Which LLM Should You Use For Your Business? (Pros & Cons of Each)

Let's like sort of rapid fire, like, best tool for that use case. Right. For research. The AI tool that I use the most, more than any other AI tool.

Hey, welcome to the Next Wave podcast. I'm Matt Wolf. I'm here with Nathan Land. And today we're going to talk a little bit about the various large language models that are out there. I feel like one of the things that we hear a lot is like, okay, you've got Claude, you've got ChatGpt, you've got Llama, you've got Perplexity, you've got Grok, you've, you know, the list goes on and on. But the reality is some of these tools are really good at some things. Some of them are really bad at things. And so we wanted to spend a little bit of time on this episode, just kind of deep diving in, like, what's this good for? What's this good for? If I was doing copywriting, what would I use? If I'm using research, what would I use?

Being a know it all used to be considered a bad thing, but in business, it's everything. Because right now, most businesses only use 20% of their data. Unless you have HubSpot, where data that's buried in emails, call logs and meeting notes become insights that help you grow your business. Because when you know more, you grow more. Visit HubSpot.com to learn more.

So just something I think should be a really valuable resource for people. Just, hey, I need to do this. Let me go double check with that episode of the Next Wave on how I actually should do that. Like, what tools should I be using to go do that? So that's what this episode's all about. We don't have a guest today. It's just me and Nathan chatting from our own experience about these tools. Just getting into it here. One of the biggest news in the AI world right now is from ChatGPT, from OpenAI, right? They just released their new OpenAI 01 model. Maybe do you want to kind of break down a little bit?

I mean, I mean, some of it, we don't fully know how it's working yet. There's a lot of, like, debate about what's actually going on with the new Zero1 model. But the way that they're describing it is this is a new paradigm in the past, you know, the large language models, they're really great at, you know, they're trained on tons of data. You know, they can make great stuff from that, but they can't really reason about what they're seeing, right? And so they're saying this is now a basic reasoning that they kind of attached on top of those large language models. It's not like, from what I can tell so far, like, it's not, you know, there's not great use cases for like regular people. Yeah, it's a little bit better at editing and encoding and a few things. But the big deal probably is that now you can. It's. It's almost like in the past the large language models were like had like half a brain, right? Like almost like the creative side or something like this. And now you have like the logic side is there now too. It's like, right, you put those two together. Like it's amazing with the reasoning side, it's all at inference time. Like there's a whole nother side of things that they can improve now where like, yeah, you can just throw more GPUs at this. And so like, yeah, all the talk about, like, oh, you know, we've hit a limit and it's not going to get better anytime soon. Like, no, this is, there's no end in sight now. Like, this is going to continue to get way better. And the people at OpenAI, they're saying like, yeah, it's almost like this is like the GPT 2 or 3 moment where they've built this amazing new. They've had a breakthrough, but consumers can't really realize that yet. There's not like if you just use it in ChatGPT, you're not gonna have like, oh my God, this is amazing. It's like, oh, it's like slightly better at some things, but there's more going on beside, you know, behind the hood.

It's using what they call chain of thought reasoning, right? Where basically there was a technique that people used when they were, you know, quote unquote, prompt engineering called chain of thought reasoning, where you would ask it a question and then within that same prompt you would say, think this through, think it through step by step, you know, and that was how people would do this chain of thought reasoning. To me, what this is, is they've just sort of baked that in. So now you don't have to ask for that chain of thought reasoning. You don't have to tell me, think this through step by step. I guess what I'm still uncertain about is like, how is this new model super different from just doing that sort of prompting technique?

I mean, the rumors I've heard from like friends in Silicon Valley who know people there is like, it's based on that idea. But there's more to it than that.

I mean, I get that question. Yeah.

And so I don't know, we could, you know, we could guess what that is, but like, we have no idea, like. Yeah, yeah.

And when you use this new open AI model too, it, it actually will show like a little sort of dialogue thing that says like, thinking or whatever. Right. And it's got a drop down arrow and if you open up that drop down arrow, it will actually show you sort of what is thinking. But from what I understand, it's actually not really showing you what thinking. It's almost like version. Yeah. It's almost as if it's what it's thinking is a much longer prompt and then it's using its own sort of like AI model to give you a summarized version of what it's thinking.

Yeah, well, people were saying, oh, it's amazing. You can actually finally see what they're thinking. Yeah. And now we don't have to worry about like AI taking over the world. We can, we can see what it's thinking in real time. And then OpenAI was like, oh, yeah, you know, we're not actually like necessarily showing that to consumers. Like, we have the capability to do that now though, apparently they are saying that they have the ability to do that, I believe.

Yeah.

But they're not making all of that, you know, known to like, regular people.

Yeah.

So, yeah, I think we're getting some kind of like edited down version of what they decided to show people. Right, right. Still pretty cool to see that, you.

Know, And a lot of the rumors are right. We've been hearing about this Strawberry. Right. Sam Altman trolled everybody by putting a image up on his Twitter saying, oh.

I love it as well too. The guy, I don't know who it was. A real person or. Yeah, if it was.

So there's been a lot of talk around Strawberry and then this came out. So a lot of people are like, hey, Strawberry is finally out.

Right? Yeah.

But we're here at Inbound and we were. We've been talking to a lot of people who are deep into A as well, and somebody's like, yeah, it's not even Strawberry, it's something else. It's called. It's actually the Orion model, which is different than Strawberry Q, star, whatever you want to call it, you know.

Yeah, it's hard to know. Like, like, Also, is this GPT5 or is that something else too? Yeah, because maybe, yeah, the, the, the large language model itself is going to keep getting better and better. Maybe they're still working on that and maybe There is another GPT5 coming. Yeah, this reasoning thing is another thing because now they, they didn't improve upon so.

Well, the way they announced it on their blog as well was like, we're resetting the counter. I don't remember the exact wording.

Right.

But they're like, we're resetting this. So we're starting with 01. Right.

Still keeping it super confusing with like preview and mini and all these.

Yeah, yeah, that's the other thing. Right. So like the version of 01 that we're seeing right now is the preview version, all of the benchmark tests. Like if you look at their blog, you'll see that it outperformed in like PhD Reasoning and Math and science and all of these like STEM related topics. Right. But everything that it's showing that really, really outperformed is the OpenAI 01 model, the full model. Yeah, we're just seeing the preview model, which if you look at those same benchmarks, they're better than what we were getting, but they're not like insanely better. They're not like, you know, the PhD level that they're showing on these charts.

Right. Yeah. I mean, it's kind of gets us closer to AGI though too. Right. Because like OpenAI had put out their like tier list of like getting to AGI. I think number two was reasoning and number three was agents. Right. And so now they're saying they have reasoning. They're saying it's not great, but is the basic foundation how you would build reasoning into an AI system? They've nailed that now.

Yeah, yeah.

And then apparently like David Sacks on the all in podcast, he was saying something other day where apparently the word is that the OpenAI investors have been told by Sam Altman that they've nailed agents, that it's working like the new 01. Like that they haven't shown people publicly yet, but in private it's working and agents are actually going off and doing work. It's like work that companies would love to have the agents just doing for them. It's actually working. And so, you know, agents in the past, like, you know, we had Yohei Nakajima who did Baby AGI and all this on, and great concept, but like a lot of this stuff just didn't work. Like it would go off and try to do stuff for you and it would like get confused and like. And that's kind of it.

Yeah, yeah.

And you could possibly even wrap a huge bill for you too, because it just keeps trying. And so if they've actually nailed that, I mean, it's going to be a huge step forward when that comes out.

So just for anybody who's listening that maybe hasn't listened to like previous episodes, when we talk about agents, an agent is essentially like it'll do multiple steps. Right. You can give it a task and it will go and potentially use tools and do multiple steps for you to get to the result that you wanted. So like examples people might give of like an AI agent might be something where I go and ask it to book my flight for me. Right. And it goes and checks your calendar, sees what times you have available and then it goes to the airline website and sees if there's any flights that are available within that window that you want and then it books it for you and then sends you a slack message to let you know that it booked you. Right, yeah. So an agent is like all of like a multi step process, possibly using.

Different APIs to get things done. One example took me like, if you're doing in marketing, like doing a marketing report, you could say, go off and get me this data and like, you know, create a PDF and like do a report. Like that's something that used to take a lot of time. Yeah. Like in theory, agents should be able to easily do that kind of stuff.

Yeah, yeah. Well, so, so Sam Altman said, I don't remember if he did it in a tweet or if it was on the blog post, but he basically said for most cases you still want to use GPT4. Yeah, he said for most of the cases you still want to go use GPT4. You want to use OpenAI01 if you really need it to think through logic or do a math problem or solve really complex like things that require more logic.

Right, right.

So that's why we wanted to do this episode is to kind of talk through what are some of the large language models, pros and cons. Like what models should I be using if I need this task done? Which models should I be using for this task over here. Right. And so we wanted to start by talking about ChatGPT and this new OpenAI 01, because you probably don't need 01 for most things, like maybe go and ask it some complex questions just to see what it's capable of and look at the way it's reasoning. But for 99% of use cases, GPT4 is probably going to be better for most of your use cases. But obviously ChatGPT isn't the only game in town. Right, right. We've got Chat GPT, we've got Claude, we've got Llama, we've got Gemini, we've got grok, we've got all of these tools. So let's talk a little bit about Claude. For me, this is what I think CLAUDE is the best at. I think Claude is really, really good at, like, storytelling, and I think it's amazing. This is what I use it for more than anything else is summarization taking a fairly long document. Now, it does have, like, some context token limits where some documents tend to be too big. It seems to be based on file size on claude, though. Like, on Claude, it'll. I don't know the exact file size, but if you go over like 20 megabytes or something, it'll say it's too big. So if you have a long PDF, you can actually take that PDF, run it through a compression tool, shrink the file size down, and then CLAUDE will read it. So I've actually downloaded some like, PDFs from archive.org before, tried to throw it into Claude and it would say, oh, this file's too large. And it would be like 20 megabytes.

Yeah.

So I went on Google and I said PDF compression tool, right? And I found a free PDF compressor and it would compress that, you know, 25 megabyte PDF down into a one megabyte PDF without changing any of the text in the PDF. And then I was able to pull it into Claude. So if you actually run into that issue with like a PDF on Claude, just go and compress it down into a smaller file size and it'll typically work. But CLAUDE is amazing at summarizing documents, like taking an archive.org document and just shrinking it down.

Yeah, definitely. Claude's a great at writing, like, it's definitely the best LLM at writing right now, for sure. At summarization, if I had to guess, 01 is probably better now.

You think so?

If I had to guess. But like, you know, I just. We just flew out to Boston from, you know, me from Japan. I haven't had much time to actually, like, play with it. But, you know, from people I trust on Twitter and things like that who've been trying it out, that's what I've been hearing is like, in terms of editing, anything that's complex. So I assume, like, summarization would probably fit into that as well.

Do you know what the context window is of OpenAI1? Does it have a limited context window?

I actually don't know.

Yeah, I'm not sure either.

We should know that, Producer.

Yeah, so the other thing that I really. So both Claude and Chat GPT have these features where you can kind of create your own little, like, almost like mini apps inside of them. Right. I don't know the better way to describe it, but you have custom GPTs over on ChatGPT, and then you've got projects over inside of Claude.

Right.

And what this allows you to do is create like, custom instructions for a specific use case that you might use over and over again, but also feed it some documents where you want it to use those documents for context every time you use it. Both ChatGPT and Claude can do that. But like, we were talking about this off air, Claude just has a better user interface. It just feels a lot more intimate.

Yeah, I mean, it's, you know, so OpenAI actually came up with it first. As far as we know, they did it, you know, they. They came up with custom instructions, which was great because, like, okay, now you can actually give the, you know, chatbot, like, context. But it was like, okay. It's like very generic though, because you can't tell, like, oh, because sometimes I'm working on my newsletter, sometimes I'm doing Twitter or sometimes personal stuff, whatever.

Yeah.

Like, you, you know, you couldn't give it to that. You know, you had to give it all the context for all the stuff.

Yeah.

And then with a. Then they came out with the custom GPTs, and then you could do, okay, I have one for, you know, getting in shape. I have one for my newsletter, you know, all this kind of stuff. So. But the user interface was always really awkward. And then there's like. And then there's gonna be like a public store and there's gonna be revenue share.

So confusing.

I didn't know they were actually doing the revenue share. Like on that one episode we did with Siki, we found out, like, oh, they actually are paying people.

Like, they do share revenue. I'm not allowed to tell you about it.

Like, he also told me, you know, behind the scenes, that he's also been pretty good for Legion actually, as well. Like, people are just. Because there's a link to his website.

Right.

So that's, that's cool. But like, for like a regular person, Claude came out the projects and I think it's just. Is so much better. Just like a whole interface where it's like, okay, here's the. Here's the project and I can put files in it, I can put notes in it, whatever, to teach it to Give it all the context it needs to accomplish something.

Yeah.

Versus having to, you know, like when ChatGPT first came out, if you wanted to do that, I'd like be copying and pasting stuff into it. There's all this stuff you need to know and here, let me copy and paste that in.

Yeah, yeah. So like one example, just to sort of make it more tangible for people. And I've shared this example on past episodes, so if you're hearing this again. Well, I'm just solidifying the idea for you. But one of the ways that I use it lately is for YouTube shorts and script writing for YouTube shorts. And what I've done is I've created a custom project inside of Claude where I went and found about 15 different transcripts of shorts that I found on YouTube that I thought were really, really good shorts. They hooked me in. I watched the whole time. This, this short worked for me. It's got, you know, half a million, a million views. It's working for other people. This is a good short. Right. I went and took the transcripts from those shorts and I loaded those 15 transcripts into a project inside of Claude. And then for the custom instructions for that prompt, I would say in your knowledge base, I've given you a bunch of transcripts of YouTube shorts that are really, really effective. I'm going to give you a topic. When I give you a topic, write a short for me. Write a script for a short for me that is very similar in style and flow to the information that I gave you. So now I can go and, for instance, grab a blog post about something that happened in the news. Right. I can grab a blog post. One that I just published was about OpenAI01. I went and took the article that explains OpenAI's01 from their blog, pasted it into this custom project that I made, gave no other prompt. I just literally copied and pasted the article in. It knows what it needs to do because of the custom instructions and it wrote me a 59 second script that sounds like a lot of the scripts that I uploaded. It hits all the right beats, all the right points.

Yeah.

And so that's sort of a tangible example of like what projects can be used for in your own workflow.

That saves you so much time too, right?

Yeah.

You know, before, I think it was good that we came out here to inbound, like, you know, especially for me to get out of Japan for a little bit and actually talk to people in English. I was surprised how many people, like, just don't Know, like, about projects or custom GPTs and how much time that can save you. They're still in the land of, like, they just go to chatbot every time and they're starting fresh with, like, it having no context.

Yeah.

Every single time. And then they're kind of confused by why it can't do more. And it's like, yeah, if you provide it more context, it can do a whole lot more than you're currently thinking.

Yes.

Even with the current abilities of it. So. And so I think it's good that people, like, learn that and like, yeah, Claude's the best for custom projects, but you can still do it with ChatGPT. Most people use Chat BT. Yeah, you can do it. Custom GPT.

Yeah.

You don't make that public either. You keep it private and it's just for you.

Yeah, same. Same with the cloud projects. You can actually, I believe you can share them. I don't. It's not public. Like, they don't have a marketplace.

Yeah.

But you can share a link and let other people use your, like a team thing.

I believe, I believe you can even share it. Like an entire team.

Yeah, I believe so. The other really cool thing about Claude is their artifacts.

Yeah.

So if you are going to use it for code, it will actually show you the code in the same window and actually let you run the code if it's something that'll run in a browser. So if it's like a JavaScript or a Python code or something that can actually be executed in the browser, it will actually let you run it side by side with your chat. So you have your chat window on the left side and on the right side you've actually got your code and there's usually a little, like, toggle switch to actually view the code. And if the website populates on the right side and you can see, oh, that link is broken, or this needs to be centered, you go to the left side of the chat box and say, hey, center the headline, center the call to action button, or whatever. And I always thought that was really cool to not have to, like, open it in a new tab, see what it looks like, jump back. It's just all right there on the single window.

Yeah, they're really nailing it, like on the user interface. Right. Because, like, why does open AI not have that? Right. Like, they should have that.

Yeah.

Like, they were there first and they just missed it. And the same thing. We're like, you know, I'm hearing that O1 or 01 Preview is the best at coding. And like, well, if they had the thing where you could see the artifacts and actually see it live, that would show it to so many more people. There's like a lot of great engineers on Twitter talking about, you know, who've been like, really skeptical of AI and they've now tried 01 Preview and they're like, okay, it's not amazing yet, but like everyone is overhyping things before, like it would give you code that sometimes works, sometimes didn't. Yeah, this is like a decent, not a great engineer, but it's like a decent junior level engineer now.

Yeah.

And that's a huge step forward and especially now that, you know, OpenAI is saying it's going to get better and better faster and faster now.

Yeah, yeah. Okay, well, and then, and then we've also got Google. Right. So Google has Gemini.

Yeah.

And one of the beautiful parts about Gentleman I is it's got this monstrous context window. I can't remember it's a million or if it's up to 10 million. I know at one point keep increasing it.

So it's like some point.

It's like, I know at one point they said it's going to be 10 million, but when they launched it, it was a million. I don't know where it's at now. It might be at 1, 2 million and they might have already bumped it to 10 million.

I think it's.

I don't remember.

With like RAM with computers or something. Like it's okay, you have one gig, two gig, four or whatever.

And just to put that into context. Right. So. So a 10 million context window means that you can upload about 7.5 million words between. Between what you give it and what you get back. The combination of the two can be about 7.5 million words. That's like all of the Harry Potter books, all of the Game of Thrones books, the Bible, all of that combined all into a single, like. Yeah, you can put all of that in there all at once.

Right.

And so when it comes to what is Google Gemini good at? It's the largest in terms of context window and how much data you can upload into it. But one thing that Google did recently with Gemini that I think is really, really cool is the. The Notebook lm. That's the one where you can actually upload all of these documents and it will create an audio podcast for you out of these documents. Have you seen that yet?

I haven't, no.

Oh my gosh. Oh, you're in for a treat. We play with this. So Notebook lm, you can go to it, I believe. I don't know if you have to be a paid member of Gemini or not, but you can go into this Notebook LM and you can drop files into a folder. So you can go to archive.org, download the most complex research paper you've ever seen, that you have no idea what it means, right? Pull that PDF, throw it into this Notebook LM tool. And Notebook LM will actually generate an audio podcast for you that explains the PDF. And it's two hosts. There's a male and a female host. They're AI generated voices and they have a conversation back and forth. Kind of like the conversation we're having now, right? They have a conversation back and forth that explains the PDF in terms that like, anybody can understand. And because they have such a large context window, you can throw a ton of documents in here, right? You can, you can go and find like we can go and throw the blog post about Chat GPT in there, a blog post explaining Claude in there, a blog post explaining Grok, a blog post explaining Gemini. Throw all of that data in there and they will, it'll create a podcast out of that information that explains the pros and the cons and the differences between the two.

Yeah, it seems like Google's doing a lot of cool stuff. It's just like people don't know about it and even me, like, I know about some of it, but it's like, it's hard to get the habit. Like I have the habit of using ChatGPT and even, you know, I use Claude a bit now. It's so hard. Like there's so many of them.

Yeah, yeah, yeah. So, I mean, like, I have a feeling we're going to start hearing a lot, a lot of AI generated podcasts because of it. Because you, anybody can go and take the latest, like, TED news articles in the AI world, throw them all into Notebook LM and then have it spit out a podcast for you explaining what's going on in all of these news articles.

Oh, no, our buddy is already doing the TED AI podcast over there.

And then if you want to take it to a next level too, you can create some like custom characters inside of like Mid Journey or, or, you know, Flux or Leonardo or whatever AI image tool you use. Create some images of some characters, throw those into like a hey Gen or a Di talking and doing, and then have them actually talking. So you have, you can make video content of two people having a podcast conversation based on all of the data that you uploaded and that's all totally possible right now, like today with current.

At the next level, like vtuber or something too. Like there's.

Yeah, except the vtuber doesn't even exist. It's all generated with AI. It's really wild. Notebook LM is one of the things I've had a lot of fun playing with. I think once you actually go mess with it, you'll be like, oh, damn, this is cool.

Okay, so that's what Gemini is good at. Huge context and making podcasts now.

Yeah. Replacing us.

Yeah.

Disclaimer. This is actually not us talking.

This is.

Yeah, surprise. This is Notebook LM all along, you know. And also Gemini does have their own version of custom GPTs and projects. They call them gems, but they're not nearly as robust. You can't do as much with them. They don't seem to connect to like APIs or use tools or anything like that. But you can give it your own context and your own custom instructions, similar to you can with projects and, and with custom GPTs. I haven't played with gems at all yet because I have my needs met with Claude and ChatGPT already, but they have that as well, if that's something you're interested in. And then we also wanted to talk quickly about Llama. So Llama is open source, right? And Llama is. It doesn't really excel in any of the areas we've talked about. Right. Like Claude. Sonnet 3.5 is going to be better than the outputs for Llama for the most part. Same with the latest models of ChatGPT, same with Gemini. All of those closed off models, they're going to be a little bit better. But if you really, really want like your data to be secure, you want to run it on your own hard drive, you don't want it to be connected to the Internet, you don't want your data going to open AI, you don't want your data going to Google or Anthropic or any of these companies. That's where tools like Llama come into play. Because you can install them locally on your own computer and they're pretty good. I mean, for 90 plus percent of use cases for people, they're going to be good enough, you know, and so that's really where Llama comes into play. The other thing about Llama is because it's open source, people can build off of it, they can iterate off of it, they can go and make their own sort of fine tunes of it and, you know, tweak it and train it and sort of Mold it. So if you wanted an uncensored llama, you can get there if you wanted to.

You actually ever use it, though? Have you just only tried it? Because I've only tried it. I haven't never built a habit of actually using it.

So I use a Llama a little bit, but it's only because I have my meta Ray Ban sunglasses and llamas built into it. So I use Llama, like, built into the sunglasses.

I'm glad it exists, though. Like, like I've said before, like, I hate the idea of it everything being OpenAI. And now they're, like, collaborating with the US Government as well. Like in the future, like the idea that, like, all of our intelligence isn't controlled by one company. Right, right. Kind of scary. So I'm glad it exists.

Yeah. And then. And then, you know, finally we've got Grok. Right. And Grok again. I don't know if it's, like, really better than any of the other ones at almost anything.

Well, it has access to Twitter data, so that's. That's one thing.

Yeah. So it's got the Twitter data and it's completely uncensored. Like, completely, like.

Well, like 99.99. Yeah.

I mean, I've asked it questions that I thought for sure there's no way it was going to answer.

Yeah.

And it answered it for me. Like broke down recipes. It should not be giving me things like that.

Okay. And now you're like, on the FBI watch list.

Exactly. But it is very, very uncensored. It's got a really cool image generation model built into it called Flux 1, which is capable of making really, really realistic images.

Yeah.

And also pretty uncensored. Not going to say fully uncensored because it's not going to do any like, like super adult content. Right. But it's uncensored in the terms that you can prompt anybody's names, like celebrities.

And like crazy political memes, whatever. Right. That's. That's one of the things people are using it for a lot.

Yeah. Which, by the way, is illegal in California as of this week. Did you, did you see that?

Yeah.

Yeah. So Gavin Newsom in California just signed a bill basically making California making, like, political means that were generated with AI illegal in California. But we don't need to get. We don't. We don't need to get into.

That's going to go to the Supreme Court. But anyways.

Yeah. Yeah, that's going to be interesting to watch play out. I mean, Elon Musk moved to Austin now So he's not really under California rules, but as soon as that law came out, Elon went and posted some sort of crazy meme and said, oh, this, this would suck if this ended up being seen in California or something.

Right, right.

So you know Elon, he's in troll. Yeah, yeah.

I mean, so, so grok is, it's, it's gotten better though. Like the fact that like they started for like nothing, like what was like a year ago or it wasn't that long. And I was like, people are like, oh, there's no way he's going to catch up. It's like, well, he hasn't caught up, but like it's pretty decent now. Like, you know, I'm not going to use it over chatbots, obviously, but it's decent.

So what, what sort of. You're talking about this before you hit record. But what sort of like use cases would you use it for? Like in terms of it like hunting Twitter profiles for you?

Yeah, I've used it a little bit like this. I think it was Robert Scobo, it was someone like that who share how they were using it, that you can like pull up data about users. Right. Like you can pull up like, like what kind of tweets do they do? What are their top tweets? Just anything. You know, I'm not using it a lot for that, you know, use case. I don't really have a huge need for that. Yeah, but it works for that. Like it's, it's the best for that right now.

Yeah.

I mean also you can pull up things about news to the. Right. Because it's got access to what people are tweeting about. Information about something that's currently hot and happening right now is probably the best for that.

Yeah, but there is also some downsides to that. Well, right, Like. Well, yeah, if people are posting memes as if it's real news, it might think it's real news and feed it back to you.

Right.

So there's that as well. And then the very last one I want to touch on really quickly because I think when it comes to research, Right. When you want to like deep dive and learn on a topic or you know, find information about something specific, it actually needs to search the web. I still think Perplexity, hands down is the best.

Yeah.

Now Perplexity is model agnostic. If you have a pro membership for Perplexity, you can get in there and choose. I want to use GPT4. They actually just added OpenAI01 in there as well as One of the models you can use, you can pick Claude, you can pick Llama, you can pick any of these models, and it will use whatever your model of choice is. But what it'll do is it'll search the Internet, find information for you, and then once it finds the information, it uses its large language model to help sort of summarize and make the information that it gathered for you a little bit easier to digest.

Yeah, I mean, Perplexity. I mean. I mean, there was a reason that, you know, we got Ervin Zurin, the CEO, to come on. He was, like, one of our first two guests, I guess.

Yeah, yeah, yeah.

And that was the reason that I wanted to get him on, because, like, you know, I've been using Perplexity for, like, since the early days of it. It's like, it's been one of the, you know, one of the most useful things. And, like, early on, most people didn't know about it, and people in Silicon Valley were talking about it, but, like, outside of that, it was like, oh, everything was chatgpt. I'm like, people are kind of sleeping on Perplexity. It's, like, pretty damn good.

Yeah, yeah, yeah, yeah. No, I love Perplexity. I mean, honestly, when it comes to using AI, just. Yeah, the AI tool that I use the most, more than any other AI tool right now, for me, it's Perplexity.

Yeah.

I go to Perplexity more than any other AI tools because I just get random ideas. Like, I'll be. I'll be walking, and I'll see, like, a tall building, and I'll think it's, like, a fascinating architecture, and I'll just be like, who built this building and why does it look so cool? Or, you know, something really random. Like, I. I just ask so many random questions of Perplexity. It, like, feeds my curiosity.

It's amazing for podcasts, too, right? Like, so we, you know, here at Inbound, there was an event yesterday where, like, a bunch of podcast hosts were there, and I talked to a few of them, and they didn't know about this. They didn't know that. Like. Oh, yeah. When you have. When you're interviewing somebody, Perplexity is by far the best way to, like, pull up notes about what you should talk to them about.

Yeah, you just have to be careful, because sometimes it will pull up, like, LinkedIn profiles of, like, the complete wrong person. Like, if you start asking questions about Matt Wolf, it will. There's a professional golfer named Matt Wolf also.

They're talking about golf, and you're like.

Yeah, well, it'll give you a mix. Right. Like I've had it summarized and it'll say, you know Matt Wolf, co host, the Next Wave podcast, he's got a popular YouTube channel. He's, you know, his handicap at golf is this, like. And it'll start to like blend the two. So you probably want check sometimes, but for the most part it's pretty good. Right? It's pretty dang good. But you know, to go ahead and wrap this one up, I want to kind of. Let's like sort of rapid fire, like use cases. Best tool for that use case. Right. So like copywriting and storytelling. For me, I'm probably going to Claude.

Yeah. Claude.

Yeah. For coding for me, I'm probably still going to Claude, but maybe OpenAI01. I haven't tried it for coding yet myself.

Yeah. I mean, I think I code more than you. Right. So like, I'm more, you know, for you. I think with you can use Claude, you can actually just see it right there. Right. Which is obviously awesome.

Yeah.

But you know, as someone who codes like for me, like, oh, one, you know, preview, @ least I've heard from people I trust. If it's better, then. Yeah, I would definitely be going with.

O1.

Yeah. Yeah. I'd be using in something like Cursor. Cursor for.

Sure. Cursor is great. It's a fork of Visual Studio code with like AI built into.

It. Yeah. Where you can like read your whole code base and have. It basically has context of your entire code base when you're working on.

Something. Yeah, yeah.

Yeah.

Amazing. Yeah. I mean, since OpenAI01 came out, I've literally been traveling the entire month, so I have not had like a. A focus session to play with it. So my answer might change on that one. You want something completely uncensored. Anything goes. I think Grok is the obvious answer for that one.

Right?

Yeah. Also really, really realistic images.

Yeah. Great memes. Yeah, good for.

Memes. Great for making memes. Great. Like the images it'll generate like really realistic pictures of. Of people that either exist or don't exist. Right. It's really good at that. With Flux one built into.

It.

Yeah. So math, science, logic, that kind of stuff. We're looking at OpenAI01. That's really the only one that's going to do that really well right.

Now. Right.

Right. For research for me, perplexity, like I said, that's the one I.

Got. They were the same on most of these major.

Disagreements. And then if you need super, super long context. You need to upload all the Harry Potter books and all the Lord of the Rings books and all the Game of Thrones books, and you need to find a good comparison between all of them. You're going to go to.

Gemini. Yeah.

Yeah. And then also Gemini is really.

Good. Or to create this.

Podcast. Yeah, we're for creating a podcast and replacing our.

Jobs.

Yes. Yeah. So that's kind of the breakdown, I guess, of like, what these different models are good at and what we use them for. I think that about. I think that's covers everything. So, you know, if you're. You're listening to this podcast and you like stuff like this, make sure you subscribe to us on YouTube. We're going to keep on putting out videos like this. We're going to get a lot more tactical. We're going to give you a lot more use cases, a lot more ways to actually implement this AI in your business. So subscribe on YouTube if you. If you prefer audio, where, wherever you find podcasts. So make sure you subscribe on all of those platforms. And thank you so much for tuning in with us.

Today. Yeah, thank you.