WEBVTT 1 00:00:00.181 --> 00:00:02.570 If you've been on the internet, you've seen Dan Coe. 2 00:00:02.811 --> 00:00:05.120 He's got millions of followers and I've seen 3 00:00:05.281 --> 00:00:06.224 him everywhere. 4 00:00:06.585 --> 00:00:09.075 So I reached out to him and I was like, how do you do it? 5 00:00:09.476 --> 00:00:10.500 And he told me that his 6 00:00:10.600 --> 00:00:14.249 secret is LLMs, AI, and prompts. 7 00:00:14.790 --> 00:00:18.700 So in this episode, he shows his exact playbook for coming 8 00:00:18.780 --> 00:00:25.080 up with ideas, creating the content, and most importantly, content that is going to go viral. 9 00:00:25.260 --> 00:00:33.540 Now, why I find this interesting is right now there's an unfair advantage to create X accounts, to create YouTube channels that get distribution. 10 00:00:33.960 --> 00:00:39.080 If you can figure out distribution, you create a bunch of startups for those audiences. 11 00:00:39.680 --> 00:00:46.040 So if you stick around to this end of this episode, you will understand how to create content like Dan Co. 12 00:00:46.762 --> 00:00:49.840 And, you know, people generally charge thousands of dollars for this. 13 00:00:50.490 --> 00:00:50.940 It's free. 14 00:00:51.361 --> 00:00:54.600 All I ask is for a like and a comment on this episode. 15 00:00:54.821 --> 00:00:56.793 I can't wait to see what you build. 16 00:00:57.015 --> 00:00:57.880 Have a creative day. 17 00:01:06.221 --> 00:01:07.124 What's up, Dan? 18 00:01:07.586 --> 00:01:08.429 Great to have you. 19 00:01:08.870 --> 00:01:11.640 By the end of this episode, what are people going to take 20 00:01:11.901 --> 00:01:12.262 out of it? 21 00:01:13.406 --> 00:01:14.129 Glad to be here, dude. 22 00:01:14.349 --> 00:01:15.674 Thank you for having me on. 23 00:01:15.694 --> 00:01:17.340 I have a few things to share, 24 00:01:17.760 --> 00:01:23.519 but the outcome as a whole will be a big picture overview of my content ecosystem. 25 00:01:23.559 --> 00:01:23.680 So 26 00:01:24.161 --> 00:01:32.040 before we just started, you're mentioning like, you're curious about how my output is so high, 27 00:01:32.521 --> 00:01:35.913 when I personally don't think it's that high, it doesn't take too much. 28 00:01:36.013 --> 00:01:37.900 So I think it just comes 29 00:01:37.980 --> 00:01:43.900 down to having a really smart system, and then being able to augment that with AI in a unique 30 00:01:44.362 --> 00:01:45.527 way, which we're going to learn. 31 00:01:45.607 --> 00:01:48.740 But the other thing that we have to learn in order to do that 32 00:01:48.820 --> 00:01:54.815 well is just how to use LLMs in a way to get them to do exactly what you want. 33 00:01:55.116 --> 00:01:56.860 So I'm not a coder. 34 00:01:57.060 --> 00:02:01.937 I don't use too many of the fancy tools, mostly just cloud chat GPT. 35 00:02:01.977 --> 00:02:02.860 So how are we going to use 36 00:02:03.382 --> 00:02:09.320 the base tools that most people have access to and understand to create something incredible? 37 00:02:10.140 --> 00:02:10.501 I love it. 38 00:02:10.541 --> 00:02:12.829 I only have one ask from you. 39 00:02:13.210 --> 00:02:16.260 You know, I just ask that you don't hold back any sauce. 40 00:02:16.561 --> 00:02:19.531 you give the prompts, you show how it's really done. 41 00:02:20.032 --> 00:02:22.039 Because what would be success for me is if 42 00:02:23.423 --> 00:02:30.580 thousands of people consume this episode and understand how to use LLMs to be like you. 43 00:02:30.640 --> 00:02:32.992 Because when I see Dan Coe, I see millions of followers. 44 00:02:33.012 --> 00:02:33.977 I see you everywhere. 45 00:02:33.997 --> 00:02:34.540 I see content 46 00:02:34.640 --> 00:02:34.841 here. 47 00:02:34.882 --> 00:02:35.585 I see content there. 48 00:02:35.605 --> 00:02:37.091 And I'm like, how does this guy do it? 49 00:02:37.734 --> 00:02:38.940 Dan, can you commit to it? 50 00:02:39.862 --> 00:02:40.373 Absolutely. 51 00:02:40.577 --> 00:02:40.720 Yep. 52 00:02:42.265 --> 00:02:43.218 All right, let's get into it. 53 00:02:44.541 --> 00:02:45.643 Cool. 54 00:02:45.763 --> 00:02:52.832 So the first thing there, just to touch on millions of followers, having so much content, so many different platforms. 55 00:02:54.274 --> 00:02:59.220 The thing about that is all of my content is the same across all different platforms. 56 00:02:59.540 --> 00:03:03.245 So the base of it all comes down to two things. 57 00:03:03.285 --> 00:03:09.612 It comes down to my newsletter, which I write every week, sometimes twice a week, but once a week is like baseline. 58 00:03:10.173 --> 00:03:13.937 And then two is two to three social media posts a day. 59 00:03:14.758 --> 00:03:16.060 And those are usually written. 60 00:03:16.501 --> 00:03:20.795 And so I write Twitter first because it's like the 280 character limit. 61 00:03:22.980 --> 00:03:27.400 And then since that's like the limiting factor out of all the platforms, that can pretty 62 00:03:27.561 --> 00:03:30.360 easily transfer over to any other platform. 63 00:03:30.500 --> 00:03:33.220 So that gets posted to threads by Instagram. 64 00:03:33.941 --> 00:03:38.940 I turn that into an image and post that onto LinkedIn, onto Instagram. 65 00:03:39.280 --> 00:03:41.580 Sometimes I use them as a real script. 66 00:03:41.960 --> 00:03:48.926 So I pull up my camera, look at my phone, read my best tweet, recite it to the camera, maybe add a bit on there. 67 00:03:49.847 --> 00:03:53.890 And then I have reels, TikToks, shorts, etc. 68 00:03:54.070 --> 00:04:05.520 And the good thing about that is since the ideas themselves are almost always validated ideas or have the potential to do very well. 69 00:04:06.121 --> 00:04:17.960 If I can nail the first idea that goes out on Twitter, then I'm practically nailing all the other content that goes out on all other platforms because I'm not much of a trend follower. 70 00:04:18.340 --> 00:04:24.160 Sometimes I am, but most of the time I believe that the algorithms are based off of human psychology. 71 00:04:24.561 --> 00:04:35.000 And if you understand human psychology and can use AI to help you understand that more, your content will see a notable increase in engagement and other things of that nature. 72 00:04:35.461 --> 00:04:44.800 So first, I'll just give an overview in this Canvas style so you understand my weekly process. 73 00:04:45.080 --> 00:04:57.540 So every week I plan out my newsletter and the idea for the newsletter, it's based on a few different things. 74 00:04:57.660 --> 00:05:03.600 It could be a top performing tweet of mine that I have before because I know that that tweet has already done well. 75 00:05:04.020 --> 00:05:09.500 So I'm just going to take on it, take it, expand it into a newsletter that turns into a YouTube video podcast. 76 00:05:09.784 --> 00:05:10.239 Good to go. 77 00:05:11.821 --> 00:05:17.300 Or it can be based on a video that is already doing well on YouTube. 78 00:05:17.800 --> 00:05:37.800 So a good way to generate ideas that help you grow is to go to YouTube, look at the accounts in your niche or the people that kind of like tribe you want to join online, go to their account, go to videos filter by most popular, and then just write down 10 of the videos that you think you could recreate. 79 00:05:38.180 --> 00:05:41.843 Now, the secret there is you're not watching the videos. 80 00:05:41.863 --> 00:05:44.425 You're not trying to steal anything from the video itself. 81 00:05:44.746 --> 00:05:49.289 You're trying to take the topic, the angle and write your own perspective on it. 82 00:05:49.550 --> 00:06:02.380 Because if other people are watching those videos, since they have a lot of views, then they're going to just by the nature of YouTube and people binge watching things, they're going to be recommended your video. 83 00:06:02.641 --> 00:06:03.606 they're going to watch that. 84 00:06:03.646 --> 00:06:06.320 And if they hear you say the same things as the other person, 85 00:06:07.002 --> 00:06:09.048 then you're not going to stand out or be unique. 86 00:06:09.429 --> 00:06:12.398 So that's what this process is. 87 00:06:12.458 --> 00:06:13.120 So that's usually 88 00:06:13.220 --> 00:06:15.848 the two ways that I come up with newsletter ideas. 89 00:06:16.450 --> 00:06:19.540 And I keep a document where I tend to, 90 00:06:20.342 --> 00:06:22.711 I just have a list of ideas that I can pull from. 91 00:06:22.992 --> 00:06:25.120 I pick the one that I think is going to do the 92 00:06:25.160 --> 00:06:25.762 best that week. 93 00:06:26.083 --> 00:06:31.240 Now, what I do for that is I of course have a place where I write the newsletter 94 00:06:31.501 --> 00:06:32.784 just in a note or document. 95 00:06:33.425 --> 00:06:39.460 But I tend to find a few things that I've either talked about before 96 00:06:40.102 --> 00:06:40.804 relating to that. 97 00:06:40.905 --> 00:06:44.937 So previous newsletters, previous tweets, whatever they may be. 98 00:06:45.319 --> 00:06:45.579 And then 99 00:06:46.482 --> 00:06:53.640 Sam Altman, the co-founder of OpenAI, just said that it is the era of the idea guy and he is not 100 00:06:53.740 --> 00:06:54.022 wrong. 101 00:06:54.644 --> 00:06:57.998 I think that right now is an incredible time to be building a startup. 102 00:06:58.118 --> 00:06:58.600 And if you listen 103 00:06:58.680 --> 00:07:00.788 to this podcast, chances are you think so too. 104 00:07:01.370 --> 00:07:04.320 Now, I think that you can look at trends to 105 00:07:04.380 --> 00:07:08.355 basically figure out what are the startup ideas you should be building. 106 00:07:08.515 --> 00:07:09.760 So that's exactly why 107 00:07:10.081 --> 00:07:11.626 I built ideabrowser.com. 108 00:07:11.867 --> 00:07:16.060 Every single day, you're going to get a free startup idea in your inbox, 109 00:07:16.220 --> 00:07:21.312 and it's all backed by high quality data trends. 110 00:07:21.593 --> 00:07:23.137 How we do it, people always ask. 111 00:07:23.458 --> 00:07:24.500 We use AI agents 112 00:07:24.540 --> 00:07:26.739 to go and search what are people looking for 113 00:07:27.386 --> 00:07:28.779 and what are they screaming for 114 00:07:29.042 --> 00:07:30.740 in terms of products that you should be building. 115 00:07:31.321 --> 00:07:34.440 And then we hand it on a silver platter 116 00:07:34.541 --> 00:07:35.780 for you to go check out. 117 00:07:36.824 --> 00:07:38.179 We do have a few paid plans 118 00:07:38.704 --> 00:07:40.560 that take it to the next level, 119 00:07:41.304 --> 00:07:42.220 give you more ideas, 120 00:07:42.500 --> 00:07:43.617 give you more AI agents 121 00:07:43.881 --> 00:07:46.539 and more almost like a chat GBT for ideas with it. 122 00:07:46.942 --> 00:07:49.538 But you can start for free, ideabrowser.com. 123 00:07:49.900 --> 00:07:50.679 And if you're listening to this, 124 00:07:50.900 --> 00:07:52.199 I highly recommend it. 125 00:07:53.202 --> 00:08:00.080 A lot of the times I like to weave in other concepts from specific books or videos. 126 00:08:00.560 --> 00:08:09.300 So this is where AI really comes into play because I'm talking about survival and how to reinvent yourself in this newsletter. 127 00:08:10.122 --> 00:08:16.000 And when I say survival, I'm talking about psychological survival, something that I find really unique and interesting. 128 00:08:16.903 --> 00:08:19.800 And I've previously watched three videos on that. 129 00:08:20.221 --> 00:08:25.120 They're each by a channel called actualize.org and they're like three hours long. 130 00:08:25.460 --> 00:08:31.440 So it's a lot of learning when I'm on walks and other things of that nature that allows 131 00:08:31.521 --> 00:08:33.700 me to write in-depth newsletters. 132 00:08:34.180 --> 00:08:37.780 But I'm usually not taking notes during this time. 133 00:08:38.320 --> 00:08:43.320 And this is where LLMs can come into play because they can usually pull from YouTube 134 00:08:43.500 --> 00:08:49.160 videos or PDFs, allowing you to talk to them and pull up the relevant points that you want 135 00:08:49.200 --> 00:08:50.966 to talk about in a newsletter. 136 00:08:51.026 --> 00:08:54.960 So the research process there is thinking about the newsletter 137 00:08:54.980 --> 00:09:03.000 and the topic I want to write, talking with AI a bit and just getting specific key points and 138 00:09:03.301 --> 00:09:10.520 summaries and other unique perspectives, and maybe throwing in a few things about the topic that I'm 139 00:09:10.600 --> 00:09:19.920 talking about, just so I have a chat that I can refer to that turns six hours of videos into 140 00:09:20.542 --> 00:09:21.785 a thousand words, right? 141 00:09:21.805 --> 00:09:24.272 So then I can write about it myself. 142 00:09:25.635 --> 00:09:27.340 Now, the other thing here is if I bake 143 00:09:27.601 --> 00:09:32.337 in something I've written previously, so this is on reinventing yourself. 144 00:09:32.357 --> 00:09:33.220 That's kind of my thoughts 145 00:09:33.300 --> 00:09:33.701 on that. 146 00:09:34.403 --> 00:09:37.050 So you can think of this newsletter as like combining these two. 147 00:09:37.491 --> 00:09:40.720 So when I take the 148 00:09:40.760 --> 00:09:45.660 summary, paste it into another chat or link it to another chat, then I can say, okay, what are the 149 00:09:45.700 --> 00:09:46.544 similarities here? 150 00:09:46.645 --> 00:09:47.791 Is there anything that I'm missing? 151 00:09:47.891 --> 00:09:49.419 I'm kind of just in this process of 152 00:09:49.781 --> 00:09:56.740 ideation with the LLM until I feel like I have enough firepower to start piecing together an 153 00:09:56.900 --> 00:09:58.885 outline and then to start writing it. 154 00:09:59.266 --> 00:10:04.680 Now, I don't have the LLM right for me, like the actual 155 00:10:04.780 --> 00:10:05.242 newsletter. 156 00:10:06.485 --> 00:10:11.199 But with what we're going to talk about, you could technically do that. 157 00:10:11.259 --> 00:10:11.540 And if we 158 00:10:11.600 --> 00:10:15.391 have time, I'll actually show you how to do that specifically. 159 00:10:16.113 --> 00:10:18.560 But that's the research process. 160 00:10:18.900 --> 00:10:19.703 Nothing special here. 161 00:10:19.903 --> 00:10:25.460 Just getting information from the getting the ideas so that I can put 162 00:10:25.540 --> 00:10:26.445 them into the newsletter. 163 00:10:26.566 --> 00:10:29.140 Otherwise you just get stuck staring at a blank screen. 164 00:10:29.761 --> 00:10:30.923 So I have a question on this. 165 00:10:31.685 --> 00:10:39.500 So what your thesis is basically you use X Twitter as a litmus test 166 00:10:39.580 --> 00:10:40.282 on ideas. 167 00:10:41.184 --> 00:10:41.445 Yes. 168 00:10:41.505 --> 00:10:47.540 And then once you have an idea that gets validated, then you're like, okay, 169 00:10:47.660 --> 00:10:51.366 this might have legs to extend this to other mediums. 170 00:10:52.288 --> 00:10:56.575 Then you look to YouTube as a encyclopedia 171 00:11:00.061 --> 00:11:00.883 of knowledge. 172 00:11:01.464 --> 00:11:11.000 You find popular videos or videos that just are high quality that, you know, might 173 00:11:11.060 --> 00:11:13.991 be, you know, might be, it might be hours long. 174 00:11:14.292 --> 00:11:16.480 And then you use, it looks like you use Gemini 175 00:11:16.701 --> 00:11:19.029 in the first example to summarize it. 176 00:11:19.391 --> 00:11:21.860 You can use, you know, really anything you want, right? 177 00:11:23.120 --> 00:11:23.521 Yeah. 178 00:11:23.602 --> 00:11:28.700 I tend to go with Gemini 2.5, especially when there's, oh, this one's only nine minutes, 179 00:11:28.800 --> 00:11:34.040 but for like the three to six hour videos, I'll use Gemini just because the large context window. 180 00:11:34.520 --> 00:11:34.761 Right. 181 00:11:34.961 --> 00:11:37.142 So you get smart about the videos. 182 00:11:38.083 --> 00:11:42.846 And then from that, you extend it, right? 183 00:11:42.866 --> 00:11:46.489 And you're not using the LMs to, at this point, write it. 184 00:11:46.549 --> 00:11:59.939 But I guess my question is, because someone listening to this is going to be like, okay, but you never talked about the hardest part, which is your great ideas on Twitter. 185 00:12:00.900 --> 00:12:01.400 You know what I mean? 186 00:12:02.344 --> 00:12:02.456 Yeah. 187 00:12:02.621 --> 00:12:04.099 So how do you think about that? 188 00:12:05.304 --> 00:12:06.680 So it's kind of circular, right? 189 00:12:06.780 --> 00:12:09.440 The ideas for Twitter can come from two different places. 190 00:12:09.641 --> 00:12:12.840 It can come from the newsletter itself. 191 00:12:13.582 --> 00:12:15.434 So I'll show over here in a second. 192 00:12:17.162 --> 00:12:19.120 But it can come from the newsletter itself. 193 00:12:19.561 --> 00:12:21.520 And that's a good way to generate ideas. 194 00:12:21.641 --> 00:12:24.997 But the mistake that people make there is they'll have a really good newsletter and 195 00:12:25.580 --> 00:12:30.320 they'll think, OK, I'm supposed I'm supposed to pull ideas from this and they'll read a 196 00:12:30.380 --> 00:12:36.200 certain sentence or paragraph and just try to copy paste that directly and post it on Twitter with 197 00:12:36.420 --> 00:12:45.700 maybe a few changes when in reality, what you're looking for is just the idea that you can turn 198 00:12:45.800 --> 00:12:47.143 into a high performing tweet. 199 00:12:47.624 --> 00:12:54.800 So it's kind of the same thing there where the first step is learning 200 00:12:54.941 --> 00:12:56.627 how to write high performing tweets. 201 00:12:56.828 --> 00:12:58.354 And there's courses on there. 202 00:12:58.676 --> 00:12:59.579 There's courses on this. 203 00:12:59.599 --> 00:12:59.760 There's 204 00:12:59.800 --> 00:13:00.704 YouTube videos on this. 205 00:13:01.125 --> 00:13:04.740 The best thing I can recommend is actually what I'm going to show you, 206 00:13:05.360 --> 00:13:10.576 but you need to kind of immerse yourself in good writing and ideas. 207 00:13:10.736 --> 00:13:11.880 I think the best thing you can 208 00:13:11.940 --> 00:13:18.980 do to write better social content in general is to just keep a swipe file of really good ideas 209 00:13:19.321 --> 00:13:21.990 that you'd like to emulate under your own brand. 210 00:13:22.110 --> 00:13:25.060 I think of brand as the ideas that you associate 211 00:13:25.200 --> 00:13:25.802 yourself with. 212 00:13:26.364 --> 00:13:31.400 And so you're not necessarily copying other people's ideas or taking other 213 00:13:31.460 --> 00:13:32.142 people's ideas. 214 00:13:32.804 --> 00:13:38.700 You're synthesizing a bunch of different ideas that are technically what compose 215 00:13:38.760 --> 00:13:39.944 your mind and your worldview. 216 00:13:40.405 --> 00:13:45.460 And you're bringing them together in a very articulate way under your 217 00:13:45.560 --> 00:13:46.142 own brand. 218 00:13:46.282 --> 00:13:52.220 And then as people consume those over time, you gain that authority in their head. 219 00:13:52.942 --> 00:13:59.060 so uh that's one way to come up with ideas is just keep a swipe file you have to become like 220 00:13:59.220 --> 00:14:04.800 a ruthless note taker and just consistently save ideas until it's until you've read so many of them 221 00:14:04.920 --> 00:14:09.720 and written so many of them that it's become second nature to you on how to just structure 222 00:14:09.840 --> 00:14:16.220 an idea like you can give me a word and then if you give me a minute to think about it i could 223 00:14:16.300 --> 00:14:21.920 probably come up with a really good post about that thing and do you use any tools for that 224 00:14:23.963 --> 00:14:36.200 um i use if we go to twitter so i've used both tweet hunter x and super x it feels like 225 00:14:37.042 --> 00:14:42.740 a lot of people or no company has really mastered this yet just the twitter sidebar in general 226 00:14:43.382 --> 00:14:48.640 where when you go to a certain person's profile this is the super x extension and it just shows 227 00:14:48.700 --> 00:14:49.845 their top performing tweets. 228 00:14:50.266 --> 00:14:53.880 So if you write down five to 10 accounts that you really like, 229 00:14:54.500 --> 00:15:03.060 and you kind of want to, I think you refine your writing style by reading the writing you aspire 230 00:15:03.261 --> 00:15:03.823 to have. 231 00:15:04.565 --> 00:15:09.040 And so if you have the accounts that talk like you want to talk, and you consistently visit 232 00:15:09.381 --> 00:15:15.420 their highest performing tweets with super X or tweet hunter X, and save all of these down and try 233 00:15:15.781 --> 00:15:21.015 to exchange either the structure or the idea and practice posting. 234 00:15:21.336 --> 00:15:22.318 What I mean by that is right 235 00:15:22.980 --> 00:15:27.240 here, there's a clear structure, go on more walks, walk for no reason, walk to solve a problem, 236 00:15:27.400 --> 00:15:28.222 et cetera, et cetera. 237 00:15:29.085 --> 00:15:34.139 You can take this structure, replace or bring another idea into it. 238 00:15:34.259 --> 00:15:34.600 So rather 239 00:15:34.700 --> 00:15:41.497 than walks, it could be code, code more code every day, something of that nature. 240 00:15:41.958 --> 00:15:42.580 And then the more 241 00:15:42.640 --> 00:15:48.700 you, or that's exchanging the, taking the structure and exchanging the idea from it. 242 00:15:49.061 --> 00:15:55.440 But you can also take an idea, like go on more walks and exchange the structure of it. 243 00:15:55.781 --> 00:15:59.120 So then you look at another structure where this is just a single sentence. 244 00:16:00.401 --> 00:16:05.760 Uh, I don't know, platitude of sorts, this one at least. 245 00:16:06.601 --> 00:16:12.040 And you can just take the idea of walks, try to write it as a single sentence. 246 00:16:12.562 --> 00:16:14.088 now you have two tweets from one idea. 247 00:16:14.850 --> 00:16:17.480 Um, and the more you do that and practice it, 248 00:16:17.500 --> 00:16:20.471 then really any idea has the potential to do very well. 249 00:16:20.512 --> 00:16:21.997 Cause you can just pop it into a 250 00:16:22.720 --> 00:16:28.960 preexisting structure, or you can take a structure and plug in one of the ideas that you're trying to 251 00:16:29.040 --> 00:16:30.063 include in your brand. 252 00:16:31.067 --> 00:16:35.080 So, uh, one thing there that I'll talk on, and then we'll get into 253 00:16:35.882 --> 00:16:38.106 actually doing all of that. 254 00:16:40.471 --> 00:16:45.100 After I write the newsletter, I have three prompts that I like to 255 00:16:45.160 --> 00:16:45.662 run it through. 256 00:16:46.023 --> 00:16:49.474 So this first one is just a YouTube title generator. 257 00:16:50.377 --> 00:16:51.320 And I'll show you how 258 00:16:51.360 --> 00:16:52.283 this one's structured. 259 00:16:52.504 --> 00:16:57.880 And if you do this, Greg, I can put all of these in a Google Doc so people 260 00:16:57.980 --> 00:17:02.975 can copy paste them and read through them and dissect how they're structured. 261 00:17:03.557 --> 00:17:04.460 But for this 262 00:17:04.560 --> 00:17:09.148 prompt specifically, I, uh, wrote a prompt. 263 00:17:09.729 --> 00:17:16.299 I took my best, like 15 titles on YouTube and I, 264 00:17:18.662 --> 00:17:23.160 whatever I plug into it, the newsletter I plug into it, it pulls out the key points from that 265 00:17:23.220 --> 00:17:30.900 newsletter and tries to spin them into, uh, 20 to 30 YouTube titles that are similar and follow 266 00:17:31.000 --> 00:17:35.094 the same psychological patterns and principles as my best performing titles. 267 00:17:36.118 --> 00:17:36.840 And so it spits 268 00:17:36.880 --> 00:17:37.583 these out here. 269 00:17:37.603 --> 00:17:41.380 And then I tend to read through these cross out ones that I don't think would 270 00:17:41.440 --> 00:17:47.300 work, highlight ones that I think would potentially come up with a better one from my own mind, 271 00:17:47.900 --> 00:17:49.587 test that out on YouTube. 272 00:17:49.868 --> 00:17:52.780 If it doesn't work after two weeks, I'll try changing the title. 273 00:17:53.461 --> 00:17:56.551 Usually that'll get it to a decent place in terms of views. 274 00:17:57.574 --> 00:17:59.440 And the reason I create YouTube titles 275 00:17:59.580 --> 00:18:07.579 for this is because my newsletter is a practically an outline for my YouTube videos, right? 276 00:18:07.620 --> 00:18:07.820 I have 277 00:18:07.860 --> 00:18:10.028 it pulled up as I'm looking at the screen. 278 00:18:10.229 --> 00:18:13.220 I mean, at the camera, I'll look down, read a sentence, 279 00:18:13.440 --> 00:18:14.404 recite it to the camera. 280 00:18:14.685 --> 00:18:15.549 Sometimes I'll riff. 281 00:18:15.970 --> 00:18:17.356 Sometimes I'll read straight from it. 282 00:18:18.119 --> 00:18:18.360 If I'm 283 00:18:18.420 --> 00:18:24.280 looking down and reading at the newsletter, my editor just adds B roll or text screens over my 284 00:18:24.360 --> 00:18:24.661 face. 285 00:18:24.942 --> 00:18:29.218 So people can't see me looking down, but that's the general structure of it. 286 00:18:29.418 --> 00:18:29.840 And people 287 00:18:29.940 --> 00:18:30.442 quite like it. 288 00:18:30.502 --> 00:18:36.760 The objection there usually is, uh, well, if you're posting the same thing on 289 00:18:36.820 --> 00:18:39.730 two platforms, won't people notice that or won't they get bored? 290 00:18:40.352 --> 00:18:42.840 And most of the time I've seen 291 00:18:42.920 --> 00:18:43.523 the opposite. 292 00:18:43.703 --> 00:18:47.900 Like there are people that read it and then when they watch or listen to it, they 293 00:18:48.502 --> 00:18:50.928 get something entirely new because it's a different medium. 294 00:18:51.751 --> 00:18:55.000 Other people prefer to watch or listen 295 00:18:55.200 --> 00:18:56.925 rather than read. 296 00:18:57.807 --> 00:19:03.040 And I just feel like my philosophy behind it is I'd rather produce 297 00:19:03.742 --> 00:19:10.160 one amazing thing a week and just put all of my attention into that and put it out across 298 00:19:10.280 --> 00:19:15.840 all platforms rather than try to create something new for each platform and each of those things 299 00:19:16.402 --> 00:19:17.706 not be as good. 300 00:19:18.568 --> 00:19:22.400 And there's probably marginal difference between the two paths, but I've really 301 00:19:22.500 --> 00:19:28.800 gotten into this flow of the weekly flow of newsletter, YouTube video, social posts across 302 00:19:28.920 --> 00:19:29.582 all platforms. 303 00:19:29.683 --> 00:19:31.388 And it's worked out pretty well. 304 00:19:31.448 --> 00:19:35.600 People don't get angry and it's seems like it's 305 00:19:35.640 --> 00:19:35.941 working. 306 00:19:38.605 --> 00:19:46.620 But the next thing I do is I'll take the newsletter or the YouTube video and I'll plug them 307 00:19:46.760 --> 00:19:54.278 into a deep posts generator prompt and just a content ideas generator. 308 00:19:54.298 --> 00:19:55.140 And these are both kind 309 00:19:55.160 --> 00:19:58.528 of the same thing for the deep posts generator. 310 00:19:59.310 --> 00:20:03.840 I wrote a prompt that breaks, it breaks down the 311 00:20:03.880 --> 00:20:05.705 newsletter or whatever you feed it. 312 00:20:05.745 --> 00:20:07.790 It could be a PDF, a YouTube video, anything. 313 00:20:08.632 --> 00:20:10.537 And I came up 314 00:20:11.740 --> 00:20:16.300 with this prompt, still kind of fuzzy how I did it because it was like a huge conversation, 315 00:20:17.143 --> 00:20:21.900 but I broke down, I asked it to break down a bunch of these social posts that I really liked, 316 00:20:22.962 --> 00:20:28.420 the way they were structured, the way they were written and the key things that made them do 317 00:20:28.540 --> 00:20:29.082 really well. 318 00:20:29.604 --> 00:20:34.439 And after that conversation, it said, okay, well, a lot of these have paradoxes 319 00:20:35.202 --> 00:20:36.588 and counterintuitive truths. 320 00:20:36.869 --> 00:20:38.916 A lot of them have a transformation arc. 321 00:20:39.037 --> 00:20:39.880 A lot of them have core 322 00:20:39.960 --> 00:20:41.465 problems. 323 00:20:41.525 --> 00:20:46.160 A lot of them have examples or they handle objections or they have action steps or 324 00:20:46.361 --> 00:20:47.444 aspirational statements. 325 00:20:48.127 --> 00:20:50.976 And so I was like, okay, take each one of these and 326 00:20:55.848 --> 00:21:01.160 break down the newsletter, whatever you're fed into like five compelling post ideas, 327 00:21:01.461 --> 00:21:05.012 like the most impactful ideas that could be turned into posts. 328 00:21:05.514 --> 00:21:07.480 And then I want you to ideate 329 00:21:08.162 --> 00:21:13.860 three core paradoxes, a bunch of key quotes, transformation arc, core problems, key examples. 330 00:21:14.080 --> 00:21:20.820 So with this, I'm not asking it to write tweets for me because the LLM isn't going to be too good 331 00:21:20.860 --> 00:21:23.831 at doing that unless you guide it to in a very specific way. 332 00:21:24.353 --> 00:21:26.280 But instead here is I have it give 333 00:21:26.360 --> 00:21:38.080 me the pieces of ideas like the deconstruction of high performing content and ideas and just give 334 00:21:38.100 --> 00:21:38.802 me a bunch of those. 335 00:21:38.923 --> 00:21:40.167 And so I can read through here. 336 00:21:40.889 --> 00:21:44.120 And when one thing sparks an idea for me, 337 00:21:44.500 --> 00:21:46.529 boom, I can go and start writing a tweet on that. 338 00:21:46.992 --> 00:21:48.780 Or I can combine a bunch of these together 339 00:21:49.341 --> 00:21:56.680 since technically each of these, like all of these paradoxes, quotes, problems are all 340 00:21:57.803 --> 00:21:58.164 related. 341 00:21:58.184 --> 00:21:59.407 They're all about one idea. 342 00:21:59.467 --> 00:22:03.920 So I just have a bunch of building blocks for good content 343 00:22:04.100 --> 00:22:07.348 in here. 344 00:22:07.368 --> 00:22:11.679 The next prompt that I use is just a general content idea generation. 345 00:22:11.699 --> 00:22:12.220 I have it give 346 00:22:12.280 --> 00:22:13.764 me 60 ideas. 347 00:22:14.627 --> 00:22:19.020 And these are usually based around the tweets that have done really well for me 348 00:22:19.682 --> 00:22:20.886 or the social posts in general. 349 00:22:21.087 --> 00:22:24.460 I found that people really like when I give harsh life advice 350 00:22:25.102 --> 00:22:25.965 and I like that too. 351 00:22:27.088 --> 00:22:30.439 Counterintuitive truths, which is very similar to the paradoxes. 352 00:22:31.881 --> 00:22:34.310 Core problems or pain points, again, very similar. 353 00:22:35.053 --> 00:22:36.820 Key insights, wisdom, big ideas. 354 00:22:37.441 --> 00:22:41.980 So I can just read through here and I'm not technically, I'm not trying to copy paste these 355 00:22:42.662 --> 00:22:43.164 as a tweet. 356 00:22:43.285 --> 00:22:47.099 I'm just trying to generate a starting point for an idea so that I can 357 00:22:48.584 --> 00:22:50.170 have those ideas faster, right? 358 00:22:50.190 --> 00:22:53.400 Because I feel like good ideas are the fuel for content, 359 00:22:53.520 --> 00:22:59.640 but usually good ideas come from sifting through hours of YouTube videos on a walk or reading a 360 00:22:59.700 --> 00:23:07.420 good book or finding a really good sub stack article and having that generate ideas or just 361 00:23:07.480 --> 00:23:10.054 sitting and thinking with your thoughts until something emerges. 362 00:23:10.094 --> 00:23:11.060 And those are great ways to 363 00:23:11.140 --> 00:23:19.000 come up with ideas, but this is just a way to kind of force that to an extent and still maintain the 364 00:23:19.040 --> 00:23:23.291 quality without having the LLM actually write it for you. 365 00:23:24.634 --> 00:23:26.900 Now, so we just went over like in general 366 00:23:27.844 --> 00:23:31.196 how I go or how I create my newsletters and content each week. 367 00:23:31.216 --> 00:23:32.140 That's just the writing 368 00:23:32.341 --> 00:23:33.424 ideation process. 369 00:23:34.246 --> 00:23:38.940 How I actually structure that on a day-to-day basis is quite simple, 370 00:23:39.702 --> 00:23:45.759 where I wake up, do a little morning routine, shower, walk, whatever it may be. 371 00:23:45.839 --> 00:23:46.120 And then I 372 00:23:46.240 --> 00:23:49.973 sit down at my computer and the next two hours is just dedicated to writing. 373 00:23:50.936 --> 00:23:52.020 So in that writing, 374 00:23:52.140 --> 00:23:58.520 I have to finish one section of my newsletter and I have to finish three posts, three social posts. 375 00:23:59.322 --> 00:24:03.200 And then within that time, you usually have time within that two hours still 376 00:24:03.823 --> 00:24:07.780 to paste those social posts to all platforms or at least schedule them. 377 00:24:08.420 --> 00:24:10.840 And so that's kind of my routine every day. 378 00:24:11.123 --> 00:24:12.820 It's just two hours of writing. 379 00:24:13.200 --> 00:24:18.320 And that's the base of all of my social media, all of my newsletter. 380 00:24:19.382 --> 00:24:23.860 One day out of the week, I record my YouTube video and pass that off to the editor. 381 00:24:24.623 --> 00:24:26.740 And then boom, my content is done. 382 00:24:28.845 --> 00:24:29.920 And the rest is history. 383 00:24:30.782 --> 00:24:36.739 you got millions millions of followers millions of likes well that that was the other thing that i 384 00:24:38.726 --> 00:24:42.019 found relatively quick is 385 00:24:45.888 --> 00:24:51.580 once i had a post that started to generate more followers than other ones did 386 00:24:52.583 --> 00:24:58.160 i knew that i just had to start creating spinoffs of that post because then it's like 387 00:24:59.724 --> 00:25:02.532 I almost had a predictable way to increase the follower growth. 388 00:25:02.793 --> 00:25:05.140 So it's like the, the key part 389 00:25:05.240 --> 00:25:10.980 here is one, you need to experiment until you kind of strike gold and know what brings in followers. 390 00:25:11.581 --> 00:25:16.160 Then you need to make that a consistent part of your process and consistently create spinoffs of 391 00:25:16.240 --> 00:25:18.567 that while with your other time. 392 00:25:19.189 --> 00:25:21.817 And let's say that's 30% of the time. 393 00:25:21.837 --> 00:25:22.760 That's like one post a 394 00:25:22.780 --> 00:25:23.603 day out of the three. 395 00:25:24.005 --> 00:25:27.800 The other two posts are for continuing the experimentation on until you find 396 00:25:27.860 --> 00:25:32.458 the next one that is like you striking gold, then you make that a part of your process. 397 00:25:32.499 --> 00:25:32.820 Now you have 398 00:25:32.900 --> 00:25:38.240 two posts a day that are just consistently most like they, they're not all going to bring in a 399 00:25:38.280 --> 00:25:44.240 ton of followers, but you're getting closer and closer to just consistently increasing followers 400 00:25:44.360 --> 00:25:45.523 over time by doing this. 401 00:25:46.265 --> 00:25:51.860 And if you keep that balance of your core ideas that are consistently 402 00:25:52.001 --> 00:25:57.020 going to bring in followers with a healthy dose of experimentation until you find more, 403 00:25:57.464 --> 00:25:59.460 and then you just cycle out the core ideas, 404 00:26:00.400 --> 00:26:03.540 that's really the entire growth process 405 00:26:03.721 --> 00:26:06.520 on any social platform, in my opinion. 406 00:26:07.060 --> 00:26:09.140 So there's one thing that's missing from this, 407 00:26:09.300 --> 00:26:12.880 which is visual assets, like media. 408 00:26:13.321 --> 00:26:19.060 So on X, I've noticed that if I tweet just words 409 00:26:19.422 --> 00:26:21.379 versus I tweet words with an image, 410 00:26:22.001 --> 00:26:27.252 the words with image, you know, call it performs 40% better. 411 00:26:27.272 --> 00:26:31.200 Um, and so how do you think about 412 00:26:31.260 --> 00:26:31.461 that? 413 00:26:31.501 --> 00:26:35.480 How do you think, you know, okay, you do this process to come up with ideas, 414 00:26:36.244 --> 00:26:39.280 to write the content, but what do you do about the image? 415 00:26:41.021 --> 00:26:44.510 I don't do anything, but, but that's just me. 416 00:26:45.252 --> 00:26:48.180 Um, because I've ever since I started out, 417 00:26:48.320 --> 00:26:54.397 I kind of put the constraint on myself of like, I want to do this with just writing. 418 00:26:55.079 --> 00:26:55.320 I didn't 419 00:26:55.400 --> 00:26:59.951 start YouTube until I think two years after I was on Twitter. 420 00:27:00.893 --> 00:27:04.040 And just by creating that constraint, 421 00:27:04.180 --> 00:27:05.666 it made me be more creative. 422 00:27:05.706 --> 00:27:08.495 And I think it made me refine my writing a lot more. 423 00:27:09.037 --> 00:27:09.900 I've occasionally 424 00:27:10.341 --> 00:27:16.820 incorporated visuals in my Instagram posts and newsletters for like drawing out specific concepts 425 00:27:17.041 --> 00:27:22.140 or having certain infographics, or I even did animations on Instagram at one point. 426 00:27:22.680 --> 00:27:23.844 And those things definitely helped. 427 00:27:24.045 --> 00:27:28.400 But the animations eventually died down because a lot 428 00:27:28.480 --> 00:27:29.725 more people started doing them. 429 00:27:30.327 --> 00:27:32.093 And then same with the visuals. 430 00:27:32.113 --> 00:27:33.839 Like I noticed they were a 431 00:27:34.000 --> 00:27:40.120 good pattern interrupt when I would post those after not posting them for a while, and they 432 00:27:40.140 --> 00:27:41.326 would get a lot more engagement. 433 00:27:41.728 --> 00:27:44.060 But then if I tried to make that a consistent thing, they would 434 00:27:44.100 --> 00:27:47.411 just balance out as most of the posts did. 435 00:27:48.013 --> 00:27:49.900 And so then I'm like, I should just stick with writing 436 00:27:51.062 --> 00:27:59.960 because the ideas in my head, the thing that I feel built my audience the most, 437 00:28:00.221 --> 00:28:07.780 there's no way to know this, but I think it came from my focus on idea density and novel 438 00:28:07.880 --> 00:28:08.462 perspectives. 439 00:28:09.143 --> 00:28:15.780 So in my YouTube videos, especially, I try to bake in at least one thing that I think 440 00:28:16.141 --> 00:28:19.772 will like blow people's minds as an exaggeration. 441 00:28:20.173 --> 00:28:22.600 It's like the thing that I found so interesting 442 00:28:22.720 --> 00:28:24.808 that I feel like not too many people know about. 443 00:28:25.351 --> 00:28:27.760 If I can find a way to incorporate that 444 00:28:28.422 --> 00:28:33.295 into a newsletter that has a pretty broad and validated angle. 445 00:28:33.736 --> 00:28:35.100 So people go into the video 446 00:28:35.685 --> 00:28:37.460 because it's already validated. 447 00:28:37.820 --> 00:28:39.039 They like that topic. 448 00:28:39.240 --> 00:28:40.540 They'll just watch it to watch it. 449 00:28:41.140 --> 00:28:43.280 And then I have a good hook, a good lead. 450 00:28:43.741 --> 00:28:46.400 And then I lead them into like that mind blowing insight 451 00:28:47.325 --> 00:28:50.080 that makes them think a bit deeper 452 00:28:50.121 --> 00:28:51.379 and learn something new 453 00:28:51.642 --> 00:28:53.020 and have something new to explore 454 00:28:53.884 --> 00:28:56.819 that gives them this unique connection with me 455 00:28:57.442 --> 00:29:01.179 that not too many other people do. 456 00:29:02.480 --> 00:29:03.600 Does that make sense? 457 00:29:03.803 --> 00:29:04.079 It does. 458 00:29:04.180 --> 00:29:08.820 I think if you have really good optimized ideas, 459 00:29:10.061 --> 00:29:12.440 you don't need visuals. 460 00:29:13.963 --> 00:29:16.260 It's just so hard to come up with good ideas. 461 00:29:16.460 --> 00:29:18.880 I mean, you're sharing the sauce around how to come up with good ideas. 462 00:29:19.882 --> 00:29:22.680 But by the way, it's not just good ideas. 463 00:29:22.840 --> 00:29:24.959 It's good ideas that are optimized for feeds. 464 00:29:26.380 --> 00:29:30.500 Because you need people to reshare it to get seen 465 00:29:32.165 --> 00:29:33.600 or like it or comment on it. 466 00:29:34.141 --> 00:29:35.559 you need them to stop scrolling. 467 00:29:37.843 --> 00:29:39.780 So for a lot of people, 468 00:29:40.240 --> 00:29:44.060 the images or the videos are a bit of a crutch. 469 00:29:45.004 --> 00:29:46.840 You can take a not-so-good idea, 470 00:29:47.160 --> 00:29:49.120 crutch it to a really nice visual, 471 00:29:50.161 --> 00:29:52.800 and likely you'll get more seen. 472 00:29:53.881 --> 00:29:56.671 I do think that if you added images 473 00:29:59.604 --> 00:30:01.860 and or videos to your X posts, 474 00:30:02.462 --> 00:30:07.320 you would see not that you need you know another five million impressions a month but i think 475 00:30:07.902 --> 00:30:14.540 the way i would i mean i think it's fun to explore like sora 2 just came out um you know 476 00:30:14.761 --> 00:30:20.040 what are some short films cinematic films that you can you know you could be creating that's one 477 00:30:20.260 --> 00:30:27.075 the other thing is you know nano banana gemini flash 2.5 you know okay i'll show you something 478 00:30:29.640 --> 00:30:41.259 real quick actually go to my my ex so i had a um post that i posted that got like no like scroll 479 00:30:42.080 --> 00:30:48.420 keep scrolling it's like uh it's a lot it's a lot down but i had a post um yeah i'll let you know 480 00:30:48.440 --> 00:30:55.640 and that basically didn't go anywhere and then i reposted it with an image there it is stop 481 00:30:56.782 --> 00:31:04.380 it went up went up there it is the cringe mountain one ah so i posted this everything i ever got in 482 00:31:04.420 --> 00:31:08.340 life was because i climbed cringe mountain you sweat you shake you look stupid and then one day 483 00:31:08.380 --> 00:31:13.060 it breaks open and suddenly you're the only one with the view it went nowhere without the you know 484 00:31:13.641 --> 00:31:20.820 yeah basically nowhere without the image but once the image combined with you know maybe it wasn't 485 00:31:20.880 --> 00:31:27.938 a great idea maybe it was a pretty good idea with i think a really great image it it got 148 000 486 00:31:28.880 --> 00:31:32.918 impressions and by the way i hear you listening to this and you're like yeah but you have 500 000 487 00:31:33.280 --> 00:31:39.540 followers or whatever the followers don't really matter anymore realistically you know it's actually 488 00:31:39.761 --> 00:31:44.680 easier to get impressions if you have less followers it's you know what i mean like i can 489 00:31:44.780 --> 00:31:50.800 post something that is just like a throwaway tweet and it will go nowhere it'll get like a 490 00:31:50.880 --> 00:32:01.260 hundred likes compared to a typical two to three thousand and yeah it's just the the audience is 491 00:32:01.540 --> 00:32:09.478 definitely a force amplifier but only if you're good at that thing like if if most people who 492 00:32:10.922 --> 00:32:14.420 haven't practiced writing content for a long amount of time were given a million followers 493 00:32:15.023 --> 00:32:17.140 I do not think that that would help them in the slightest. 494 00:32:17.700 --> 00:32:17.820 Yeah. 495 00:32:18.711 --> 00:32:18.859 Cool. 496 00:32:20.460 --> 00:32:29.400 But yeah, let's actually show a cool way to do this with Claude or in creating a prompt 497 00:32:29.460 --> 00:32:34.740 to help you write tweets or to help you, I guess, learn how to write those high performing 498 00:32:34.908 --> 00:32:35.180 posts. 499 00:32:35.980 --> 00:32:41.660 So one thing I love to do is there's a two step process here. 500 00:32:43.043 --> 00:32:46.651 anything that I like and want to incorporate into my work. 501 00:32:47.113 --> 00:32:50.320 I will ask Claude or chat GPT to break 502 00:32:50.420 --> 00:32:52.666 it down, teach me how to do it. 503 00:32:53.307 --> 00:32:58.280 I will take that as if it were a, an SOP or just a set of instructions. 504 00:32:58.961 --> 00:33:06.260 Then I will take a prompt that helps me create prompts, send that, paste the instructions into 505 00:33:06.380 --> 00:33:11.680 it and say, I want to turn this into a prompt that interviews me for the exact thing you need 506 00:33:12.501 --> 00:33:16.008 in order to execute on this as best as possible. 507 00:33:16.770 --> 00:33:22.000 So as an example here is I said, break down the 508 00:33:22.040 --> 00:33:26.340 structure of this post so that I can recreate it from scratch, break down why it works, 509 00:33:26.480 --> 00:33:31.680 the psychological patterns involved, what context is needed from me and anything else I would need 510 00:33:31.720 --> 00:33:33.225 to understand how to recreate it. 511 00:33:33.927 --> 00:33:38.120 Then I just pasted, I believe this is one of my tweets that 512 00:33:38.983 --> 00:33:40.207 did pretty good. 513 00:33:41.551 --> 00:33:43.177 How to know you are doing something meaningful. 514 00:33:43.418 --> 00:33:44.080 You feel like you don't 515 00:33:44.120 --> 00:33:45.889 make any progress for weeks, months, or years. 516 00:33:46.371 --> 00:33:47.818 Then the growth hits you all at once. 517 00:33:48.039 --> 00:33:48.220 When you 518 00:33:48.260 --> 00:33:50.068 create your own path, results aren't predictable. 519 00:33:51.032 --> 00:33:52.860 And that keeps many people from sticking with it. 520 00:33:53.280 --> 00:33:54.827 So you find a good post. 521 00:33:55.430 --> 00:33:57.620 Well, first you write this, tell it to break it down. 522 00:33:58.584 --> 00:34:02.900 you find a good post that you want to understand why it did so well or how it was written. 523 00:34:03.441 --> 00:34:07.433 But this can also be applied to something like a landing page. 524 00:34:07.453 --> 00:34:09.540 Or if you're trying to write a book 525 00:34:09.922 --> 00:34:13.000 and you read someone else's book and you're like, damn, that paragraph was good. 526 00:34:13.701 --> 00:34:18.538 I want to understand how I can take my own idea and replicate the structure of this. 527 00:34:18.598 --> 00:34:19.100 So my 528 00:34:19.782 --> 00:34:21.326 writing flows the same amount. 529 00:34:23.313 --> 00:34:24.998 You can do that for writing YouTube scripts. 530 00:34:25.018 --> 00:34:25.700 If you're able to 531 00:34:25.820 --> 00:34:26.985 break down the transcript. 532 00:34:27.346 --> 00:34:29.033 There's just so many different things that you can do. 533 00:34:29.053 --> 00:34:30.920 I actually saw 534 00:34:31.842 --> 00:34:37.576 when Clue.ly first launched, they had a landing page that I really liked. 535 00:34:38.277 --> 00:34:39.400 And I copy pasted the 536 00:34:39.400 --> 00:34:47.000 landing page, wrote exactly this, told it to break down every single part of the landing page copy. 537 00:34:48.021 --> 00:34:54.480 And it called it paradigm shift marketing and just taught me exactly how to replicate it. 538 00:34:54.840 --> 00:35:10.500 So when I could take that and turn it into a prompt and then plug my own ideas for my own product into it, then it could rewrite that same style of copy, but with my product, my features, my problem that I'm solving, unique mechanism, et cetera. 539 00:35:11.080 --> 00:35:23.080 So with here, we're breaking down a tweet and it breaks down the core structure, hook statement, pain and struggle, the payoff, the insight and warning, why it works. 540 00:35:23.422 --> 00:35:27.380 And just by doing this alone, you can learn so much about writing content. 541 00:35:30.146 --> 00:35:35.080 Like this alone is a masterclass in writing one piece of content. 542 00:35:35.723 --> 00:35:37.379 And then you can continue conversing with it. 543 00:35:37.921 --> 00:35:41.020 And that helps you write better content on your own. 544 00:35:41.922 --> 00:35:45.160 Then it gives you a formula, additional elements to make this work. 545 00:35:45.540 --> 00:35:49.560 And then what I did here is I did the same thing. 546 00:35:49.802 --> 00:35:50.758 Do the same thing with this. 547 00:35:52.023 --> 00:35:57.940 and I took one of Zach Pogrob's tweet or Instagram posts. 548 00:35:58.744 --> 00:36:00.240 It was just the best way to get your spark back 549 00:36:00.342 --> 00:36:01.340 is burning everything down. 550 00:36:01.661 --> 00:36:02.860 You have to reset your life. 551 00:36:03.442 --> 00:36:06.076 Very similar to the things I like to read and write. 552 00:36:07.326 --> 00:36:08.180 And so I like this. 553 00:36:08.260 --> 00:36:09.200 I want it to break it down. 554 00:36:10.002 --> 00:36:13.500 I told it to, it has broke down the structure, 555 00:36:14.000 --> 00:36:16.120 provocative thesis, purge list, the promise, 556 00:36:16.300 --> 00:36:24.860 the elite view, the permission teaches me why it works, writing techniques, context needed, 557 00:36:26.443 --> 00:36:27.325 what makes it work. 558 00:36:28.047 --> 00:36:31.797 And then I did the same thing for one last tweet. 559 00:36:31.877 --> 00:36:32.860 So do the same thing with this 560 00:36:32.940 --> 00:36:33.221 again. 561 00:36:33.643 --> 00:36:38.220 People in third world countries spend their days talking, playing, dancing, and making love. 562 00:36:38.320 --> 00:36:42.920 People in first world countries aspire to spend their days talking, playing, dancing, and making 563 00:36:43.000 --> 00:36:43.242 love. 564 00:36:43.382 --> 00:36:44.367 I think about this often. 565 00:36:44.729 --> 00:36:46.840 This was just one I found and I'm like, that's a good idea. 566 00:36:47.220 --> 00:36:48.244 I'll throw it in here too. 567 00:36:49.146 --> 00:36:53.380 So the process of this is pretty much break down three tweets that you 568 00:36:53.480 --> 00:37:00.136 really like and then combine all of these into a singular guide. 569 00:37:00.837 --> 00:37:02.060 So now the anatomy of viral 570 00:37:02.140 --> 00:37:09.680 philosophical posts, a complete guide breaks down the three archetypes, which were the tweets 571 00:37:11.084 --> 00:37:16.880 and then core psychological patterns, technical structure, power techniques. 572 00:37:17.140 --> 00:37:17.799 This is insane. 573 00:37:18.623 --> 00:37:19.540 This is absolutely insane. 574 00:37:20.442 --> 00:37:21.780 It's really cool. 575 00:37:21.982 --> 00:37:24.240 And like, well, imagine doing this for more than just tweets, 576 00:37:24.320 --> 00:37:25.760 like YouTube scripts and other things. 577 00:37:25.940 --> 00:37:29.660 Like this is where it starts to all tie together. 578 00:37:29.920 --> 00:37:37.020 Once you use this process a few times, you realize that you can use it for almost anything. 579 00:37:37.761 --> 00:37:48.840 And then if you rewind this podcast to looking at the canvas that I was showing you, you can now see that each chat in there was one of these prompts that I created. 580 00:37:49.200 --> 00:38:05.840 So if I want to turn my newsletter into tweets and I use this there, then it like that's so much better than me pasting my newsletter into an LLM and being like, hey, what are 10 of the best ideas from this? 581 00:38:05.900 --> 00:38:06.639 Can you write a tweet? 582 00:38:07.361 --> 00:38:08.880 Have write 10 tweets for me. 583 00:38:09.341 --> 00:38:14.500 And then it writes like the worst tweets you've ever read and still includes hashtags. 584 00:38:15.242 --> 00:38:21.740 So this is like how you give the specific instructions so that it can write like you or write how you want it to. 585 00:38:22.581 --> 00:38:31.580 And then you can paste those directly if you'd like, or you can use those as ideas to like as a first draft, a starting point. 586 00:38:33.660 --> 00:38:43.620 Now, the last important thing here is I said from that guide, what is everything you would need for me in order to start writing tweets? 587 00:38:44.242 --> 00:38:50.180 everything I need to know from you, core identity, audience psychology, philosophical stance, 588 00:38:50.840 --> 00:38:55.780 voice parameters, specific insights, transformation narrative, emotional territory, 589 00:38:56.441 --> 00:38:57.105 so on and so forth. 590 00:38:57.146 --> 00:38:57.710 A lot of stuff. 591 00:38:57.730 --> 00:38:59.140 So we're making this very comprehensive 592 00:39:01.125 --> 00:39:02.849 because the context is king. 593 00:39:03.210 --> 00:39:07.300 The more context you give to the AI, the more it can get close to 594 00:39:07.922 --> 00:39:12.340 putting out what you actually want it to put out or putting out things that will blow your mind 595 00:39:12.420 --> 00:39:15.300 and that you feel confident in replicating week by week in your content. 596 00:39:16.125 --> 00:39:17.160 So now we have two things here. 597 00:39:17.541 --> 00:39:20.600 We have a description of the context we need, 598 00:39:21.603 --> 00:39:25.520 and we have instructions for how to actually write posts. 599 00:39:26.281 --> 00:39:28.660 So what I did next is I took these two things. 600 00:39:29.181 --> 00:39:31.520 I personally pasted them into just a separate note 601 00:39:32.505 --> 00:39:34.315 and then start a new chat. 602 00:39:37.302 --> 00:39:40.700 And what I did here is I have this special, 603 00:39:41.121 --> 00:39:42.386 this thing is a lifesaver. 604 00:39:42.587 --> 00:39:43.610 I use it all the time. 605 00:39:43.630 --> 00:39:46.380 It's just a prompt that helps you create better 606 00:39:46.480 --> 00:39:46.821 prompts. 607 00:39:47.282 --> 00:39:54.618 So I can share this in some way with you guys after, but it just, it's so good. 608 00:39:55.200 --> 00:39:55.420 You just 609 00:39:55.460 --> 00:39:56.083 have to try it. 610 00:39:56.524 --> 00:39:58.974 It makes very comprehensive prompts. 611 00:39:59.375 --> 00:40:00.680 Maybe you can pause, read through this 612 00:40:00.720 --> 00:40:07.758 if you'd like, but I send that and then I try to use the most powerful, I know 4.5 just came out, 613 00:40:08.420 --> 00:40:18.660 But I use 4.1 extended thinking on this because I just like to be as advanced as I can when I'm creating a specific prompt. 614 00:40:19.601 --> 00:40:23.420 And what I did or said, what is the topic or role of the prompt you want to create? 615 00:40:24.542 --> 00:40:29.840 I said, I want to create a prompt that helps me ideate social posts based on the guide from writing posts below. 616 00:40:30.340 --> 00:40:31.819 Structure this prompt in two phases. 617 00:40:32.020 --> 00:40:33.820 The first is context gathering. 618 00:40:34.062 --> 00:40:36.800 So interview me for the ideas that I want to write about. 619 00:40:37.483 --> 00:40:39.028 and phase two is post writing. 620 00:40:39.048 --> 00:40:42.100 So write three variations of each type of post using the ideas 621 00:40:42.260 --> 00:40:42.822 I gave you. 622 00:40:43.483 --> 00:40:44.807 Here's the additional context. 623 00:40:45.268 --> 00:40:49.799 So inside of here on this one, I didn't paste the 624 00:40:50.602 --> 00:40:55.659 context that it needed from me, but I could have right in phase one, I could have said, use the 625 00:40:57.585 --> 00:41:02.800 guide on what context you need for me in order to create interview questions that you can ask me. 626 00:41:03.081 --> 00:41:10.699 And then phase two, use the tweet writing guide to take everything I gave you and turn them into tweets. 627 00:41:11.820 --> 00:41:19.460 And so what it did after that, sometimes this prompt will ask clarifying questions if it has them to make the prompt better. 628 00:41:20.663 --> 00:41:22.640 But then it starts to spit out the prompt. 629 00:41:24.003 --> 00:41:26.800 And it has phase one, context gathering interview. 630 00:41:27.541 --> 00:41:29.520 Oh, I guess I did paste it in there. 631 00:41:29.934 --> 00:41:30.079 Right. 632 00:41:30.260 --> 00:41:31.540 So it's somewhere in the thing. 633 00:41:31.881 --> 00:41:32.122 thing. 634 00:41:32.302 --> 00:41:37.479 But the, when you send this prompt for writing tweets, it goes through, it asks you 635 00:41:37.880 --> 00:41:43.100 what your domain and expertise is, audience pain point, unique observation, transformation, vision, 636 00:41:43.260 --> 00:41:47.914 personal connection, uh, what tone specific examples. 637 00:41:48.395 --> 00:41:50.020 And then once it has enough information, 638 00:41:50.281 --> 00:41:54.756 it'll go into phase two, which is to generate nine posts using, uh, 639 00:41:58.247 --> 00:42:02.240 yeah three variations of the patient observer posts which was one of the examples 640 00:42:03.484 --> 00:42:09.260 uh three variations of the dramatic profit posts three variations of the quiet devastator posts 641 00:42:09.922 --> 00:42:15.420 post structure requirements constraints output format and then i just had it rewrite 642 00:42:16.443 --> 00:42:23.200 it as markdown without the code block so that i could paste that into my notes because not a 643 00:42:23.220 --> 00:42:30.560 coder don't use cursor any of that but i just keep things in notes but uh greg do you have questions 644 00:42:30.941 --> 00:42:39.200 on this what's going through my mind is like it feels like i've been doing content 645 00:42:40.784 --> 00:42:47.580 like a neanderthal you know that's that's what it feels like because i just i just brute force 646 00:42:47.702 --> 00:42:48.540 my way into it. 647 00:42:49.282 --> 00:42:51.271 I have an idea and I start typing 648 00:42:53.423 --> 00:42:54.660 and then I just throw it out there. 649 00:42:55.761 --> 00:42:58.176 It works for me and sometimes 650 00:43:01.353 --> 00:43:02.800 do what works type thing. 651 00:43:04.847 --> 00:43:05.599 That being said, 652 00:43:05.800 --> 00:43:06.839 what's going through my mind is 653 00:43:07.845 --> 00:43:10.600 we have a lot of accounts because I run a holding company. 654 00:43:13.146 --> 00:43:14.038 I find that 655 00:43:14.923 --> 00:43:19.539 some of my, you know, I love my team, but some of my team haven't been creating content. 656 00:43:19.580 --> 00:43:19.680 Like 657 00:43:19.740 --> 00:43:22.656 I've been writing, you know, I started a blog 20 years ago. 658 00:43:22.696 --> 00:43:23.139 You know what I mean? 659 00:43:23.159 --> 00:43:23.340 I've been 660 00:43:23.380 --> 00:43:30.860 writing for so many years that it's just kind of, uh, it's, it's, it's, it's, it's my instincts 661 00:43:31.201 --> 00:43:31.742 almost now. 662 00:43:32.704 --> 00:43:39.680 Um, so this is really helpful for managing multiple accounts with multiple people. 663 00:43:40.903 --> 00:43:46.980 and you really don't have an excuse not to be posting something every single day if you have 664 00:43:47.040 --> 00:43:55.400 this yeah i mean another way to think of it too is if you're a ghostwriter social media manager 665 00:43:56.402 --> 00:44:04.640 uh you're managing clients you can kind of send them a prompt that gets all of their 666 00:44:04.780 --> 00:44:10.640 you send it to them rather than like a onboarding questionnaire that pulls all of their details 667 00:44:10.761 --> 00:44:14.276 from them, gets examples of their best content, et cetera, et cetera. 668 00:44:14.356 --> 00:44:15.220 And then you just create 669 00:44:15.340 --> 00:44:18.492 prompts for like tweets, tweet writing for them. 670 00:44:18.873 --> 00:44:20.880 You create another prompt for YouTube script 671 00:44:20.980 --> 00:44:27.040 writing or landing page generation, all based around their voice, their profile, et cetera. 672 00:44:28.001 --> 00:44:38.630 And one last example that I'll share here is you can do a very similar thing for almost anything where imagine I know how to create offers. 673 00:44:38.730 --> 00:44:49.880 I've like been in the marketing space for so long, but a lot of people just starting, they have this superpower where they can start learning by doing faster. 674 00:44:50.663 --> 00:44:55.140 right you're it's not that you're avoiding reading a book like 100 million dollar offers by 675 00:44:55.581 --> 00:45:01.780 alex hormosi you're able to get the information you need to act and have ai act for you as a 676 00:45:01.880 --> 00:45:06.358 first draft so you get the first iteration out of the way as well so you can fail faster on 677 00:45:06.780 --> 00:45:13.160 creating your offer so that you can refine faster and in my eyes doing things this way isn't like 678 00:45:13.380 --> 00:45:18.211 outsourcing your agency or your cognition to AI. 679 00:45:18.312 --> 00:45:22.040 It's actually getting you closer to being high 680 00:45:22.140 --> 00:45:29.774 agency and learning through doing. 681 00:45:30.075 --> 00:45:32.840 The best way to learn is by building projects, failing, 682 00:45:33.280 --> 00:45:34.304 iterating, et cetera. 683 00:45:34.384 --> 00:45:38.760 So the example here and how to turn this into a prompt to create an offer and 684 00:45:38.800 --> 00:45:45.740 start selling and failing on whatever product it is, a SaaS startup, a physical product, 685 00:45:45.880 --> 00:45:51.760 digital product, whatever, I can just ask, give me a detailed guide on how to create offers like 686 00:45:51.820 --> 00:45:52.503 Alex Hormozy. 687 00:45:53.586 --> 00:45:57.600 The reason we do this rather than, hey, here's my product, help me create an offer 688 00:45:57.720 --> 00:46:02.174 from it, is because I want to narrow the context from the beginning, right? 689 00:46:02.215 --> 00:46:03.759 I don't want AI, I 690 00:46:03.940 --> 00:46:10.098 don't want the LLM to pull just general context that it thinks is best for creating an offer or 691 00:46:11.201 --> 00:46:11.942 writing copy. 692 00:46:12.704 --> 00:46:18.015 I want it to pull from the expert that I know has skin in the game here. 693 00:46:18.416 --> 00:46:20.120 So it gives 694 00:46:20.200 --> 00:46:27.740 me a detailed guide with the value equation, building a grand slam offer, pricing, 10x value 695 00:46:27.860 --> 00:46:31.309 test, naming your offer, et cetera, et cetera. 696 00:46:32.552 --> 00:46:35.780 And I think when I was doing this, I cut myself off. 697 00:46:36.320 --> 00:46:41.239 But what you can do here is then I can say, okay, take this and 698 00:46:43.626 --> 00:46:46.574 act as if you are guiding me through creating an offer. 699 00:46:46.975 --> 00:46:48.138 What are the exact steps? 700 00:46:48.499 --> 00:46:48.740 Make it 701 00:46:48.800 --> 00:46:49.743 extremely detailed. 702 00:46:50.164 --> 00:46:53.936 And then I can do the same thing I did here or sorry. 703 00:46:54.578 --> 00:46:55.360 Then I can ask next, 704 00:46:55.460 --> 00:47:02.620 Okay, what's all the context you need for me in order to take my product and turn it into a very good offer? 705 00:47:02.961 --> 00:47:04.120 Then it will spit all that out. 706 00:47:04.501 --> 00:47:05.220 Now you have two things. 707 00:47:05.320 --> 00:47:08.300 You have the set of instructions and you have the context that you need. 708 00:47:08.940 --> 00:47:15.140 So the next thing you do is you paste the prompt that helps you create great prompts. 709 00:47:15.723 --> 00:47:17.280 It's going to say, what do you want to create? 710 00:47:18.002 --> 00:47:19.780 I say I want to create a two-phase prompt. 711 00:47:20.560 --> 00:47:23.700 Here's the information that you need to interview me for. 712 00:47:24.583 --> 00:47:28.255 then phase two, here's exactly how to turn this into an offer. 713 00:47:28.476 --> 00:47:29.760 So I want you to create my offer 714 00:47:29.840 --> 00:47:30.663 blueprint for me. 715 00:47:31.385 --> 00:47:36.200 And then you, it'll output a prompt, you copy paste this, you send it, 716 00:47:36.661 --> 00:47:37.864 you answer the questions. 717 00:47:39.367 --> 00:47:44.700 It spits out an offer blueprint that is probably 10 times better than 718 00:47:44.861 --> 00:47:47.209 something you would have done on your own. 719 00:47:47.791 --> 00:47:48.815 Just that, right. 720 00:47:48.855 --> 00:47:50.240 And it would probably be on par with 721 00:47:50.360 --> 00:47:56.640 what you would be able to do after two to three months of actually learning about it. 722 00:47:58.102 --> 00:47:59.754 And I believe that is it. 723 00:48:03.602 --> 00:48:06.280 Well, you delivered, dude. 724 00:48:07.263 --> 00:48:09.139 That's why I wanted to have you. 725 00:48:09.981 --> 00:48:11.800 You actually over-delivered, to be honest. 726 00:48:12.571 --> 00:48:12.740 Nice. 727 00:48:13.101 --> 00:48:20.080 And because I think my mind is just racing with how much more I can do with content. 728 00:48:20.882 --> 00:48:25.880 And, you know, what are other audiences I could be spinning up using this method? 729 00:48:27.581 --> 00:48:34.440 If you can, yes, let's include that Google Doc or that doc with some of this in the show notes. 730 00:48:36.784 --> 00:48:38.720 And I appreciate that generosity. 731 00:48:39.860 --> 00:48:42.280 Dan Coe, I hope you come back on the pod. 732 00:48:42.501 --> 00:48:49.940 I'll include links to where you can follow Dan on YouTube, on X, his newsletter. 733 00:48:51.204 --> 00:48:51.779 What else, Dan? 734 00:48:52.487 --> 00:48:52.859 That's it. 735 00:48:54.003 --> 00:48:57.320 If you're curious, you'll find stuff that branches off of that. 736 00:48:58.084 --> 00:48:58.380 Amazing. 737 00:48:58.601 --> 00:48:59.039 Thanks, Dan. 738 00:48:59.120 --> 00:49:00.198 I really appreciate it. 739 00:49:01.061 --> 00:49:06.859 And dude, it takes a lot for me to get my mind buzzing, but you did it. 740 00:49:08.194 --> 00:49:08.360 Good. 741 00:49:08.641 --> 00:49:09.500 Yeah, I appreciate it, man. 742 00:49:09.681 --> 00:49:12.440 And I'm glad that it did provide value. 743 00:49:12.560 --> 00:49:15.000 That's one thing I'm always hopeful for. 744 00:49:15.382 --> 00:49:16.240 Because you never really know. 745 00:49:16.320 --> 00:49:19.200 I've used this so much that it's second nature to me. 746 00:49:19.280 --> 00:49:20.320 So I'm very glad. 747 00:49:20.883 --> 00:49:24.100 I mean, I've used LLMs with content. 748 00:49:24.320 --> 00:49:25.779 Like, how can you make this more clear? 749 00:49:26.960 --> 00:49:29.936 Or, you know, that kind of stuff. 750 00:49:31.745 --> 00:49:33.880 But the way you approach content creation 751 00:49:34.081 --> 00:49:38.480 is a very methodical way of approaching content creation. 752 00:49:38.901 --> 00:49:46.840 it's like very surgical and um by the way i think this is the best way to learn how to create 753 00:49:47.362 --> 00:49:52.757 content you you might actually like everyone should set this up maybe over time you you're 754 00:49:53.860 --> 00:49:58.500 like you know what i'm just gonna now i understand what works and what doesn't work i'm just gonna 755 00:49:58.721 --> 00:50:05.380 shoot from the hip like greg um and that might be what you what might you know end up being 756 00:50:05.783 --> 00:50:06.368 great for you. 757 00:50:06.912 --> 00:50:07.699 Or you might be like, 758 00:50:08.663 --> 00:50:08.880 hey, 759 00:50:11.034 --> 00:50:11.720 I'm going to double down 760 00:50:11.760 --> 00:50:13.359 on this and I'm going to make 20 accounts 761 00:50:14.448 --> 00:50:15.760 and that's what this is going to look 762 00:50:15.820 --> 00:50:16.387 like. 763 00:50:16.427 --> 00:50:17.620 And I think I'm really 764 00:50:17.701 --> 00:50:18.878 interested in that because 765 00:50:20.874 --> 00:50:21.680 I just think that we're 766 00:50:21.721 --> 00:50:23.079 in this window where there's a huge 767 00:50:23.665 --> 00:50:25.460 arbitrage opportunity to earn attention. 768 00:50:26.680 --> 00:50:26.700 So 769 00:50:26.700 --> 00:50:27.768 any way to help that, 770 00:50:29.760 --> 00:50:30.814 I'm looking for ways 771 00:50:31.320 --> 00:50:32.070 to optimize. 772 00:50:32.800 --> 00:50:35.480 yeah agreed 773 00:50:36.393 --> 00:50:36.859 Dan Co 774 00:50:37.001 --> 00:50:38.239 Startup Ideas Podcast 775 00:50:39.030 --> 00:50:39.658 thanks for coming on 776 00:50:40.794 --> 00:50:41.160 thank you man