then, you know, seeing which of these people, right?
00:19:54.079 --> 00:19:58.160
If especially if you're in B2B enterprise sales or SaaS sales, right?
00:19:58.240 --> 00:20:01.119
You know, and you have a big LinkedIn network, you know, like I do.
00:20:01.279 --> 00:20:04.720
That's something that takes a lot of time to do all those things manually, right?
00:20:04.799 --> 00:20:06.240
That might be every single day.
00:20:06.319 --> 00:20:10.000
I don't know if you're an SER, BDR, that might be a third of your day.
00:20:10.160 --> 00:20:11.519
It can be done for you, right?
00:20:11.680 --> 00:20:14.160
Set it up once in ChatGPT voice, set it up as a schedule.
00:20:14.240 --> 00:20:18.400
And then every day you can also be like, hey, check in, walk me through, give me a game plan on this.
00:20:18.640 --> 00:20:25.759
And, you know, in a 10-minute uh ChatGPT voice conversation, you've already done what would have normally taken you three hours and 10 minutes.
00:20:26.000 --> 00:20:27.519
All right, let's go next.
00:20:27.680 --> 00:20:31.359
Number four, uh, stack multiple tasks at once.
00:20:31.519 --> 00:20:33.440
Yeah, you don't just have to give one.
00:20:33.599 --> 00:20:39.359
Uh, you can just kind of ramble on and just keep giving more and more assignments, you know, as you are going back and forth.
00:20:39.519 --> 00:20:42.480
Remember, sometimes Chat GPT will interrupt you.
00:20:42.640 --> 00:20:47.200
You can interrupt it, which is actually fine because that's how a normal conversation goes, right?
00:20:47.519 --> 00:20:51.039
Normal business conversation, sometimes you just interrupt each other, right?
00:20:51.119 --> 00:21:06.640
You might not do that in a big business meeting or if you're meeting with the president of the company, but if you're working with colleagues or people on your team, you probably interrupt each other all the time because if you see someone's going down the wrong path, you don't necessarily want to give them 30 seconds or three minutes to keep going down that path.
00:21:06.799 --> 00:21:08.400
You're like, oh no, no, wait, hold up.
00:21:08.480 --> 00:21:09.680
That's not what I was talking about.
00:21:09.839 --> 00:21:11.519
Let's let's rewind a little bit, right?
00:21:11.599 --> 00:21:22.799
You can do the exact same thing, uh, but also just stack those multiple tasks and the voice will just only return when it needs more uh information from you or when it has updates.
00:21:23.119 --> 00:21:27.279
All right, the big unlock here, use your iPhone.
00:21:27.359 --> 00:21:27.839
My gosh.
00:21:27.920 --> 00:21:33.119
But it's a little tricky because remember, all right, uh Codex doesn't have an app.
00:21:33.200 --> 00:21:34.640
It is in the ChatGPT app.
00:21:34.720 --> 00:21:36.079
So confusing part here.
00:21:36.240 --> 00:21:44.480
If you go into the ChatGPT app and you're looking for that uh little button I told you to push, that's just gonna launch GPT live, which is not what you want.
00:21:44.720 --> 00:21:56.400
So you're gonna go onto your iPhone, you're gonna click remote, then at the bottom of the screen, uh you're gonna click that um that button to start a um Chat GPT voice.
00:21:56.480 --> 00:21:56.880
All right.
00:21:56.960 --> 00:21:59.839
So don't just open your uh Chat GPT app.
00:22:00.240 --> 00:22:03.359
On your iPhone and click the voice chat button.
00:22:03.519 --> 00:22:08.400
You need to first click remote because that's essentially then at that point, and this is what I was doing today.
00:22:08.559 --> 00:22:11.279
That's how you are literally on the phone, right?
00:22:11.359 --> 00:22:13.119
For me, quite literally hands free.
00:22:13.200 --> 00:22:21.279
I had an AirPod, you know, one AirPod in my ear, and I was literally controlling my entire computer, working on multiple projects, right?
00:22:21.359 --> 00:22:34.000
Going through all those folders, and it was downloading, uploading, opening programs, changing things, doing the things that I would normally be doing, doing it all hands-free, just giving uh you know my my Jarvis instructions.
00:22:34.160 --> 00:22:34.559
All right.
00:22:34.720 --> 00:22:38.480
All right, number six, a spoken update is not proof.
00:22:38.559 --> 00:22:38.720
All right.
00:22:38.799 --> 00:22:40.160
And I talked about this earlier.
00:22:40.319 --> 00:22:42.240
You should require a durable artifact.
00:22:42.319 --> 00:22:42.960
What does that mean?
00:22:43.119 --> 00:22:47.920
All right, when you go back, especially right, and this is something I really found yesterday morning.
00:22:48.000 --> 00:22:53.519
Um, I was looking back through the the um transcript of what I said, and I'm like, wait, how did we get this done?
00:22:53.599 --> 00:22:53.839
Right.
00:22:53.920 --> 00:22:58.160
Because sometimes all you get is what you said and what ChatGPT said.
00:22:58.240 --> 00:23:12.799
So, you know, one thing I would encourage you to do in this voice conversation, or you know, you can leave this in your um agents MD file inside of any project folder is just say, hey, always require written evidence when you're done, right?
00:23:12.960 --> 00:23:17.839
Or you know, build a, you know, an outline every single time that you complete the tasks.
00:23:17.920 --> 00:23:24.960
Uh, you know, make sure you outline what was done, or maybe you have a folder, um, a file, you know, whether it's locally, et cetera.
00:23:25.119 --> 00:23:35.440
Every time you um, you know, complete a run, complete a task, complete a project, upload this file and say exactly what was changed, what was done, where the file location is, et cetera.
00:23:35.599 --> 00:23:36.799
Um, that's huge.
00:23:36.960 --> 00:23:43.920
You always need written evidence because, yeah, it's nice to be able to just flow with voice mode, but sometimes you need that data.
00:23:44.079 --> 00:23:45.119
You need that data, right?
00:23:45.200 --> 00:23:55.279
Maybe you want it in a markdown file, maybe you want it uploaded to your Google Drive, maybe you just want it in line in the in the thread inside codecs, right, as a bullet point, but you need that written proof.
00:23:55.440 --> 00:24:09.279
And then last but not least, and this one's really cool, another one that I haven't seen many people mention, but there's literally on the desktop version, if you click that little orb, you can drag it.
00:24:09.440 --> 00:24:09.759
All right.
00:24:09.920 --> 00:24:13.759
And you don't even have to have codex kind of active or open on your screen.
00:24:13.839 --> 00:24:17.519
This is one thing I'll hope I'll be able to uh to kind of demo.
00:24:17.680 --> 00:24:22.559
Um, but all you have to do is pull the little orb uh away, right?
00:24:22.799 --> 00:24:25.519
Which it's kind of hidden, right?
00:24:25.599 --> 00:24:27.200
You don't even know that you can do it.
00:24:27.359 --> 00:24:28.240
A lot of times, right?
00:24:28.319 --> 00:24:35.359
One thing I do when there's new features, I just click around because you know, open AI is known for you know hiding little fun Easter eggs.
00:24:35.440 --> 00:24:38.880
Uh, you know, if you're talking about like codex pets or anything like that.
00:24:39.039 --> 00:24:43.519
Um, but yeah, I just clicked and I was like, huh, you can drag this thing, right?
00:24:43.599 --> 00:24:46.160
Um, and then I saw maybe one or two other people mention this.
00:24:46.240 --> 00:24:58.240
But yeah, for the most part, you can just have that little orb just chill on your desktop and you have this omnipresent agent that's just gonna chill, it's gonna do absolutely nothing until you tell it to, right?
00:24:58.319 --> 00:25:02.799
So one little uh little uh, I guess not cheat code, but best practice for this.
00:25:02.960 --> 00:25:10.079
Um, especially right, I like to listen to music a lot, and you can't really do that because it's listening for any word, right?
00:25:10.160 --> 00:25:21.039
So I will just have an AirPod in listening to music, and then on my Mac, I just you know set the output to my AirPod so I could still listen to music or be on a call with a colleague, right?
00:25:21.119 --> 00:25:21.839
Something like that.
00:25:22.000 --> 00:25:29.759
And then I can still, you know, I can still mute the mic, but um, if it's just me in front of my computer, that's all I really need to do.
00:25:29.920 --> 00:25:37.599
I can listen to my music in uh in airpod and use my my um my computer microphone to then talk to the orb, right?
00:25:37.680 --> 00:25:39.440
That sounds weird talking to an orb.
00:25:39.599 --> 00:25:43.119
All right, but it just uh allows you to have that omnipresent agent.
00:25:43.440 --> 00:25:44.079
All right.
00:25:44.640 --> 00:25:46.079
My gosh, what could go wrong?
00:25:46.240 --> 00:25:46.880
Here we go.
00:25:47.039 --> 00:25:48.319
Let's go live.
00:25:48.559 --> 00:25:50.160
I'm not I'm not gonna lie.
00:25:50.319 --> 00:25:59.359
Sometimes, especially because I I have a lot of uh more uh kind of uh private, uh you know, uh personal private information in my codex.
00:25:59.599 --> 00:26:11.680
You know, sometimes when I'm like, oh, I gotta share my my entire codex, I'm you know, sweating bullets a little bit, but I I always want you guys to see, you know, see how this uh goes live and kind of uh see how it works.
00:26:11.920 --> 00:26:14.880
All right, let's try this live live stream audience.
00:26:14.960 --> 00:26:17.759
If you could let me know if you can see my screen.
00:26:19.039 --> 00:26:22.720
All right, and hopefully we'll be able to hear the audio as well.
00:26:24.400 --> 00:26:38.559
So uh as a reminder, this is the and yeah, if you do want to see the video version of this, if you're listening on the podcast, in the show notes, there's always a link to the episode page on our website, and you can go watch the video version.
00:26:38.799 --> 00:26:42.880
So just skip to uh, you know, I don't know, about 26 minutes or so.
00:26:43.440 --> 00:26:49.039
Okay, so at the bottom here, you'll see um there's a normal microphone.
00:26:49.200 --> 00:26:50.000
Don't click that.
00:26:50.160 --> 00:26:51.279
That is the dictation.
00:26:51.440 --> 00:26:54.240
Uh, the other one is to start a new voice chat.
00:26:54.400 --> 00:26:56.000
All right, so let's just go ahead.
00:26:56.079 --> 00:27:01.279
I'm gonna go to um make this an unattached chat thread.
00:27:01.359 --> 00:27:03.839
Um, and then I'm just gonna riff a little bit here.
00:27:04.000 --> 00:27:04.400
All right.
00:27:04.559 --> 00:27:17.519
Um, so if you hear me talking, I might hit the pause, uh, the mute button so I can keep talking to you all and explain what's going on, but otherwise assume that I'm just talking from here on out uh to Chat GPT.
00:27:17.599 --> 00:27:18.720
So let's get it going.
00:27:18.880 --> 00:27:36.160
I'm gonna actually uh work on a project that I wanted to do because I put a lot of work into a recent um speech that I did, and there were some things that happened in there that I'm like, huh, I should probably pull that um and do do something more with that speech that I did.
00:27:36.319 --> 00:27:39.440
So uh let's go ahead and get started here.
00:27:50.799 --> 00:27:52.319
Gotta love the live demos.
00:27:52.400 --> 00:27:57.200
I've literally never seen this uh this screen come up before where it said voice chat couldn't start.
00:27:57.359 --> 00:27:58.319
Oh, that's funny.
00:27:58.480 --> 00:28:00.079
All right, let's try it again.
00:28:02.400 --> 00:28:06.400
Uh hey, what would you like to try again?
00:28:06.720 --> 00:28:07.440
All right, cool.
00:28:07.599 --> 00:28:09.759
No, so uh can you look?
00:28:09.920 --> 00:28:15.279
It's maybe in my downloads folder, but uh maybe from like two or three weeks ago.
00:28:15.440 --> 00:28:22.400
Um I did this presentation for a firm and uh there's probably like a PowerPoint.
00:28:22.640 --> 00:28:24.799
It was about um ChatGPT work.
00:28:25.039 --> 00:28:26.480
Let me know if you can find it.
00:28:27.200 --> 00:28:31.119
I'll check your recent presentation files for that.
00:28:31.519 --> 00:28:37.599
All right, so ChatGPT work PowerPoint in your downloads so you can open it from the file card on your screen.
00:28:38.000 --> 00:28:39.440
Oh, cool, great.
00:28:39.759 --> 00:28:44.720
So can you just kind of go through and bullet point what I talked about and what I didn't?
00:28:44.880 --> 00:29:00.079
Um, and then while you're doing that, can you also open uh Chrome and then go to YouTube and find the live stream that OpenAI did a couple of weeks ago for the Chat GPT uh work announcement?
00:29:00.240 --> 00:29:14.000
It's probably like two weeks ago or so, um, and then copy that link from that open AI live stream and then use computer use um and open up an app on my computer.
00:29:14.079 --> 00:29:15.119
It's called Parrot.
00:29:15.599 --> 00:29:17.279
Um, it's an app that I built.
00:29:17.359 --> 00:29:27.039
And then I want you to take that YouTube uh URL from the OpenAI live stream and I want you to paste it into Parrot and create a transcription.
00:29:27.119 --> 00:29:33.440
Um, and I want you to look at that transcription, which will tell you, you know, what they talked about in that 30 or so minute live stream.
00:29:33.680 --> 00:29:45.920
And essentially, I want you to look and find um what I did not cover um in my affirm presentation that was covered in the open AI live stream.
00:29:46.000 --> 00:29:49.200
So uh just take take your time and start working on that.
00:29:50.240 --> 00:29:51.599
I'll get started on that.
00:29:52.640 --> 00:29:59.039
I'm comparing your affirm deck with the open AI work launch stream now, using Chrome and Terry for the transcript.
00:30:00.880 --> 00:30:01.440
All right.
00:30:03.119 --> 00:30:07.759
So I just put this on mute, so you'll probably still hear Chad GPT.
00:30:07.920 --> 00:30:08.880
Oh, it's not on mute.
00:30:11.519 --> 00:30:12.160
All right.
00:30:14.400 --> 00:30:15.039
There we go.
00:30:15.119 --> 00:30:16.720
I think I think I'm on mute now.
00:30:17.839 --> 00:30:19.759
I'm not, I have no clue what's going on.
00:30:20.000 --> 00:30:22.480
Okay, that's that's weird another time.
00:30:22.799 --> 00:30:33.680
Um this it's it's it's showing the the transcript here, but uh obviously I'm talking to the live stream audience now, not Chad GBT, even though it's still uh transcribing.
00:30:33.759 --> 00:30:36.160
So uh hey chat, are you still listening to this?
00:30:41.519 --> 00:30:41.839
Okay.
00:30:42.880 --> 00:30:43.839
Interesting.
00:30:44.480 --> 00:30:50.480
Love love doing these um love doing these these live streams um here.
00:30:50.960 --> 00:30:58.160
Um because I I always run through and do the demo, and then I always get these weird things that that happen that didn't happen before.
00:30:58.319 --> 00:31:06.400
So uh it was muted, but it was still um dictating what I was saying, which uh didn't happen in all of my testing.
00:31:06.559 --> 00:31:15.920
Anyways, so let me explain what I did and what's happening now because it's already opened up this program that I created called Parrot.
00:31:16.720 --> 00:31:23.920
Uh right, just this uh awesome program that I've you know built up over the past uh however long.
00:31:24.319 --> 00:31:28.079
So I told it, go find this presentation I did two weeks ago.
00:31:28.240 --> 00:31:36.559
I don't remember what was in it, uh, because I literally had to build it, like rebuild it the night before because it was right when OpenAI announced ChatGPT Work.
00:31:36.640 --> 00:31:40.799
And I didn't remember if I got everything from the live stream into that presentation.
00:31:41.039 --> 00:31:49.759
And I thought that maybe at some point I'll do an entirely new course or something like that on Codex or ChatGPT Work.
00:31:49.839 --> 00:31:54.559
Um, so I'm like, well, I put together a lot of work in this presentation and I thought it was pretty good.
00:31:54.640 --> 00:31:57.359
Uh, but there's probably some things I didn't get to.
00:31:57.440 --> 00:32:03.759
Uh so what's already happened is uh Codex went in or ChatGPT voice inside codex went in.
00:32:03.920 --> 00:32:06.240
It opened up this program that I built.
00:32:06.319 --> 00:32:11.279
Um, it grabbed the um the URL and it went in and pasted it.
00:32:11.359 --> 00:32:13.359
It looks like it has the transcript up.
00:32:13.440 --> 00:32:16.160
Um, and we'll see what's what's happening here.
00:32:18.400 --> 00:32:23.279
The parent transcript is captured, so I could ground this in what they actually covered.
00:32:23.440 --> 00:32:24.400
Here's the quick take.
00:32:24.640 --> 00:32:28.720
Your deck focused on the desktop agent and agents MD workflow.
00:32:28.880 --> 00:32:32.799
The stream emphasized connected workflows and shareable outcomes.
00:32:32.960 --> 00:32:36.799
Those connectors across Slack, Calendar, and Excel to PowerPoint to Slack.
00:32:37.119 --> 00:32:39.920
Can you maybe just give me can you maybe just give me bullet points?
00:32:40.400 --> 00:32:41.039
Didn't cover.
00:32:42.000 --> 00:32:52.319
Can you maybe just give me bullet points of the biggest things that I did not cover in my affirm presentation that was in the live stream?
00:32:53.759 --> 00:32:54.319
Sure.
00:33:00.640 --> 00:33:16.720
The biggest things you didn't cover were connected work across tools like Slack, Gmail, and calendar, end-to-end finance workflows like Excel to PowerPoint reporting, interactive sites for dashboards or internal tools, starting tasks on mobile continuously.
00:33:16.960 --> 00:33:17.359
That's a good point.
00:33:18.079 --> 00:33:26.880
I think that there was a new update a couple like uh maybe it was Thursday, but I don't even think OpenAI put anything on their website about it.
00:33:26.960 --> 00:33:28.240
It was something in sites.
00:33:28.480 --> 00:33:34.319
Um, so see if you can look up maybe their uh change log for codecs or sorry for sites.
00:33:34.480 --> 00:33:37.119
Um, I think it was something about there's some new analytics.
00:33:37.279 --> 00:33:38.799
Can you look that piece up?
00:33:39.519 --> 00:33:41.200
Yeah, I'll check that.
00:33:41.839 --> 00:33:47.599
Um, also look in my uh transcripts for your everyday AI.
00:33:48.000 --> 00:33:55.119
Um, because I, you know, every Friday and Monday uh we go over kind of like new features and new updates.
00:33:55.200 --> 00:33:57.039
Uh so can you just check this?
00:33:57.200 --> 00:34:04.079
Uh, the last week's um shows because I think there were a couple other uh codex updates in there.
00:34:04.160 --> 00:34:16.559
So you can just, you know, open that up, or I think there's a folder um on my desktop if you want to, or not my desktop, maybe in documents if you want to use computer use, or you can just go to our website and look at the transcript there.
00:34:16.719 --> 00:34:22.960
Um, because sometimes they only update their uh kind of change log like once a week.
00:34:23.119 --> 00:34:26.159
Um, so we obviously put out shows, you know, every day.
00:34:26.320 --> 00:34:29.039
So just go um specifically on sites.
00:34:29.119 --> 00:34:31.039
I want you to get more information on that.
00:34:31.679 --> 00:34:32.159
Got it.
00:34:32.320 --> 00:34:38.159
I'll check the official notes, the sites docs, and your recent transcripts for anything site specific.
00:34:38.480 --> 00:34:38.719
Okay.
00:34:38.880 --> 00:34:56.800
And while you're doing that, um, or maybe first, can you just uh create a very simple um document and then just download it and save it to my computer uh that just shows kind of what I talked about in the affirm presentation and then what I did not cover.
00:34:56.960 --> 00:35:01.920
Um, and just kind of download that to my computer, but also save it to my Google Drive just so I have it.
00:35:02.000 --> 00:35:06.079
And then, you know, name it so it's easy for me to see and understand what's in there too.
00:35:06.719 --> 00:35:07.199
Got it.
00:35:07.360 --> 00:35:09.920
I'll put that together and save it both places.
00:35:12.559 --> 00:35:12.880
Okay.
00:35:13.280 --> 00:35:16.639
So I realize what I did wrong now, guys, earlier.
00:35:16.719 --> 00:35:23.039
Um, when I'm like, wait, I it's still catching me speak, even no, that was a human error.
00:35:23.119 --> 00:35:29.360
Um, I accidentally uh turned off the speaker um instead of the microphone.
00:35:29.519 --> 00:35:30.400
So that was my fault.
00:35:30.480 --> 00:35:32.239
So right now I have both muted.
00:35:32.400 --> 00:35:37.760
So uh, you know, uh Chad GPT is still talking to me, but um, it's not super important.
00:35:37.920 --> 00:35:54.880
You know, essentially I just wanted to show you those capabilities because what just happened, even though I kind of fumbled through that demo quite a little bit, um, right, this is something I was gonna do because I knew I put together, like I said, a lot of good information for this uh AFEM presentation, just going over some of the features.
00:35:55.039 --> 00:35:58.000
You know, I had some good visuals, some good content, all that stuff.
00:35:58.079 --> 00:35:58.480
Uh, right.
00:35:58.559 --> 00:35:59.840
So why would I start from scratch?
00:36:00.000 --> 00:36:02.159
But I knew that there was new things that needed to be updated.
00:36:02.320 --> 00:36:07.519
I didn't have 35 minutes to go re-watch the um, you know, ChatGPT live stream.
00:36:07.760 --> 00:36:16.719
So I just had it literally uh use its built-in browser, go find the YouTube channel for OpenAI, find that live stream, take that link.
00:36:16.880 --> 00:36:20.480
It opened up a program that it wasn't even pinned to my desktop.
00:36:20.559 --> 00:36:21.280
So it just found it.
00:36:21.360 --> 00:36:32.960
It opened up the program that I built, it transcribed it, and then it compared uh kind of everything that was in that PowerPoint that it opened in its file browser um to the transcript um from the open AI live stream.
00:36:33.119 --> 00:36:40.400
Now, right now, it's putting it together and it's already, it just told me that it's uh put that document together and it's done.
00:36:40.639 --> 00:36:41.360
So that's good.
00:36:41.440 --> 00:36:44.000
And it also said it confirmed the missing sites update.
00:36:44.079 --> 00:36:47.599
So all right, I I do want to show maybe one or two other things quick.
00:36:47.679 --> 00:36:54.079
So I'm gonna start a new voice chat and here we go.
00:37:00.480 --> 00:37:13.199
Hey, can you um use the Beehive MCP and look at my uh poll from yesterday um and tell me what the results from the poll were.
00:37:15.039 --> 00:37:18.800
Yeah, I'll check yesterday's Beehive poll results quickly.
00:37:22.320 --> 00:37:29.679
All right, so I just muted chat, but uh what I'm showing for our live stream audience here is I'm actually minimizing.
00:37:29.760 --> 00:37:36.400
Uh I'm gonna minimize codex here, and you'll see here kind of this little orb uh floating around on my desktop.
00:37:38.639 --> 00:37:42.639
OpenAI's mu Jarvis Live Mode is leading with 32.
00:37:42.880 --> 00:37:47.360
Claude Opus 5 hands-on has 21, and six people picked other.
00:37:48.320 --> 00:37:48.639
Okay.
00:37:49.039 --> 00:37:51.039
Uh could you just start that over?
00:37:51.119 --> 00:37:52.320
I missed the beginning.
00:37:53.119 --> 00:37:53.679
Sure.
00:37:54.239 --> 00:37:58.159
Yesterday's AI Working Wednesdays poll has 59 votes.
00:37:58.400 --> 00:38:02.000
OpenAI's new Jarvis Live Mode is leading with 32.
00:38:02.239 --> 00:38:06.719
Claude Opus 5 hands-on has 21, and six people picked other.
00:38:08.880 --> 00:38:09.920
Uh cool.
00:38:10.159 --> 00:38:16.639
Can you tell me um what my open rate was um yesterday?
00:38:16.719 --> 00:38:22.400
Uh or sorry, on Monday, July 27th versus the Monday before that.
00:38:22.480 --> 00:38:26.320
I just want to see kind of what the open rates were over those last ones.
00:38:27.920 --> 00:38:28.239
Okay.
00:38:28.480 --> 00:38:31.199
I'll pull up both Mondays and compare them.
00:38:31.519 --> 00:38:39.119
So essentially what I'm doing right now, I just muted both is well, I got rid of codecs, and now I just have this little floating orb here.
00:38:39.199 --> 00:38:39.440
Right.
00:38:39.519 --> 00:38:41.119
So I'm dragging it around my screen.
00:38:41.280 --> 00:38:42.960
I can put it literally anywhere.
00:38:43.039 --> 00:38:47.199
Um, it's showing me, even though I haven't muted, uh, what the open rate was.
00:38:47.360 --> 00:38:56.000
It says um this yesterday or two days ago, it was about 55%, and uh the Monday before it was 58%.
00:38:56.320 --> 00:39:00.079
That's still because you know, opens keep uh trailing in a couple of the days after.
00:39:00.239 --> 00:39:01.280
So uh pretty cool.
00:39:01.440 --> 00:39:04.000
You can see right there, uh some of the basic things.
00:39:04.079 --> 00:39:11.920
So I went through showing you uh multiple tasks at once, kind of stacking those using different connectors and MCPs, right?
00:39:12.079 --> 00:39:15.360
I used my uh you know, Google Drive that's a connector.
00:39:15.519 --> 00:39:22.320
I used an MCP, which is a model context protocol for my newsletter because it doesn't have an official Chat GPT connector.
00:39:22.480 --> 00:39:30.480
I, you know, did things like browsing the web, um, you know, pulling, you know, uh opening other programs on my computer.
00:39:30.559 --> 00:39:32.559
And, you know, it was clicking around, you know.
00:39:32.639 --> 00:39:38.000
Uh you probably saw it, it happened very quickly because computer use is very fast inside GPT 5.6 soul.
00:39:38.320 --> 00:39:42.559
So that's a wrap for the demo portion.
00:39:42.719 --> 00:39:45.519
It didn't go too bad, right?
00:39:45.599 --> 00:39:48.320
Uh maybe we'll see how this actually turns out.
00:39:48.400 --> 00:39:50.400
Hopefully, it recorded all that audio.
00:39:50.559 --> 00:39:53.679
Um, but here's the uh takeaway, right?
00:39:54.320 --> 00:39:59.920
This is a completely uh new way to work, right?
00:40:00.960 --> 00:40:04.320
In almost a new way to think about work, um, right?
00:40:04.480 --> 00:40:06.960
Because even before, right?
00:40:07.840 --> 00:40:20.320
Honestly, like even just 10 days ago before this update came out, for the most part, when I wanted to be the most productive, I was still sitting in my chair and you know, clicking around, right?
00:40:20.480 --> 00:40:22.960
Which is not bad necessarily, right?
00:40:23.199 --> 00:40:26.559
But distraction, overwhelm.
00:40:26.800 --> 00:40:35.920
And sometimes what I found is when you're not actually looking at a screen and when you're able to just kind of ramble and yap, right?
00:40:36.400 --> 00:40:43.199
Um, sometimes you get much better results because you can communicate things sometimes in a much clearer way.
00:40:43.440 --> 00:40:45.360
Because sometimes, especially if you're typing, right?
00:40:45.440 --> 00:40:50.400
Not everyone can, you know, especially if you work in an open office, you can't always ramble, uh, right.
00:40:50.480 --> 00:40:57.519
Or if you're working on something private, maybe you work at home and you can't, you know, talk about certain things, you know, with other people around.
00:40:57.760 --> 00:41:11.760
Um, this is something that for me, I'm not saying I I've struggled to adjust how to work, um, but I've I've had to rethink what it means to work, right?
00:41:11.920 --> 00:41:14.639
And I had a great day working, right?
00:41:14.719 --> 00:41:15.920
I had a great day working yesterday.
00:41:16.079 --> 00:41:34.639
Went out and, like I said, took an hour walk, and it was not only being able to go get outside and touch grass here in Chicago, but I actually think that I got a lot more done in that one hour than I would have gotten done two or three hours doing something very similar using codecs or even ChatGPT voice in front of my computer with all my screens because it's distraction.
00:41:34.719 --> 00:41:38.480
And then I would have said, Oh, I I have to go do all these other things, right?
00:41:38.639 --> 00:41:43.840
Um, so it is definitely the new ChatGPT voice is like having a Jarvis.
00:41:44.079 --> 00:41:54.079
And at least for me, I'm even though I've been Codex pilled since the day it came out, sometimes I still find myself still doing some of the work, right?
00:41:54.239 --> 00:42:13.840
And this has been a refreshing uh change in that because I'm actually just using my brain and thinking a little bit more, uh, trying to think more strategically and creatively, um, and you know, being able to communicate things in a different way and you know, being able to describe all the nuance and you know, having Chat GPT voice sometimes poke holes in my plan.
00:42:14.079 --> 00:42:23.280
So it's been for me a lot more talking and iterating and working through my voice, which for me is really easy, and maybe it will be for you.
00:42:23.360 --> 00:42:25.360
But I hope this episode was helpful.
00:42:25.519 --> 00:42:40.800
Uh, maybe this won't be for you, but there's a good chance that using the new Chat GPT voice is could be the biggest paradigm shift in how you've worked since maybe Chat GPT came out, or even more so than that.
00:42:41.039 --> 00:42:43.039
So uh thank you for tuning in.
00:42:43.119 --> 00:42:47.840
If you haven't already, again, please go to your everydayai.com, sign up for the free daily newsletter.
00:42:48.000 --> 00:42:48.559
Thanks for tuning in.
00:42:48.639 --> 00:42:51.199
We'll see you back tomorrow and every day for more everyday AI.
00:42:51.280 --> 00:42:52.320
Thanks, y'all.
