Ep 883: How To Make Slides with AI: Hands on Comparison With the 9 Most Popular Options (Replay)

WEBVTT
00:00:01.919 --> 00:00:15.759
No matter your role, no matter your industry, no matter your experience level, chances are you still spend a lot of time doing this one thing, making slides, creating those decks, right?
00:00:16.000 --> 00:00:28.320
So whether that's toiling in PowerPoint, copying and clicking in Canva, or working on a template in Google Slides, just about everyone who sits in front of a computer screen spends time creating slides.
00:00:28.559 --> 00:00:36.719
And this was one of the areas of the early generative AI phase where the tools really kind of struggled mightily for years.
00:00:36.960 --> 00:00:42.159
And there was a lot of hoopla over how there wasn't a lot of good AI options.
00:00:42.479 --> 00:00:48.560
Then, kind of silently, yet kind of quickly, we got a host of solutions.
00:00:48.799 --> 00:00:59.359
But I think most people overlooked just how good many of these AI tools are at generating slides because we essentially saw an avalanche of model capabilities all hit us at once.
00:00:59.520 --> 00:01:07.200
And I think that reasoning models in agentic systems took away the spotlight as slide generation kind of arrived at the same time.
00:01:07.359 --> 00:01:09.200
So no one really took notice.
00:01:09.439 --> 00:01:10.400
Well, we did.
00:01:10.560 --> 00:01:22.000
And that's why we're going to put AI to work on Wednesday and take a look at at least nine, well, maybe 10 of the best ways to generate slides with AI, all aimed at beginners.
00:01:22.159 --> 00:01:25.920
And we're doing it all live, errors, hiccups, and all.
00:01:26.079 --> 00:01:27.359
So which is best?
00:01:27.519 --> 00:01:29.200
Will PowerPoint shine?
00:01:29.359 --> 00:01:32.879
Uh, what about the nano banana integration in Notebook LM?
00:01:32.959 --> 00:01:39.280
Or maybe the old kid on the block with gamma or the new token hungry claw design could take the crown.
00:01:39.359 --> 00:01:40.079
I don't know.
00:01:40.239 --> 00:01:41.200
We're gonna see.
00:01:41.280 --> 00:01:43.280
Let's find out and get into it.
00:01:43.439 --> 00:01:46.560
So here is the big picture.
00:01:48.159 --> 00:02:01.519
The capability gap right now makes it hard to keep up because I can almost guarantee, even if you uh watch this show every day, there's gonna be one of these tools that I talk about, and you're gonna be like, wait, I didn't know you could create slides that way.
00:02:01.680 --> 00:02:08.240
And it's just now by default, a lot of these large language models create slides, uh, right?
00:02:08.479 --> 00:02:15.439
You know, it's something that kind of snuck in in terms of capabilities, you know, around six to nine months ago.
00:02:15.599 --> 00:02:20.479
Like I said, about the same time that we got all of these agentic systems and reasoning models, right?
00:02:20.639 --> 00:02:32.879
But I remember telling people uh like nine months ago, people didn't know that you could just create a spreadsheet in Chat GPT or you know, create a PowerPoint in Claude, and you can't, right?
00:02:32.960 --> 00:02:43.680
And finally, now with Google Gemini catching up to the pack, all of the big players by default can create artifacts like that if you just use the right model and ask it to.
00:02:43.919 --> 00:02:58.240
So when you combine though, your dynamic data inputs and then the personalization and the customization that comes by default out of large language models and schedule those things, you can have on-demand personalized decks, uh, right.
00:02:58.319 --> 00:03:08.400
And then when you can throw in your brand options as well, a lot of people overlook just how capable this is, right?
00:03:08.639 --> 00:03:20.960
Because I think slide generation has now turned from a task that so many people spend so much time on to now you can get an on-demand, pretty polished draft at least in minutes.
00:03:21.120 --> 00:03:23.280
So, on today's show, here's what we're gonna cover.
00:03:23.360 --> 00:03:29.680
We're gonna go over the pros and the cons of the top nine options and see how they make slides and look at their output.
00:03:29.759 --> 00:03:35.360
So, everything from Chat GPT and Claude, Gemini, Gamma, PowerPoint, and more.
00:03:35.759 --> 00:03:41.919
You're gonna learn how the tech actually works, at least on the surface level, and go over best practices.
00:03:42.000 --> 00:03:49.680
And you'll instantly, by the end of this, if you put this into practice, you're instantly gonna be able to implement going from zero to draft by the end of the show.
00:03:49.840 --> 00:03:52.000
No more overwhelm, no more confusion.
00:03:52.159 --> 00:03:52.879
Let's get started.
00:03:52.960 --> 00:03:54.240
Welcome to everyday AI.
00:03:54.319 --> 00:03:56.400
My name's Jordan Wilson, and well, we do this every day.
00:03:56.479 --> 00:04:05.039
It's your daily unedited, unscripted live stream podcasts, and free daily newsletter, helping everyday business leaders like you and me make sense of the AI noise.
00:04:05.360 --> 00:04:07.840
Uh, these updates are coming nonstop.
00:04:07.919 --> 00:04:11.120
I tell you what matters, what doesn't, how to use it.
00:04:11.280 --> 00:04:16.959
You take that information, and all of a sudden you're the smartest person in AI and you can go grow grow your company and career.
00:04:17.199 --> 00:04:21.439
Starts here unedited, unscripted live stream podcast, but take it to the next level.
00:04:21.600 --> 00:04:24.639
Make sure you go to our website, your everydayai.com.
00:04:24.800 --> 00:04:33.360
Uh, in today's newsletter, we're gonna be not only recapping the highlights from today's show in case you miss anything, uh, but also all the other AI news you need to know to get ahead.
00:04:33.519 --> 00:04:37.439
And yeah, this is gonna be one of those uh episodes that's a little more visual.
00:04:37.600 --> 00:04:45.680
So you might wanna, for a podcast audience, yeah, check out today's newsletter uh and you you know, go watch uh this video on our website.
00:04:45.759 --> 00:04:48.399
So we link to it in the newsletter, it's always on our website too.
00:04:48.560 --> 00:04:50.639
So let's get straight into it.
00:04:50.800 --> 00:04:53.680
Uh, and let me say this this is meant to be a quick demo.
00:04:53.839 --> 00:04:54.160
All right.
00:04:54.240 --> 00:04:57.519
I'm not gonna show you my best practices using one system.
00:04:57.920 --> 00:05:02.240
Uh, I think that, well, I hope at least that this is gonna be more appealing.
00:05:02.319 --> 00:05:04.800
And you know, this is actually, I put this out in the newsletter.
00:05:04.959 --> 00:05:07.680
You all voted for this as the thing that you wanted to learn most.
00:05:07.759 --> 00:05:11.439
I want to start doing uh more practical uh guides, right?
00:05:11.519 --> 00:05:17.439
And instead of going deeper on one system, say, hey, here's how you do data analysis in three to five tools.
00:05:17.600 --> 00:05:20.319
Here's how you do uh, you know, create slides or decks.
00:05:20.480 --> 00:05:24.240
Here's how you can create, you know, quick disposable apps or websites.
00:05:24.319 --> 00:05:29.360
Uh so gonna take these a little bit more topic-based, but again, I'm doing this very generally.
00:05:29.439 --> 00:05:31.199
My prompt is gonna be overly simple.
00:05:31.360 --> 00:05:37.600
I'm not gonna be, you know, using uh, you know, codecs and or using skills and plugins.
00:05:37.680 --> 00:05:39.439
I'm doing something that's so simple.
00:05:39.680 --> 00:05:41.680
Your grandma could go and do the same thing.
00:05:41.759 --> 00:05:44.959
Or if you are a grandma, you can do it along with me, right?
00:05:45.120 --> 00:05:47.040
I'm making it that simple, right?
00:05:47.120 --> 00:05:52.160
The simplest prompt, uh, you know, basic paid plans, nothing crazy.
00:05:52.399 --> 00:06:02.720
So we're gonna be seeing how a model can correctly follow the input because we're not just gonna be judging the quality, all right, because models by default are multimodal.
00:06:02.800 --> 00:06:07.839
You have to be able to understand uh how they work, uh, the pros and the cons.
00:06:08.000 --> 00:06:11.920
So, you know, the prompt that I'm choosing is intentionally vague.
00:06:12.000 --> 00:06:14.800
So I can see how these models, number one, handle it.
00:06:15.040 --> 00:06:20.160
Number two, because we're gonna be indirectly testing prompt adherence, tool calling, and also taste.
00:06:20.319 --> 00:06:22.720
So again, this is not a final workflow.
00:06:22.879 --> 00:06:28.720
And if you are doing something like this, right, pick the one that you want, double down, but let's get in.
00:06:28.879 --> 00:06:29.920
Let's start live.
00:06:30.079 --> 00:06:30.800
Oh my gosh.
00:06:30.959 --> 00:06:33.360
Like, not gonna lie, this one I'm a little nervous on.
00:06:33.519 --> 00:06:35.680
I'm also at Microsoft Build right now.
00:06:35.759 --> 00:06:37.680
Uh, so I just have my little laptop.
00:06:37.839 --> 00:06:41.199
Normally I have a lot of screens, so might be a little jumping around.
00:06:41.360 --> 00:06:43.120
Uh, hopefully not.
00:06:43.680 --> 00:06:44.639
Let's get started.
00:06:44.800 --> 00:06:45.360
Let's get started.
00:06:45.519 --> 00:06:46.480
Live stream audience.
00:06:46.560 --> 00:06:46.959
Let me know.
00:06:47.040 --> 00:06:48.000
Can you see my screen?
00:06:48.079 --> 00:06:48.879
Hopefully you can.
00:06:48.959 --> 00:06:50.480
All right, we're gonna go in order.
00:06:50.560 --> 00:06:53.600
Uh, and and here is the uh the tricky part.
00:06:54.160 --> 00:07:02.639
Uh, there's gonna be a little bit, uh, because not all of these are just gonna be, you know, I click, you know, put my prompt in, click go.
00:07:02.800 --> 00:07:07.439
Some of them force you through some some different prompts and uh which can be a good or a bad thing.
00:07:07.519 --> 00:07:15.120
So I'm gonna try to walk you through which ones are accepting one-shot generations versus which ones are asking me follow-up questions, right?
00:07:15.279 --> 00:07:19.680
Which I think asking follow-up questions in most cases is usually a good thing.
00:07:19.839 --> 00:07:20.959
So keep that in mind.
00:07:21.120 --> 00:07:33.519
The sample is not going to be consistent all the way across because by default, some of these systems do kind of, you know, force you or prompt you uh to go through a certain series of things to get more information.
00:07:33.680 --> 00:07:35.040
All right, let's start first.
00:07:35.199 --> 00:07:39.519
So the first one we're gonna go over is Claw Design, and then we're gonna go over Claude.
00:07:39.759 --> 00:07:43.759
All right, and just FYI, these are very token hungry.
00:07:43.839 --> 00:07:50.639
So if you're on a$20 a month plan, even if you try to do these two comparisons, you might run out of uh tokens for your five-hour limit.
00:07:50.800 --> 00:07:52.079
This also is gonna take a while.
00:07:52.240 --> 00:07:53.680
These ones, that's why I'm doing them first.
00:07:53.759 --> 00:07:57.519
All right, so Claude Design, uh, you know, I don't use it a lot in this account.
00:07:57.600 --> 00:07:59.519
I have another account where I use it a little bit more.
00:07:59.600 --> 00:08:02.240
Uh, but all you're gonna do is you're gonna go to claw.ai.
00:08:02.639 --> 00:08:05.439
And then on the left hand side, there is a little design tab.
00:08:05.519 --> 00:08:09.360
So claw design is technically its own kind of little app.
00:08:09.519 --> 00:08:11.920
It's not the normal uh clawed interface.
00:08:12.079 --> 00:08:14.319
Also, it only exists on the web version.
00:08:14.399 --> 00:08:17.040
There is no clawed design if you use the desktop.
00:08:17.279 --> 00:08:22.639
All right, and then there are a couple uh different things that you can do, and this is a research preview.
00:08:22.720 --> 00:08:25.839
Uh, so there's a prototype, a slide deck, a template, or other.
00:08:26.000 --> 00:08:29.199
So right now I'm just gonna go everyday AI, news that matters.
00:08:29.279 --> 00:08:31.839
We're gonna go to slide deck, click create.
00:08:32.000 --> 00:08:41.840
It's gonna take me through a little um uh kind of prompt where normally I could uh go into a design system, add a screenshot, attach a code base, drag a file in, all that.
00:08:41.919 --> 00:08:42.960
So I'm not gonna do any of that.
00:08:43.039 --> 00:08:48.879
All I'm gonna do is put my prompt in, and I am gonna be using Claude Opus 4.8.
00:08:49.200 --> 00:08:49.759
All right.
00:08:49.919 --> 00:08:59.679
All I'm saying, and this is the same prompt I'm gonna be using in each instance, and this is why we're gonna be carefully following um prompt adherence, uh, tool calling, and taste.
00:08:59.840 --> 00:09:01.440
Those are kind of the three things we're looking at.
00:09:01.600 --> 00:09:11.279
So the same prompt I'm putting in for all of them, please look up the latest AI News That Matters episode from the Everyday AI podcast by Jordan Wilson.
00:09:11.440 --> 00:09:21.120
Please create a slide deck giving each of the main stories uh a one slide recap, one intro slide, and one outro slide.
00:09:21.279 --> 00:09:27.039
So I believe in Mondays, so from two days ago, so on Mondays, we go over the AI news that matters.
00:09:27.200 --> 00:09:29.440
Usually we do like seven to eight stories.
00:09:29.600 --> 00:09:30.720
I think this Monday was seven.
00:09:30.799 --> 00:09:33.919
So in theory, there should be nine slides, an intro slide.
00:09:34.080 --> 00:09:37.360
Each news story should have one slide and then an outro slide.
00:09:37.519 --> 00:09:42.080
All right, so I'm going to send this inside Claw Design.
00:09:42.159 --> 00:09:53.600
Uh, and I do believe uh I'm gonna have to wait here uh on the page a little bit uh because I do think it's going to ask me some follow-up questions because I didn't give it anything else, uh, but I'm gonna give it a second.
00:09:53.759 --> 00:10:03.519
So one thing I'll just, you know, as I go along, if I do have to wait uh on a certain um system, uh, I'm gonna try to not bounce back and forth too much.
00:10:03.600 --> 00:10:06.000
So I might give you a little commentary as we go along.
00:10:06.080 --> 00:10:06.960
Oh my gosh, right?
00:10:07.039 --> 00:10:07.440
Terrible.
00:10:07.519 --> 00:10:09.200
Uh so cloud design is great.
00:10:09.360 --> 00:10:12.960
One of the downsides, and you can do things like prototyping, right?
00:10:13.039 --> 00:10:14.399
This obviously isn't just for decks.
00:10:14.639 --> 00:10:18.320
You can build, you know, entire, you know, UI, UX wireframes.
00:10:18.480 --> 00:10:21.440
Uh, it's a really powerful uh tool.
00:10:21.679 --> 00:10:23.679
It is extremely slow.
00:10:23.840 --> 00:10:27.279
And uh like I said, um, it is token hungry.
00:10:27.360 --> 00:10:35.679
So you you know, depending on the complexity, even if you're on a$20 a month pay plan, you might not even be able to uh kind of create the one thing that you want.
00:10:35.840 --> 00:10:36.399
All right.
00:10:36.799 --> 00:10:39.600
So now it kind of went through the tool calling.
00:10:39.679 --> 00:10:43.039
All right, it said it searched the page, it fetched the page, found the information.
00:10:43.200 --> 00:10:44.639
It told me the main stories.
00:10:44.720 --> 00:10:46.159
It looks like I only had six.
00:10:46.240 --> 00:10:46.879
That's interesting.
00:10:46.960 --> 00:10:48.320
I'll have to double check that.
00:10:48.559 --> 00:10:54.080
Uh so uh it said before I designed a few quick questions so the deck looks the way you want it.
00:10:54.159 --> 00:10:57.519
So the thing that I really like about Claw Design is you just click on it.
00:10:57.600 --> 00:10:59.600
So in the right hand side, there's options.
00:10:59.679 --> 00:11:02.480
So it's asking me the overall visual style.
00:11:02.639 --> 00:11:05.039
I'm just gonna pick whatever on these to go through quickly.
00:11:05.120 --> 00:11:12.240
I'm gonna say clean editorial, color direction, dark background with a blue accent, uh, copy tone on the slides.
00:11:12.399 --> 00:11:15.759
I'm gonna say um keep some of Jordan's takes and opinions.
00:11:15.919 --> 00:11:24.000
The good thing is, obviously, which I love this about Claw Design, all of these uh kind of questions it's asking me, they're obviously custom, uh, right?
00:11:24.080 --> 00:11:27.679
It's not some boilerplate questions it always asks you no matter what.
00:11:27.840 --> 00:11:30.799
It does a really good job thinking through and asking you good questions.
00:11:30.960 --> 00:11:34.399
But I the thing I like is you just click, you don't have to type, which is good.
00:11:34.559 --> 00:11:36.559
Uh, it says how to handle the stories.
00:11:36.639 --> 00:11:41.039
Uh so I'm gonna say uh, you know, six story slides and then branding.
00:11:41.200 --> 00:11:41.440
Sure.
00:11:41.519 --> 00:11:47.440
I'll say uh reference the everyday AI uh news that matters as the source.
00:11:47.679 --> 00:11:48.080
Sure.
00:11:48.320 --> 00:11:48.639
Okay.
00:11:48.879 --> 00:11:51.600
Uh and then I'm gonna click continue, and hopefully that's all.
00:11:51.759 --> 00:11:53.440
Uh, I might have to check back.
00:11:53.519 --> 00:11:55.120
I'll probably do that here in a second.
00:11:55.279 --> 00:11:55.519
All right.
00:11:55.600 --> 00:11:58.720
So next, we are going to just claw now.
00:11:58.879 --> 00:11:59.919
All right, so same thing.
00:12:00.000 --> 00:12:02.799
I'm using Opus 4.8 Max.
00:12:02.879 --> 00:12:08.000
Uh, I'm using uh thinking mode, and I don't think I'm gonna have to do any follow-ups here.
00:12:08.080 --> 00:12:12.559
So in this instance, this is just the model going out and doing its job.
00:12:12.720 --> 00:12:16.799
And hopefully it's gonna correctly find this information and create a slide.
00:12:16.960 --> 00:12:20.240
All right, so we'll check back on that one in a couple minutes.
00:12:20.559 --> 00:12:23.200
Next, we are going to Gamma.
00:12:23.360 --> 00:12:28.879
So Gamma is actually one of the, you know, the old kids on the block, so to speak.
00:12:28.960 --> 00:12:34.240
Uh so this uh kind of when gamma came out, it was almost in a league of its own, right?
00:12:34.320 --> 00:12:41.600
This is before Claude and Chad GPT and Gemini and even Microsoft Copilot could generate slides with AI.
00:12:41.679 --> 00:12:43.679
Gamma was one of the originals.
00:12:43.840 --> 00:12:47.440
So in my gamma account, again, I have paid accounts for all of these.
00:12:47.600 --> 00:13:00.080
Maybe this is why the podcast should be making more money because I shouldn't be spending uh a ridiculous amount of money every single uh you know month testing these tools, but I do this so you don't have to, and I can just tell you honestly what's good and what's garbage.
00:13:00.240 --> 00:13:00.480
All right.
00:13:00.559 --> 00:13:04.399
So, anyways, uh when you go into gamma, I'm clicking generate with AI.
00:13:04.559 --> 00:13:06.240
I'm choosing the presentation.
00:13:06.320 --> 00:13:11.600
Uh, it looks like I can't uh I'm gonna have to choose eight cards.
00:13:11.679 --> 00:13:12.799
All right, hopefully that'll work.
00:13:12.879 --> 00:13:15.200
So I do have to tell the cards by default.
00:13:15.360 --> 00:13:18.000
I can click uh classic or studio.
00:13:18.240 --> 00:13:18.559
Okay.
00:13:18.879 --> 00:13:21.600
Uh actually, oh, apparently I'm not on the right plan for studio.
00:13:21.679 --> 00:13:22.159
That's fine.
00:13:22.320 --> 00:13:23.120
Uh so that's it.
00:13:23.200 --> 00:13:25.440
So I'm just I have again my same prompt.
00:13:25.519 --> 00:13:31.759
I'm not gonna read it each time, but please look up the latest AI News That Matters episode from the Everyday AI podcast by Jordan Wilson.
00:13:31.840 --> 00:13:39.039
Please create a slide deck giving each one of the main stories a one-slide recap, one intro slide, and one outro slide go.
00:13:39.279 --> 00:13:44.240
Uh, so on this one, uh, the thing first, gamma is going to generate an outline.
00:13:44.320 --> 00:13:46.000
All right, I'm gonna scroll through it.
00:13:46.080 --> 00:13:50.000
Uh, looks like I can see it, already made some errors.
00:13:50.240 --> 00:13:50.879
Interesting.
00:13:51.039 --> 00:13:51.759
That's fine.
00:13:51.919 --> 00:13:53.919
Um, I'm not gonna correct those.
00:13:54.000 --> 00:13:58.720
Uh, there's options for uh the type of text content, uh, the visuals.
00:13:58.879 --> 00:14:00.080
I'm just gonna choose these.
00:14:00.240 --> 00:14:02.960
There are some, uh, these are pre-selected for me.
00:14:03.039 --> 00:14:06.480
Uh, so I don't have to uh do anything.
00:14:06.799 --> 00:14:09.600
Uh you know, I can just click generate and then we're done.
00:14:09.759 --> 00:14:10.320
Uh all right.
00:14:10.399 --> 00:14:12.639
And then I can also select the different image model.
00:14:12.799 --> 00:14:14.639
So there's an auto-select model.
00:14:14.799 --> 00:14:18.399
You can use uh, you know, flux, you can use GPT image, all these.
00:14:18.559 --> 00:14:22.720
I'm just gonna click the default one and we're gonna click generate.
00:14:22.960 --> 00:14:26.320
All right, and then it is off and running off to the races.
00:14:26.480 --> 00:14:28.159
All right, uh, here we go.
00:14:28.320 --> 00:14:36.320
Uh, next we are using Google Gemini, and finally, finally, we got uh essentially artifact creation in Google Gemini.
00:14:36.559 --> 00:14:39.279
Uh, so there was kind of a way to do this prior.
00:14:39.360 --> 00:14:41.120
Uh, it was almost a little workaround.
00:14:41.200 --> 00:14:51.919
I covered this like a year ago, but really up until a month ago, Google Gemini did not have the ability to create slides.
00:14:52.320 --> 00:14:57.039
It didn't have the uh ability to create uh spreadsheets, right?
00:14:57.120 --> 00:15:03.200
It could create a link to Google Sheets, it could create a link, but you couldn't actually create downloadable assets, but you can now.
00:15:03.360 --> 00:15:05.759
All right, so I am again on my paid account.
00:15:05.840 --> 00:15:14.159
Uh, and in the reason I'm saying paid account because some of these features and functionalities, if you're using a free account, are not gonna work, but if you're on the base uh Gemini paid plan, this will work.
00:15:14.320 --> 00:15:18.559
I'm going to uh the model I'm using is 3.5 thinking.
00:15:19.120 --> 00:15:20.000
Same thing.
00:15:20.159 --> 00:15:21.360
I'm gonna click go.
00:15:21.519 --> 00:15:24.879
I don't think I have to clear anything here.
00:15:25.039 --> 00:15:29.440
All right, I'm just gonna give it a second, uh just to make sure.
00:15:29.600 --> 00:15:32.240
I'm trying to remember because I think actually, Gemini, you might.
00:15:32.399 --> 00:15:36.320
All right, and I'm gonna quickly check in on my other ones, make sure they're cooking.
00:15:36.559 --> 00:15:41.039
All right, we got things cooking in the other ones, not to give it away for our podcast audience.
00:15:41.279 --> 00:15:46.639
Um we're gonna give Gemini is taking a sweet second.
00:15:46.799 --> 00:15:47.679
Nothing's loading.
00:15:47.840 --> 00:15:48.720
There we go.
00:15:50.159 --> 00:15:57.759
Okay, so I thought I might have had to click approve a plan like you have to do with uh Gemini Deep Research.
00:15:57.840 --> 00:15:58.799
It looks like it's going.
00:15:58.879 --> 00:16:01.679
I might have to check back in on it in a second.
00:16:01.919 --> 00:16:02.639
That's okay.
00:16:02.799 --> 00:16:09.200
So we actually have three separate uh three separate options uh from Google.
00:16:09.840 --> 00:16:10.799
Okay, looks okay.
00:16:10.960 --> 00:16:12.720
Apparently it's it's ready already.
00:16:12.799 --> 00:16:15.600
So that was pretty fast by Google Gemini FYI.
00:16:15.679 --> 00:16:19.440
And also, there's actually way more ways we could have done this, right?
00:16:19.600 --> 00:16:24.480
We could have used and maybe would have had even better results using like Gemini Canvas.
00:16:24.720 --> 00:16:28.240
Uh, we could have used the new codex sites, right?
00:16:28.320 --> 00:16:38.399
So, you know, even from a coding perspective, which there's actually really good skills uh out there that can create beautiful slides, you know, with different programming languages.
00:16:38.559 --> 00:16:44.399
But again, I wanted to keep this as simple as possible, uh, just simple input output without having to know a lot.
00:16:44.639 --> 00:16:45.039
All right.
00:16:45.120 --> 00:16:49.600
So next we are going uh to Google Slides.
00:16:49.759 --> 00:16:50.159
All right.
00:16:50.320 --> 00:16:54.240
So on the right hand side, uh you can just click create a presentation.
00:16:54.399 --> 00:16:57.200
Let me see the exact one uh that we would choose here.
00:16:57.360 --> 00:16:58.960
Let's see, file new presentation.
00:16:59.039 --> 00:17:00.559
I want to make sure I do this correctly.
00:17:00.720 --> 00:17:02.480
Uh if it just comes up, okay, here we go.
00:17:02.639 --> 00:17:04.559
So you uh it's gonna give you options.
00:17:04.640 --> 00:17:10.880
Uh so you're gonna want to click slides, uh, and then on the right hand side, uh, you can choose your different model.
00:17:10.960 --> 00:17:12.880
Um we're just gonna go with the default here.
00:17:13.039 --> 00:17:14.559
Same thing, put the prompt in.
00:17:14.720 --> 00:17:19.039
I do think Google Slides is going to ask me a series of questions first.
00:17:19.839 --> 00:17:32.480
So before we uh leave and let uh Google Slides do its thing, uh, it is reasoning over my simple prompt and it's uh creating a plan to go about the best way to do this.
00:17:34.480 --> 00:17:36.720
All right, so we'll give it a second here.
00:17:36.880 --> 00:17:44.640
Like I said, three different uh approaches that we're taking in Google Google Gemini, Google Slides, and we're gonna click Notebook LM as well.
00:17:44.880 --> 00:17:48.799
All right, so I scroll down here, it says podcast recap details.
00:17:48.960 --> 00:17:53.920
Okay, it is asking me some questions, and I like it's easy, uh simple bullet points.
00:17:54.000 --> 00:17:57.279
So it's asking me what is the desired information density?
00:17:57.440 --> 00:17:58.799
I'm just gonna say balanced.
00:17:59.039 --> 00:18:00.960
Who is the target audience?
00:18:01.119 --> 00:18:04.319
Uh I'm gonna say just uh business leaders, right?
00:18:04.400 --> 00:18:05.359
It's you guys.
00:18:05.519 --> 00:18:08.799
Uh, what is the core narrative or goal of this deck?
00:18:08.960 --> 00:18:12.640
Uh, I'm going to say explain industry shifting news.
00:18:12.720 --> 00:18:16.160
Uh, and then how would you like to provide episode content?
00:18:16.319 --> 00:18:19.920
Uh okay, this is interesting because I told it that it should be looking it up.
00:18:20.079 --> 00:18:24.240
Uh, so I'm gonna say other and then I'm just gonna paste the prompt in again.
00:18:24.400 --> 00:18:27.039
Please look up the latest AI news that matters episodes.
00:18:27.119 --> 00:18:30.240
All right, so let's see if that one works.
00:18:30.880 --> 00:18:32.559
All right, we're gonna give it a second.
00:18:32.640 --> 00:18:33.759
I'm gonna keep cooking.
00:18:33.839 --> 00:18:37.920
I'll go back and check on uh Google Slides here in a minute.
00:18:38.079 --> 00:18:40.640
I think that's all we need to do to get it to work.
00:18:40.880 --> 00:18:46.240
All right, next we are going to Google's third entry, Notebook LM.
00:18:46.400 --> 00:18:49.519
So for this, you're gonna create a new notebook and add a source.
00:18:49.680 --> 00:18:55.279
So unfortunately, I can't do the same kind of this is the only one where it's not gonna be able to take the prompt as is.
00:18:55.440 --> 00:19:00.960
Uh so instead, what I had to do on the left hand panel, if you're using book LM, there's essentially three different panels.
00:19:01.119 --> 00:19:08.480
You have your left hand panel that has all your sources, your middle panel where you can kind of chat with your sources, and then your right hand studio panel.
00:19:08.559 --> 00:19:10.240
Uh, right hand studio panel.
00:19:10.319 --> 00:19:15.599
So essentially all I did is I manually added uh that episode on the left hand side.
00:19:15.680 --> 00:19:18.799
So the Monday episode, uh, our AI News That Matters.
00:19:18.880 --> 00:19:21.039
We do the AI News That Matters on Monday.
00:19:21.200 --> 00:19:23.759
And then in this slide deck, I'm gonna hover over.
00:19:23.839 --> 00:19:24.960
There's a little arrow.
00:19:25.039 --> 00:19:30.319
Uh so I'm gonna click that, and then there's a describe the slide deck you would want to create.
00:19:30.480 --> 00:19:37.119
All right, so I'm just gonna take away the first thing there saying please look it up since I already gave it the URL.
00:19:37.279 --> 00:19:46.000
So technically we're giving Notebook LM a little hint, but it's just it just works a little bit different because it's grounded by default.
00:19:46.079 --> 00:19:59.680
All right, so I'm gonna click generate uh from there, make sure it gets started, and Notebook LM is off to the races, and this is going to uh obviously use nano banana to create the slides, which is pretty cool.
00:19:59.839 --> 00:20:02.160
All right, next we have Chat GPT.
00:20:02.240 --> 00:20:04.079
This one should be pretty straightforward.
00:20:04.160 --> 00:20:09.440
Um, I'm not even gonna use the best model, uh, so I'm just gonna go to use thinking heavy.
00:20:09.519 --> 00:20:15.920
So I'm using GPT 5.5 thinking, uh the heavy version, same thing, put the prompt in, clip go.
00:20:16.079 --> 00:20:16.880
I use this a lot.
00:20:16.960 --> 00:20:20.000
So I know ChatGPT is not gonna ask me any follow-up questions.
00:20:20.160 --> 00:20:23.920
All right, next, I am using Microsoft Copilot online.
00:20:24.319 --> 00:20:35.200
All right, so I'm on a Mac, so I don't have the full Microsoft 365 uh, you know, co-pilot version uh that I would like to be able to demo.
00:20:35.279 --> 00:20:38.640
So I'm doing both the online version of Microsoft Copilot.
00:20:38.720 --> 00:20:46.720
I pay$20 a month for Copilot Pro, but remember, this is a personal subscription, so it works so much different than the Enterprise Microsoft 365.
00:20:46.799 --> 00:20:47.839
So keep that in mind.
00:20:48.000 --> 00:20:50.319
But a lot of the underlying technology is the same.
00:20:50.480 --> 00:21:04.160
And then I'm also gonna be demoing PowerPoint, but the desktop version, but with ChatGPT, because as weird as it sounds, the PowerPoint version, even with Copilot on a Mac, the paid one, you can't do this.
00:21:04.720 --> 00:21:07.599
It can't query the web, which is frustrating.
00:21:07.680 --> 00:21:11.200
So I can't do that to us, but we're gonna connect ChatGPT when we get there.
00:21:11.440 --> 00:21:15.680
Anyways, uh now we're doing Microsoft Copilot online.
00:21:16.240 --> 00:21:16.720
All right.
00:21:16.880 --> 00:21:18.960
So, and this is the personal version.
00:21:19.039 --> 00:21:22.240
Um, I'm just using the default model, default settings.
00:21:22.880 --> 00:21:28.400
And I do think it is going to have me click to approve, if I remember.
00:21:28.480 --> 00:21:32.240
Uh, so it's first pulling up all the information.
00:21:32.400 --> 00:21:35.039
Um, let's see, I'm actually gonna count this.
00:21:35.119 --> 00:21:38.000
So one, two, three, four, five, six, seven.
00:21:38.079 --> 00:21:39.119
Yeah, that's what I thought.
00:21:39.359 --> 00:21:40.880
So I forgot which one.
00:21:41.039 --> 00:21:46.079
One of the ones said that there was, oh no, the end says rapid fire AI industry updates.
00:21:46.160 --> 00:21:49.519
Technically, not one of the big stories, but let's count one.
00:21:49.839 --> 00:21:53.920
So the stories, let's just go over these now because we're gonna have to fact check them later, anyways.
00:21:54.079 --> 00:21:58.480
So it was the number one, the Microsoft Copilot Super App League, which was announced.
00:21:58.559 --> 00:21:59.839
Uh, in a video on Nemo Tron.
00:22:00.160 --> 00:22:00.640
Three Ultra.
00:22:00.799 --> 00:22:01.039
Yep.
00:22:01.200 --> 00:22:05.519
The NVIDIA uh AI laptops that were announced at Computex.
00:22:05.680 --> 00:22:06.400
That's number three.
00:22:06.640 --> 00:22:10.960
Number four was the CEO stories, the CEO layoffs blaming AI.
00:22:11.119 --> 00:22:11.759
That's number four.
00:22:11.920 --> 00:22:19.759
Number five was the CE uh uh Dario Amoti and uh Sam Altman talking about uh job risks with AI.
00:22:19.920 --> 00:22:22.240
So that's one, two, three, four, five.
00:22:22.400 --> 00:22:24.319
Number six was the open AI robotics launch.
00:22:24.400 --> 00:22:26.880
Number seven is the Opus 4.8 update.
00:22:26.960 --> 00:22:30.319
So there are seven.
00:22:30.559 --> 00:22:30.960
All right.
00:22:31.039 --> 00:22:32.160
So yeah, there should be seven.
00:22:32.240 --> 00:22:33.200
I think someone got that wrong.
00:22:33.359 --> 00:22:34.720
So there should be seven AI updates.
00:22:34.799 --> 00:22:35.920
So nine slides sold.
00:22:36.160 --> 00:22:40.240
Anyways, I'm gonna click start uh on Microsoft Copilot.
00:22:40.640 --> 00:22:41.200
All right.
00:22:42.240 --> 00:22:46.000
Also, let me know, live stream audience, as we're going along, who do you think's gonna win?
00:22:46.400 --> 00:22:46.880
I want to know.
00:22:46.960 --> 00:22:50.240
I'm gonna take I'm gonna take a sip here and you let me know who's gonna win.
00:22:50.400 --> 00:22:50.960
All right.
00:22:54.079 --> 00:22:56.640
Because I care about is it factual?
00:22:56.960 --> 00:22:59.519
Did it pull everything correctly and taste, right?
00:22:59.599 --> 00:23:04.319
Taste is subjective, but if it doesn't get the nine slides, right?
00:23:04.480 --> 00:23:10.160
If it doesn't properly list the seven stories, then it technically didn't adhere to the prompt, right?
00:23:10.319 --> 00:23:12.720
And something in the tool calling did not work.
00:23:12.880 --> 00:23:15.920
All right, so now we're going over to Canva.
00:23:16.160 --> 00:23:16.720
Same thing.
00:23:16.799 --> 00:23:21.759
We're going into uh templates, we're gonna create uh a new presentation.
00:23:21.839 --> 00:23:26.640
And then there is essentially when you do that, there's a little text prompt box up here.
00:23:26.880 --> 00:23:29.119
A lot of people miss this, all right.
00:23:29.279 --> 00:23:31.359
Um, but you're just gonna type it in, right?
00:23:31.440 --> 00:23:32.640
See now it already went away.
00:23:32.799 --> 00:23:36.079
All right, uh, you're gonna type type in your your prompt here.
00:23:36.160 --> 00:23:37.920
I should probably get the entire thing.
00:23:38.160 --> 00:23:41.279
This interface is a little clunky.
00:23:42.240 --> 00:23:43.920
I don't know why it's not pulling in.
00:23:44.000 --> 00:23:44.880
Okay, there we go.
00:23:45.119 --> 00:23:51.920
All right, so I typed in my prompt, and then there is a little generate button that has little stars.
00:23:52.079 --> 00:23:55.440
All right, so uh it's going through.
00:23:55.680 --> 00:23:59.440
It says finalizing already, even though I just put it in one second ago.
00:23:59.599 --> 00:24:02.319
I don't know if I'm gonna have to go back and check on this one.
00:24:02.720 --> 00:24:03.759
I forgot.
00:24:03.920 --> 00:24:07.920
Uh, but anyways, that's it for all of our web-based versions.
00:24:08.160 --> 00:24:13.200
All right, so now I'm going to have to uh remove that for a second.
00:24:13.519 --> 00:24:17.599
And now I'm going to bring up PowerPoint desktop.
00:24:17.759 --> 00:24:20.000
So now I'm going to be sharing that.
00:24:20.400 --> 00:24:22.880
So stick with me for a second.
00:24:23.119 --> 00:24:33.200
Remember, if you want to actually see the video versions of this, uh make sure to go to our website at your everydayai.com.
00:24:33.519 --> 00:24:35.039
All right, let's go ahead.
00:24:35.200 --> 00:24:39.440
I got to switch over, get this window, boom, there we go.
00:24:39.680 --> 00:24:40.000
Okay.
00:24:40.319 --> 00:24:42.799
So hopefully you all should be able to see this.
00:24:42.960 --> 00:24:44.559
But now we are in PowerPoint.
00:24:44.720 --> 00:24:54.960
And like I said, unfortunately, the co-pilot version of this, because there is a copilot version, uh, it is not going to pull uh the information.
00:24:55.119 --> 00:25:01.359
I'll actually just go ahead and uh do this uh as I check, just so you can see, right?
00:25:01.440 --> 00:25:10.480
As I quickly go through and check uh the other uh models, make sure everything in the browser uh is good and cooking.
00:25:10.720 --> 00:25:11.279
All right.
00:25:11.440 --> 00:25:14.240
Everything is, everything is okay.
00:25:14.400 --> 00:25:15.119
I take it back.
00:25:15.279 --> 00:25:19.279
I did on uh Google Slides FYI, I did have to click approve.
00:25:19.440 --> 00:25:27.519
All right, I'm just going through and checking on everything, making everything making sure everything's going as we give PowerPoint uh here a minute.
00:25:28.880 --> 00:25:31.279
All right, not sure what the heck is happening with Canva.
00:25:33.680 --> 00:25:34.000
Okay.
00:25:35.839 --> 00:25:37.680
All right, let's go, let's see.
00:25:37.839 --> 00:25:46.559
Okay, so you'll see here all it did is it just created the okay.
00:25:46.640 --> 00:25:47.680
So it says one, okay.
00:25:47.759 --> 00:25:48.400
This is so weird.
00:25:48.480 --> 00:25:51.599
Uh so earlier when I did this with Copilot, it didn't work.
00:25:51.759 --> 00:25:57.039
Now it says I can turn this into an actual PowerPoint file with design and visuals.
00:25:57.119 --> 00:26:02.880
This is interesting because last time it did not properly browse the web.
00:26:02.960 --> 00:26:04.000
It said I can't browse the web.
00:26:04.079 --> 00:26:06.400
So this is I I I don't know what's going on here.
00:26:06.559 --> 00:26:12.400
Uh so, anyways, it's asking me if I want to turn it into uh and it says just tell me thumbs up.
00:26:12.559 --> 00:26:13.200
So I don't know.
00:26:13.279 --> 00:26:15.119
I'm gonna say thumbs up, buddy.
00:26:15.599 --> 00:26:19.599
Uh, anyways, let's see if I can start another one.
00:26:21.359 --> 00:26:25.519
All right, I can, but I'm not gonna be able to share my screen.
00:26:25.680 --> 00:26:30.160
So let me unshare this one, all right, and then let me share.
00:26:30.240 --> 00:26:33.759
Yeah, normally I can just share my whole screen, but again, I'm on a laptop, so sorry.
00:26:33.839 --> 00:26:35.599
Uh we're having to bounce around a little bit.
00:26:35.759 --> 00:26:42.240
So now let me go back to my other presentation, which is hard to see.
00:26:44.960 --> 00:26:48.319
All right, so now there we go.
00:26:48.400 --> 00:26:49.440
I got the wrong one.
00:26:49.839 --> 00:26:51.039
Got the wrong one.
00:26:51.920 --> 00:26:55.519
All right, y'all.
00:26:55.599 --> 00:27:00.559
I told you this wouldn't come without its its fair share of hiccups.
00:27:00.640 --> 00:27:04.079
I'm gonna have to resize this window so I can tell the difference between them.
00:27:04.400 --> 00:27:09.839
All right, this is the problem trying to do too many too many things at once on a small screen.
00:27:10.400 --> 00:27:13.599
All right, let's bring up there.
00:27:13.759 --> 00:27:20.160
We go all right, now we have PowerPoint, but with Chat GPT.
00:27:20.240 --> 00:27:23.759
So PowerPoint has a new Chat GPT add-in.
00:27:23.920 --> 00:27:29.119
So you're gonna want to look in your banner bar for add-ins, and then you're gonna search for Chat GPT.
00:27:29.279 --> 00:27:32.400
You are going to authenticate with your ChatGPT credentials.
00:27:32.559 --> 00:27:36.720
The cool thing here is, well, even free accounts for now work with this.
00:27:36.799 --> 00:27:39.759
You don't even need a paid Chat GPT account, which is really cool.
00:27:39.920 --> 00:27:49.680
So you just need to go through uh authenticate with your credentials, and then essentially on the right hand side of PowerPoint, you have a ChatGPT bar.
00:27:49.839 --> 00:27:53.359
All right, so I'm gonna go to should I go to heavy?
00:27:53.440 --> 00:27:54.319
Yeah, let's go heavy.
00:27:54.400 --> 00:27:55.839
We'll give it some time in here.
00:27:56.079 --> 00:27:59.119
Let me get my prompt there, paste it in.
00:27:59.279 --> 00:28:04.000
I'm trying to remember if I have to wait here or approve anything.
00:28:04.079 --> 00:28:05.759
Uh, I'm not sure.
00:28:06.000 --> 00:28:14.480
All right, but what we'll probably do, I'm gonna have to try to multitask here on the world's smallest screen.
00:28:14.640 --> 00:28:22.799
So uh live stream audience, don't laugh at me if you see me squinting like I'm 90 because I'm gonna have to be keeping keeping uh keeping track of a couple different things.
00:28:22.960 --> 00:28:24.000
Okay, I think I should be fine.
00:28:24.160 --> 00:28:33.519
And the cool thing is that I really like about the Chat GPT uh plugin inside uh PowerPoint, it's really good because it doesn't just create visuals.
00:28:33.680 --> 00:28:39.200
Uh I'll I might just do a dedicated episode just on this because I think it's that good.
00:28:39.359 --> 00:28:41.119
We'll see what the output looks like.
00:28:41.200 --> 00:28:44.240
Uh, but let's just go ahead and give it time to cook.
00:28:44.319 --> 00:28:44.799
All right.
00:28:45.039 --> 00:28:50.559
So we're gonna go back now and check in on all of our browser versions.
00:28:50.640 --> 00:28:53.039
And I'm gonna give you guys my opinion.
00:28:53.279 --> 00:28:55.279
Did it follow the prompt?
00:28:55.359 --> 00:28:59.039
Did it properly bring in the information and then the taste, right?
00:28:59.200 --> 00:29:01.680
What does it actually look like?
00:29:02.000 --> 00:29:03.200
Is it good?
00:29:03.680 --> 00:29:06.079
All right, so let me go ahead.
00:29:06.240 --> 00:29:09.599
We're gonna start in the beginning with Claude Design.
00:29:09.839 --> 00:29:26.720
All right, so we have a slide-by-slide view here, and I will say this it is both really, really good and it makes me nauseous.
00:29:26.799 --> 00:29:32.960
And maybe this is because I am terminally online and I pay way too much attention to AI.
00:29:33.119 --> 00:29:42.559
But essentially all of Claude Design's uh designs, all of Claude Design's designs look the exact same by default, right?
00:29:42.880 --> 00:29:48.000
So it's literally the same thing, it's always a uh super bold headline.
00:29:48.160 --> 00:29:52.079
There's always one italicized um uh word.
00:29:52.480 --> 00:29:58.000
That italicized word is always in a light color if it's on a dark background.
00:29:58.160 --> 00:30:01.599
Literally, no matter what you do, I have no clue why.
00:30:01.839 --> 00:30:06.400
The design is the exact same in Claude design by default.
00:30:06.559 --> 00:30:06.960
All right.
00:30:07.039 --> 00:30:12.799
Uh it's gonna give you different color schemes, slightly different fonts, but it always follows the exact same thing.
00:30:13.119 --> 00:30:20.319
So the actual look of this, if you've never seen it before, you're gonna look at it and be like, wow, this is great, right?
00:30:20.400 --> 00:30:28.559
And it is, it is good, but I am absolutely tired of seeing this design because now everyone is just and has been since Claw Design came out.
00:30:28.640 --> 00:30:31.440
They're flooding this thing everywhere, right?
00:30:31.599 --> 00:30:35.279
A lot of people are using this for presentations, and I'm like, poke my eyes out.
00:30:35.359 --> 00:30:43.759
It looks good, but I am like more so than even Delve, uh, you know, in in it's not A, it's B, right?
00:30:43.839 --> 00:30:50.000
When you talk about AI isms, I think right now, uh, you know, and there's always the purple gradients of the early vibe coding.
00:30:50.079 --> 00:30:56.160
The the absolutely worst, eye gougingly bad AI ism right now is the claw design default.
00:30:56.319 --> 00:30:59.839
Anthropic team, please update this because you have a really good product here.
00:31:00.000 --> 00:31:06.240
All right, anyways, now that I got that out of the way, overall, if you've never seen this before, you're gonna look at these visuals and be like, they're amazing.
00:31:06.400 --> 00:31:09.200
All right, the cover says Hot AI Summer is here.
00:31:09.440 --> 00:31:12.400
All right, and then it has a nice little recap.
00:31:12.640 --> 00:31:16.559
It only got six of the seven stories.
00:31:16.880 --> 00:31:18.880
All right, so it missed one.
00:31:19.039 --> 00:31:20.160
Which one did it miss?
00:31:20.319 --> 00:31:32.960
It missed, we have okay, it missed the story of NVIDIA CEO calling out uh NVIDIA CEO Jensen Wong calling out the other CEOs so uh for using AI as a scapegoat.
00:31:33.039 --> 00:31:34.880
So it completely missed one of the stories.
00:31:35.039 --> 00:31:35.680
Not good.
00:31:35.839 --> 00:31:36.400
All right.
00:31:36.640 --> 00:31:39.599
Um visuals though, visuals look great.
00:31:39.759 --> 00:31:44.319
It has in it has fantastic content inside, right?
00:31:44.400 --> 00:31:48.400
So if it's it says, you know, one app, uh let's actually go to a better slide.
00:31:49.440 --> 00:31:50.960
Okay, I like this one.
00:31:51.200 --> 00:31:56.960
Um this is about Nemo Tron 3 Ultra, uh NVIDIA's new open source model.
00:31:57.119 --> 00:31:57.599
Really good.
00:31:57.680 --> 00:32:01.680
It broke out some of the key, uh, some of the key facts and stats, it laid them out.
00:32:01.839 --> 00:32:12.480
Uh so even though the slides, there's not a lot of variety, there's no uh images, obviously, because this is not an image model.
00:32:13.279 --> 00:32:19.759
But in terms of, you know, for it being no images, it's actually really good, right?
00:32:19.920 --> 00:32:21.359
Uh good content.
00:32:21.440 --> 00:32:26.799
Uh I'm looking at it, everything factually checks out, but it missed one of the biggest things.
00:32:26.960 --> 00:32:28.799
It didn't get all the stories.
00:32:28.880 --> 00:32:29.759
So bummer.
00:32:29.839 --> 00:32:31.839
All right, moving on to Claude.
00:32:32.000 --> 00:32:33.200
Oh gosh, Claude.
00:32:33.440 --> 00:32:34.559
Claude, Claude, Claude.
00:32:34.640 --> 00:32:35.920
Why are you so bad at this?
00:32:36.079 --> 00:32:37.759
Uh, interestingly enough, all right.
00:32:37.839 --> 00:32:39.279
I see what happened here.
00:32:39.680 --> 00:32:41.839
Claude made another mistake.
00:32:42.079 --> 00:32:44.720
So, in this instance, I know what it did.
00:32:44.880 --> 00:32:49.039
It used a skill, even though I did not tell it to use a skill.
00:32:49.200 --> 00:32:51.680
And actually, it made a big jump on that skill.
00:32:51.839 --> 00:33:04.799
This is why uh sometimes it's much better to for a model to force you to call a skill because it thought that I wanted to use a design skill that is technically not anywhere close to what I wanted it.
00:33:04.960 --> 00:33:07.519
Uh, so let me just scroll through, see what it did.
00:33:07.920 --> 00:33:09.279
Yeah, okay.
00:33:13.039 --> 00:33:19.599
Yeah, so it thought I wanted to use one of the predetermined design skills, which I did not.
00:33:19.839 --> 00:33:20.400
All right.
00:33:20.720 --> 00:33:24.319
Um so although it followed, right?
00:33:24.400 --> 00:33:39.759
If you watch a lot of our live streams, this uh, you know, I've been uh testing out different um kind of skills uh across different platforms, seeing how closely they can use, you know, Python and all these other things to replicate some of our templates.
00:33:39.839 --> 00:33:44.079
Um and it actually did a pretty decent job at replicating the template, but I didn't want it to.
00:33:44.160 --> 00:33:48.720
All right, so um, anyways, let's see if it got all of the stories correct.
00:33:48.880 --> 00:33:55.839
So we got story one, story two, story three, story four, story five, story six, story seven.
00:33:56.240 --> 00:34:01.759
All right, and then it also did do a little rapid fire of what's new and what's next.
00:34:02.000 --> 00:34:04.960
That one, I'll give it credit, right?
00:34:05.039 --> 00:34:06.799
Because I said all the main stories.
00:34:06.880 --> 00:34:11.039
So essentially I always do these, the big stories, and then at the end I do kind of like a rapid fire.
00:34:11.199 --> 00:34:19.760
So if a model, if if if one of the outputs includes that as one slide, I think I'll let it pass, but missing one of the main stories altogether, not good.
00:34:19.920 --> 00:34:28.800
So overall, uh you know, hit or miss here with the actual Claude output, uh, because it did get all the stories, it added the extra roundup.
00:34:28.880 --> 00:34:33.039
I don't really care about that, but it used a skill when I specifically did not want it.
00:34:33.119 --> 00:34:35.599
And technically, by my language, it should not have.
00:34:35.760 --> 00:34:39.360
This is one of those things with Claude uh Opus 4.8.
00:34:39.519 --> 00:34:41.199
I don't think it's right.
00:34:41.840 --> 00:34:43.440
I don't think it's really good.
00:34:43.760 --> 00:34:47.199
I think if I would have done this in 4.6, we actually would have gotten better results.
00:34:47.360 --> 00:34:50.159
I don't think it would have um used the skill.
00:34:50.639 --> 00:34:52.079
Next, moving on to gamma.
00:34:52.159 --> 00:34:53.760
Wow, what do we got going on here?
00:34:53.920 --> 00:34:57.360
All right, we got a lot of crazy visuals, a lot of neon.
00:34:57.599 --> 00:34:58.159
Uh, right.
00:34:58.239 --> 00:35:02.559
How come every time you ask for anything AI, they always use the same color scheme?
00:35:02.719 --> 00:35:06.880
All right, anyways, uh pretty, pretty good output here from Gamma.
00:35:07.039 --> 00:35:08.400
It does look clean.
00:35:08.639 --> 00:35:09.039
All right.
00:35:09.199 --> 00:35:11.119
It didn't go in order, okay?
00:35:11.280 --> 00:35:16.960
Uh, for whatever reason, it put uh Opus 4.8 as the first story.
00:35:17.119 --> 00:35:19.679
Obviously, in the order of the transcript, it's the last story.
00:35:19.760 --> 00:35:22.559
I didn't tell the model what order to put it in.
00:35:22.719 --> 00:35:23.199
All right.
00:35:23.360 --> 00:35:25.519
Uh, so it put it in its own order.
00:35:25.679 --> 00:35:28.960
All right, so we have the anthropic opus story there.
00:35:29.199 --> 00:35:32.000
The evolution of chat GPT agents.
00:35:32.400 --> 00:35:32.880
Nope.
00:35:33.039 --> 00:35:36.880
That's a I'm gonna guess a hallucination.
00:35:37.360 --> 00:35:37.840
Yep.
00:35:38.000 --> 00:35:40.000
Yeah, we just got a bunch of hallucinations here.
00:35:40.079 --> 00:35:46.719
So it looks like Gamma is not very good at properly uh pulling uh information.
00:35:47.039 --> 00:35:52.000
So yeah, it it has a story about Microsoft Copilot Studio.
00:35:52.159 --> 00:35:57.039
Some of the supporting bullet points are kind of correct, but the main headline is not correct.
00:35:57.199 --> 00:35:59.440
Uh yeah, Google Notebook LM advancements.
00:35:59.519 --> 00:36:07.920
It looks like it's pulling things from multiple uh stories, or it's taking things that were bullet points, not the main stories, um, and making it a main story.
00:36:08.079 --> 00:36:12.000
And that's when I talk about things like prompt adherence, it's super important, right?
00:36:12.079 --> 00:36:15.280
It needs to be able to take my language, which is clear enough, right?
00:36:15.360 --> 00:36:16.559
I said the main story.
00:36:16.639 --> 00:36:24.639
So it should be able to take a look at that transcript uh and understand what the difference is between a main story, and I even say that in the transcript.
00:36:24.800 --> 00:36:26.400
I say our main news stories.
00:36:26.480 --> 00:36:31.119
And then at the end, I usually break it down and say, hey, here's our bullet point roundup.
00:36:31.199 --> 00:36:37.440
Uh so these models, they have to be able to reason, they have to be able to call the right tools, and they have to be able to adhere to my prompts.
00:36:37.679 --> 00:36:44.719
So uh gamma, the design is okay, not my personal taste, uh, but it does create images.
00:36:44.880 --> 00:36:45.119
All right.
00:36:45.199 --> 00:36:51.440
So this is one of the first ones that creates images by itself uh because there are different uh image models baked in.
00:36:51.519 --> 00:36:57.039
So versus just being, you know, overly text like our first two, uh, you know, not bad.
00:36:57.199 --> 00:37:00.400
So I'm going through, yeah.
00:37:01.199 --> 00:37:08.480
Very, you know, super neon vibe, some hallucinations, not really following, uh following uh the prompt.
00:37:08.719 --> 00:37:10.239
So not that great.
00:37:10.559 --> 00:37:11.119
All right.
00:37:11.440 --> 00:37:14.159
Next, we have Google Gemini.
00:37:14.400 --> 00:37:21.119
All right, it rendered it as an inline, which is fine because I can download it and export it to slides either way.
00:37:21.280 --> 00:37:22.320
All right, so let's see.
00:37:22.400 --> 00:37:24.079
We have a title slide here.
00:37:24.239 --> 00:37:27.039
Uh, it does create images as well.
00:37:27.199 --> 00:37:31.119
So it did also put anthropic Opus 4.8 first.
00:37:31.280 --> 00:37:33.199
Again, I didn't tell it what order.
00:37:33.280 --> 00:37:35.840
So as long as it has them all, that's all I care about.
00:37:36.079 --> 00:37:38.960
The next one, Nvidia in Microsoft Partnership.
00:37:39.039 --> 00:37:40.719
Uh, that's correct.
00:37:40.960 --> 00:37:44.159
All right, the next one, the Copilot Super App Leaked.
00:37:44.480 --> 00:37:45.119
That's fine.
00:37:45.280 --> 00:37:49.519
It uses some very random screenshots here, but it's kind of relevant.
00:37:49.599 --> 00:37:54.719
It has two, what look like iPhones, which is funny enough since we're talking about a copilot super app.
00:37:54.880 --> 00:37:55.199
All right.
00:37:55.360 --> 00:37:57.039
Anyways, it's okay.
00:37:57.199 --> 00:37:59.519
Uh the slides look fine, right?
00:37:59.599 --> 00:38:04.800
It's using different infographics, it's using uh little icons, multiple shadings.
00:38:04.960 --> 00:38:05.199
Okay.
00:38:05.360 --> 00:38:09.039
Uh open AI's pivot to robotics, and that's it.
00:38:09.199 --> 00:38:12.239
So it missed two stories.
00:38:12.480 --> 00:38:16.639
Um, so didn't follow everything correctly in terms of what I gave it.
00:38:16.880 --> 00:38:19.119
So not the best from Gemini.
00:38:19.360 --> 00:38:22.159
The design was okay, um, right?
00:38:22.480 --> 00:38:22.960
Simple.
00:38:23.119 --> 00:38:29.119
Uh, it did create some photos in some instances, uh, but again, failed at the basics of prompt adherence.
00:38:30.159 --> 00:38:31.039
All right, next.
00:38:31.199 --> 00:38:34.320
All right, we got another failure from Google, unfortunately.
00:38:34.480 --> 00:38:36.000
The the design on this one looks better.
00:38:36.079 --> 00:38:37.599
So now we're in Google Slides.
00:38:37.760 --> 00:38:40.079
The design, I think, is actually pretty clean.
00:38:40.159 --> 00:38:48.800
It's one of the better designs we've seen so far uh because it does balance uh kind of headings, uh, subheads, uh bullet points, typographies.
00:38:48.960 --> 00:38:51.599
It pulled out some key, uh, some key points here.
00:38:51.679 --> 00:38:58.239
Uh, but it looks like the information is all just made up or generic.
00:38:58.320 --> 00:39:01.039
So I'm wondering if something just didn't run correctly.
00:39:01.280 --> 00:39:01.760
All right.
00:39:02.000 --> 00:39:05.280
So yeah, it does say it's a recap, it's a placeholder.
00:39:05.440 --> 00:39:06.239
That's interesting.
00:39:06.400 --> 00:39:12.880
Okay, so when I went through and approved it, it looks like it did not properly pull the information.
00:39:13.039 --> 00:39:16.239
Uh, but I did click approve that, so I don't know if that was my fault.
00:39:16.400 --> 00:39:24.880
I wasn't looking as closely, but regardless, when I told it to go out and fetch all this information, it just came back and made it generic.
00:39:25.280 --> 00:39:29.119
So I don't know how to score that one.
00:39:29.360 --> 00:39:30.880
Fail-ish, fail-ish.
00:39:31.280 --> 00:39:31.679
All right.
00:39:31.840 --> 00:39:35.519
Uh, anyways, going back into Notebook LM, Notebook LM is next.
00:39:35.599 --> 00:39:38.159
Uh the thing is, this uses nano banana.
00:39:38.239 --> 00:39:40.000
So again, I gave it the URL.
00:39:40.079 --> 00:39:44.000
So I'm gonna go ahead and open this on the right hand side.
00:39:44.800 --> 00:39:53.599
So um the thing with if you've used the deck creation feature inside Notebook LM with nano banana, it is hit or miss, right?
00:39:53.760 --> 00:39:56.400
This one, I say visually, is a miss.
00:39:56.480 --> 00:39:57.039
All right.
00:39:57.119 --> 00:40:00.639
Uh, at least for me personally, not loving the design.
00:40:00.800 --> 00:40:09.440
A lot of times I'll just do five of them, and usually two of them look legit amazing, and two are okay, and then one's hot garbage.
00:40:09.599 --> 00:40:13.440
So in this case, this one is looks hot garbage esque, all right.
00:40:13.519 --> 00:40:14.719
But we have a title slide.
00:40:14.880 --> 00:40:17.199
All right, let's see how we did in the second one.
00:40:17.440 --> 00:40:19.519
This one, I have no clue what this is.
00:40:19.599 --> 00:40:21.679
All right, took a ton of information.
00:40:21.840 --> 00:40:24.480
Uh, I mean, we have stuff about NVIDIA workforce.
00:40:24.559 --> 00:40:27.360
So it's kind of throwing a lot of things all together.
00:40:27.440 --> 00:40:29.599
It's almost like another recap slide.
00:40:29.840 --> 00:40:33.039
Um, here's my Microsoft is collapsing.
00:40:33.119 --> 00:40:36.000
It's scattered AI ecosystem into a singular super app.
00:40:36.159 --> 00:40:36.480
Okay.
00:40:36.719 --> 00:40:39.760
So it looks like maybe we just had two overview slides.
00:40:39.920 --> 00:40:40.800
All right, that's fine.
00:40:40.880 --> 00:40:42.400
Let's see how we do in the rest of them.
00:40:42.559 --> 00:40:45.039
Uh NVIDIA and RTX, pretty good.
00:40:45.280 --> 00:40:45.599
All right.
00:40:45.760 --> 00:40:48.960
I'm looking at the specifics here.
00:40:49.119 --> 00:40:49.920
This is correct.
00:40:50.000 --> 00:40:53.679
All right, it's bringing in the right size of the models, pulling everything from the transcript.
00:40:53.760 --> 00:40:55.280
Uh, did a pretty good job there.
00:40:55.440 --> 00:40:57.679
Uh, next the AI layoff narrative.
00:40:57.840 --> 00:40:58.239
Correct.
00:40:58.320 --> 00:41:01.840
We have there Jensen Wong calling out the uh the CEOs.
00:41:02.000 --> 00:41:06.559
It kind of made a uh some some little uh stat, some little chart.
00:41:06.639 --> 00:41:07.840
So okay, good.
00:41:08.320 --> 00:41:12.480
Uh next, Anthropis, uh Anthropic Opus 4.8.
00:41:12.800 --> 00:41:14.719
Um pretty good, right?
00:41:14.800 --> 00:41:18.960
It has this little diagnostic slider, the enterprise trade-off, the core update.
00:41:19.119 --> 00:41:31.199
Okay, so even though personally not to my taste, uh it actually, even though I was a little confused, it looks like it did kind of a title slide and an overview slide, which I guess is okay as long as we don't miss any of the stories.
00:41:31.920 --> 00:41:35.679
And then last but not least, this is OpenAI's software simulations.
00:41:35.840 --> 00:41:37.440
Oh, I zoomed in.
00:41:37.840 --> 00:41:40.880
Um, are the training ground for physical autonomy.
00:41:40.960 --> 00:41:45.280
Yes, this is the story about uh OpenAI moving to uh robotics.
00:41:45.440 --> 00:41:46.719
Uh, pretty good.
00:41:46.960 --> 00:41:50.400
And then this last one, I'm not sure what this is.
00:41:50.639 --> 00:41:52.719
This looks like a general slide.
00:41:52.880 --> 00:41:55.519
So, overall, fairly strong.
00:41:55.679 --> 00:41:59.039
Notebook LM in terms of prompt adherence didn't do the best.
00:41:59.199 --> 00:42:02.400
It is obviously only grounded in the information that we gave it.
00:42:02.480 --> 00:42:08.880
So I didn't see anything made up, anything super off topic, off topic, but it seemed to generalize some things, so not the greatest.
00:42:09.280 --> 00:42:12.719
All right, next, uh, let's go to Chat GPT.
00:42:12.880 --> 00:42:13.440
All right.
00:42:14.079 --> 00:42:17.440
So, ChatGPT, we have a cover image here.
00:42:17.599 --> 00:42:28.079
It looks like the same uh the same layout throughout, kind of text on the left hand side, and then it generates an image on the right hand side, uh, presumably using GPT image too.
00:42:28.239 --> 00:42:33.039
The cool thing is this also has like speaker notes at the bottom, which is pretty cool.
00:42:33.199 --> 00:42:37.280
Um, so overall, I'm liking this one.
00:42:37.440 --> 00:42:44.719
And so far, this might technically be the best, even though it's not visually the best, because it might hit all our points here as I'm looking.
00:42:44.880 --> 00:42:46.639
So, number one, we have the title slide.
00:42:46.719 --> 00:42:47.840
We have everything in order.
00:42:48.000 --> 00:42:50.480
The first one here is about the Microsoft Super app.
00:42:50.639 --> 00:42:51.519
Nice and clean.
00:42:51.679 --> 00:42:57.840
A great, actually a great visual on the right-hand side, even though it's not to my taste, uh, because I just don't like all the neon stuff.
00:42:57.920 --> 00:42:58.880
It's actually a good visual.
00:42:58.960 --> 00:43:06.239
It it represents, it has all these uh, you know, these little neon lights of all these different types of apps uh going into one.
00:43:06.320 --> 00:43:08.400
So it actually did a good job visualizing it.
00:43:08.559 --> 00:43:09.840
All right, number two, NVIDIA.
00:43:10.079 --> 00:43:15.280
What's actually cool here is it used kind of the NVIDIA green and it you know has something that looks like a supercomputer.
00:43:15.360 --> 00:43:17.360
So the visuals are actually on point here.
00:43:17.519 --> 00:43:18.239
All right, yep.
00:43:18.320 --> 00:43:21.199
The new PC here with the RTX Spark.
00:43:21.360 --> 00:43:22.079
Good job.
00:43:22.239 --> 00:43:24.639
Uh the AI layoffs, really good.
00:43:24.800 --> 00:43:29.679
Has an empty boardroom with a big question mark, uh, you know, a projector screen.
00:43:29.920 --> 00:43:30.480
Oh, okay.
00:43:30.559 --> 00:43:31.679
This uh this is good.
00:43:31.760 --> 00:43:34.800
Um I'm actually this is the first time so far I've been impressed.
00:43:34.960 --> 00:43:37.760
Uh Chat GPT did good.
00:43:37.840 --> 00:43:40.400
Okay, OpenAI's next frontier physical work.
00:43:40.559 --> 00:43:44.719
This might, again, I don't like the whole robot thing, but this one looks good.
00:43:44.800 --> 00:43:50.400
This is a robot in the physical world holding up blueprints, and there's uh a building being erected in the back.
00:43:50.639 --> 00:43:53.039
It's actually real good, even though it's not my taste.
00:43:53.119 --> 00:43:57.840
I think overall, if I showed these to everyone, people are probably voting for this one so far.
00:43:58.000 --> 00:43:59.760
All right, here's the Opus 4.8.
00:44:00.239 --> 00:44:53.360
the honesty take uh and that's it and then we have our uh our closing slide there so I think we got I think we got it all I think we'd had I think we got wait did we miss one hot AI summer we might have missed one I'd have to go back and look unless it created it combined which one did it miss okay it combined that's that's what happened okay because uh I was wondering I'm like I remember seeing all the information so this one kind of failed because it didn't give each one its own dedicated slide so it combined the Jensen Wong uh calling out CEOs with Sam Altman and Dario Mati's uh shift on AI jobs so it overall this one's the best but it didn't so technically none of them have followed directions to the T.
00:44:53.679 --> 00:44:59.360
And all of them have had so far had some degree of failure but overall I do think ChatGPT is in the lead for now.
00:44:59.519 --> 00:45:05.039
All right next going to Microsoft Copilot and I'm actually surprised this looks pretty good.
00:45:05.119 --> 00:45:19.679
This one is actually there's some visuals here uh which is cool the thing I love about Microsoft Copilot is by default you can actually edit it in line which is really cool you don't have to download the PowerPoint version open PowerPoint and go edit it.
00:45:19.920 --> 00:45:22.880
So this one pretty slick pretty good so far.
00:45:23.039 --> 00:45:27.440
All right so first we have the Microsoft super app good next we have NVIDIA NemoTron.
00:45:27.519 --> 00:46:14.239
So no visuals no photos in here but overall uh branding looks pretty good um correct information that's good then we have the uh the NVIDIA and Microsoft partnership then we have uh what's this the big picture all right this just looks like a recap slide maybe okay then we have the model race okay so this is about Claude Opus 4.8 we have open AI's robotics good uh another one on Claude Opus 4.8 so interestingly enough it looks like it combined opus 4.8 it did make a slide just I did talk about other models on Monday and it made a slide comparing opus 4.8 to those other models even though that was not technically its own story.
00:46:14.559 --> 00:49:54.719
But we do have the dedicated Opus 4.8 uh we have the uh the Dario Omati and Sam Altman shift it pulled out a quote all right interestingly enough and then a lightning round it did round up everything so again not a hundred percent prompt adherence um but we did cover every single story at least the visuals inside Microsoft Copilot actually really good even though there's no photos to it that's okay you know some interactive pieces and I love the fact that you can edit inside the app so at least for me so far uh you know maybe a a maybe microsoft copilots ahead you know chat gpt is right there claw design is is is there as well so uh all right let's go to canva canva no looks look looks bad uh it got like three things i i knew canva wasn't gonna do well um but i know people would be like you should try canva all right it gave us uh four slides of information it gave me yeah it hallucinated it all it said story one openai's gpt 4.0 launch right that's not it so it just hallucinated a bunch of information nothing useful all right now let's go look at our two PowerPoint uh options and wrap it up all right as I thought yeah the actual PowerPoint version did not work all right it said it was going to it didn't all right but let's look at the chat GPT PowerPoint version I know this has been a long one y'all but hopefully it's helpful hopefully me spending you know 49 minutes on this is gonna you know keep you from spending 30 hours trying to figure out what's best and what's not all right let's go ahead and get our chat gpt version right yeah there we go okay so now we have this is PowerPoint but the chat GPT uh add-in okay so pretty good all right so similarly to how Copilot works obviously because this is in PowerPoint I can start editing immediately uh which is nice the good thing is which I'm not gonna get into this is the only one well notebook LM you have some of these uh capabilities but uh you can edit it iteratively as well which is really nice not all of them do that and there's different modes in this uh chat GPT um uh PowerPoint integration so uh uh cover slide good it also gave uh a nice little table of contents my thing here these slides are clean these slides are very clean okay probably in terms of proper um spacing alignment so far it's actually claw design is really good uh so I'd say claw design and the chat GPT PowerPoint versions in terms of design spacing typography uh overall taste probably the best Microsoft Copilot next after that so we have Microsoft Super App first uh NVIDIA's NemoTron again using some of their colors uh the NVIDIA and uh Microsoft partnership really good uh the AI uh layoff narrative uh with Jensen wrong yeah yeah it's doing good it's it's always creating you know multiple pull out boxes so uh it could have used because you can use skills inside of chat GPT so I'm pretty sure I could have used uh the image two skill but I didn't call it right and I didn't call it anywhere else but I do I I I do know that chat GPT inside of PowerPoint could have done those things.
00:49:54.880 --> 00:50:00.000
All right then we have geez just overall I just the design of this one is just so clean.
00:50:00.239 --> 00:51:03.280
All right uh so we have the open uh the Frontier Labs this is the anthropic uh 4.8 story it looks like then we have the open AI robotics story uh oh no that one was just a transition slide so it added an extra one that's fine uh it added a feature comparison so it made more than we asked for and then it kind of rounded up everything with the rapid fire recap at the end and then kind of a uh an actionable call to action so uh it did add some extra slides uh but I think it did cover everything so that's a wrap y'all this one was long there's no winner tell me if you're watching the video version which one do you think so obviously with some iteration you could probably find a winner for you I will say that there's certain ones that do really well and just from doing this all the time I obviously give you a very simple prompt uh right and we were testing multiple things and obviously all of these versions would have been better with some back and forth with me investing time but that wasn't the point.
00:51:03.519 --> 00:51:28.079
I will say both from my personal experience of using all of these many times uh and from you know just my take on these uh I do think claw design really good uh if especially once you start to iterate on it downside by default it's always gonna spit out the the the most templated thing ever uh even though that template looks good if no one's seen it before but it is great when you iterate but it's token hungry.
00:51:28.239 --> 00:51:33.280
So you know you're not gonna be able to use it a lot unless you're on a$100 or$200 max plan.
00:51:33.360 --> 00:51:42.719
So I I I will say the tier one options are uh number one uh actually let me go back and look at the chat GPT version real quick.
00:51:42.880 --> 00:51:45.119
I kind of forgot what that one looked like.
00:51:45.440 --> 00:51:47.840
That was actually okay that one was pretty good.
00:51:48.000 --> 00:51:50.639
I forgot about that one because there's photos in there as well.
00:51:50.800 --> 00:52:26.880
Okay so I'm gonna say that the the top tier here is is Claw Design uh the two versions of chat GPT and then the Microsoft Copilot so out of the 10 uh that we tested I will say those are the first tier so maybe that's where you start and iterate with those uh although I will say this if you do work with one of these systems one of these systems with enough work will usually be able to give you great outputs right you have to edit them a little differently you have to go through the process some accept skills some don't right some accept connectors and apps which is great.
00:52:27.039 --> 00:52:35.519
Some you can run automations right I could have turned this into an eight hour course but luckily I'm gonna shut up enough in time to make it at least less than an hour.
00:52:35.599 --> 00:52:37.039
All right I hope this one was helpful.
00:52:37.199 --> 00:52:56.079
Do you want more of these right yeah they're a little dirtier they're a little longer more hiccups more blabbing but I like to like the problem with AI y'all and in other people that try to cover this stuff is sometimes it's overly polished and I'm like that's not how it works right you're gonna get errors things take longer like this podcast things take longer.
00:52:56.239 --> 00:53:06.239
So if you like these longer in-depth looks but starting with a skill and taking that skill across different uh you know AI systems, let me know.
00:53:06.400 --> 00:53:17.840
But let me know by a comment if you're listening on Spotify if you like this if you hate it let me know uh but please if you haven't already go to your everydayai.com sign up for the free daily newsletter we're going to recap the too long didn't watch version.
00:53:17.920 --> 00:53:19.199
So thank you for tuning in.
00:53:19.280 --> 00:53:22.239
We'll see you back tomorrow and every day for more everyday AI.
00:53:22.400 --> 00:53:23.440
Thanks y'all