6/18/2025 - Exploring Midjourney's New AI Video Generation Feature

Transcript

1. 0:05[Music] Champ, are you ready? Are you ready, big boy? Are you ready for the singing? Come on, boy. Get over here. [Music]
2. 0:32She came on [Music] his feel.
3. 0:47She sat on a stool and he said, "What do you want?" She said, "Give me a love that doesn't freeze up." [Music]
4. 1:06Said, "I have melted some in my time, dear. But to sit next to you, well, I shiver and shake.
5. 1:20And if I knew love, well, I don't think I'd be here. Asking myself if I've got what it takes
6. 1:35to melt your icy blue heart. [Music] Should I start turning for years?
7. 1:51into a river. [Music]
8. 2:10What do you think, champ? What do you think, buddy? You good? Why you so you're you're a little ramy tonight? What's going on?
9. 2:25[Music] sitting in this lonely town. Yeah.
10. 2:42Wonder when things are going to change. [Music] Dream my life away. Seems these dreams have turned to a bunch of glass.
11. 2:58[Music] Get my love up, but my past is pulling me down. [Music] Wondering how long this black sheep will stick around.
12. 3:19Somebody told me once before, you can never go home again. Won't you leave? Santa things to ste me away. Yeah. From
13. 3:32the truth of who I am and what I believe. So I thanked him for his two cents with a handshake and some sympathy. Yeah.
14. 3:46packed on my blue jeans and headed for that big prize of my freedom. Bye-bye, black sheep. To the black sheep of the
15. 4:02family, you're not singing anymore, champ. Bye-bye. Oh, seems so very much to me. Bye-bye,
16. 4:17black sheep to my friends and my family. Bye-bye. How going to set my soul
17. 4:31set it free? [Music] Oh yes. How is everybody? What is going down? What's going up? What's shaking?
18. 4:46What's sitting still? What do you think is sitting still, but it's actually shaking? That happens.
19. 5:03Oh, good lord. Good lordy. Lordy lordy. All right. So, I know what we're playing with tonight, which is good.
20. 5:13You guys ready to play? We're gonna play. We're gonna do a little playing. I did another test run of feed your prompt on the
21. 5:25AI readiness project, but I was midway between a rewrite. And here's what I learned. Don't share something that's not written.
22. 5:37I didn't know what the [ __ ] I was saying. Have you checked out AI 2027? I have not. Oh, wait. Was that out like a month
23. 5:46or two ago? I think I have checked that out. Um, I thought that was something that came out today. AI 2027. Yeah, that's the sort of the
24. 5:56shit's coming, the robots are going to eat us. Is it that one? The geopolitics of super intelligence. We predict pred predict the impact of
25. 6:05super human AI over the next decade will be enormous exceeding that of the industrial revolution. Yeah. Mid 2025
26. 6:11stumbling agents. That's right where we are. Early 2026 coding automation sounds about right. We've got shitty
27. 6:26versions of that now. Mid 2026, China wakes up. depends what they're talking about with China because some of the
28. 6:33[ __ ] China's doing is already better than what we're doing in the creative spaces certainly or at least as good. Um,
29. 6:42late 2026 AI takes some jobs. That's an interesting one. January 2027, agent 2 never finishes learning. That we seem to be on track
30. 6:55for that. China steals agent too. Then we get into monthby-month breakthroughs of once once we hit super intelligence. Yeah, this is a cool
31. 7:08article. The infographic that that dynamically uh does its thing is pretty cool, too. Let's see if Brandon's here
32. 7:15yet. No, Brandon's going to be late. He's got weather coming through Ohio. I watched the first OpenAI podcast
33. 7:22YouTube. That was cool. Um, was that the one Jeff? That is uh it was Sam Alman's brother hosting it. Um yeah, I thought
34. 7:31it was quite good. I thought I thought the best part of it was the opening three minutes where they're just acting
35. 7:36like brothers. It was really good. It was really good. Um it was a little boring. So was that was that an Open AI production? If it was,
36. 7:47that explains why it was boring because his brother just asked him softball questions. Posted today. Posted today. Huh?
37. 7:57I don't know that one. I do not know that one. YouTube. Dear YouTube. Was that the one with his brother? Oh, no. Wait.
38. 8:12No. All right. Yeah, we could we could listen to that.
39. 8:26On brand. Severe weather has passed. Now I'm trying to get the kiddos settled. Beautiful. All right. So,
40. 8:37Well, it wasn't his brother. No, no, no. Wait, it wasn't his brother. No, no, no. There's a there's a an interview with
41. 8:44Sam Alman's brother from like three days ago. Two days ago. I don't know. Maybe yesterday. Is that two days ago? No,
42. 8:50that's yesterday. two days ago would be a day before yesterday, right? Yeah. So, sometime in some amount of days, there's
43. 9:00a video that looks like it's in a very similar setting with Sam Alman's brother and him. And then this is different.
44. 9:10Uh, it's a 40-minute interview. Yeah, the one with his brother's about 40 minutes, too. I saw the first and second
45. 9:17videos. Well, well, well. Ain't that special? So, but is this Let's see. Open AAI. Yeah, that's not that one.
46. 9:35So, I'll go Sam alman brother. [Music] That's two years ago. Oh, he was interviewed by his brother.
47. 9:51And then where is it? Come on, Sam. What's his brother's name? Jack Alman. Jack. Whoops.
48. 10:15All right. Share your screen, Kyle. I Yeah, I know. I'm just getting [ __ ] together. I'm just getting [ __ ] together. I don't know if I
49. 10:24want to share I don't know if I want to look at this stuff yet because it's a little boring. Now I'm singing yesterday in my head.
50. 10:31Yesterday, all my troubles seem so far away. [Music] Is Jack working today? I invited a nice
51. 10:46lady. She may be connecting soon. Fantastic, Mr. Bring your friends. Bring your neighbors. Come on. Come all to the
52. 10:53AI learning lab where learning occasionally takes place, but not in the ways intended. Um,
53. 11:08so the thing we're going to play with today is MidJourney dropped their video model. It's out. You can go make videos
54. 11:15on MidJourney right now. And if you just go there, you're not going to see it. And you're going to be like, "Where's
55. 11:21the video model? How do I make one of these here videos? This doesn't make any sense to me." So, we're gonna I'm going
56. 11:28to show you how to do that. Um, it looks to be pretty flipping good from what I can see. 26,000 coming tonight. DQ Blizzard. Hi
57. 11:42Dave. All right. What are we gonna do? Who's got questions? So, if you're new here, by the way, I'm still getting weird.
58. 11:58Steo, every time he likes something, it displays. Ah, Mark viewer, prioritize comments. Steo, you've been deprioritized. [Laughter]
59. 12:12All right. Not that I don't love you. I do love you, but I think it was a setting on my side is why you were showing up everywhere.
60. 12:23I might need to stop the live to get it to change the setting. All right. So, we'll just see a lot of Steo comments
61. 12:29likes tonight. You can keep liking, Steve. It's fine. I see the other comments in between them. Um Oh, the
62. 12:35videos are so good. All right. Let's see. Let's see. I think my friend Dave So, why don't we do this? We'll watch
63. 12:42the first We'll watch the first five minutes or so of the one with his brother or until I get bored. Maybe we go longer
64. 12:51than five minutes. Maybe it's actually compelling enough. Maybe I was watching it in some sort of bad way and then
65. 12:58we'll go look at the new one that dropped today. All right. I knew it. I'm the last priority. Yeah, Mr. We can't see anything you say. We're
66. 13:09just guessing. Open AI drop transcription for meetings for plus users. Really? Is it where is it?
67. 13:27New chat. I'm a plus user. Tools. No. Settings.
68. 13:43Where is it, Danielle? I've spent 410 hours in the learning lab. Wow. Well, if it makes you feel any better,
69. 13:53Kak, I've got about 1,250 hours of content up on YouTube. So, so I've got you beat. Oh my god. Lol. Low professional
70. 14:09background. [Music]
71. 14:24[Music] Rowdy Irwin. Rowdy's not liking the set. What is your background? That's my Listen, here's the deal. Those of you,
72. 14:37those of you trolling, thinking like, "If this is supposed to be some kind of learning lab, that sure looks to me like a shitty home office
73. 14:49decorated by someone with ADD who's got a hoarding complex." Okay, that's what it looks like, right? What
74. 14:59you don't see on the other side of the camera is the $20 million production studio, right? This was put together by a team
75. 15:06of 20 to make it look like a shitty home office. So there, there you go. Fantastic. Bob, tell him what he's won.
76. 15:14He had one crap. He thought it was a shitty home office. All right. [Laughter] No, man. I like it. It's Listen, I got
77. 15:25booze. I got I got 3D prints of of cars. I got a a rabbit. Rabbit R1. Not that kind of rabbit, you weirdos.
78. 15:39I got a picture of the wife. I got look a trophy from Super Bowl 12 when the Orange Crush I I think they lost.
79. 15:54Got that at a yard sale. So, don't think I don't have anything here. This not This is not amateur hour and it's like you've got someone here
80. 16:08that if you ask for my qualifications I could get out the certificates. Is he glitching for anyone else? No, I
81. 16:22think that's just my personality. Danielle. Um, all right. So, we're going to watch some movies. We're going to do movie
82. 16:35night. So, this is just like grade school. Okay, kids. You know when the when your teacher was hung over in grade
83. 16:40school? And she was like, "I've got a surprise for you. It's movie day." And then she put on the movie, turned out
84. 16:47the lights, and you'd hear her snoring five minutes later. We're gonna We're going to do that tonight. I see a 69 Camaro. Exactly.
85. 16:56That was from That's from Vicki. That judge is from Mr. It Pikachu I got at the yard sale. Uh the empty bottle of Bllandons. That's
86. 17:08from Serena and the Irregulars. I printed Groot. I'm in that copy of Wired magazine. Bet you didn't know that. Want to see?
87. 17:28Want to see what I looked like when I was younger and not fat? Well, less fat. [Music] So this the issue Richard Dawkins
88. 17:52I guess I probably should have had this thing uh bookmarked. What did you do the other night? I watched the guy try to find a picture of
89. 18:02himself in a magazine. Look at that. Huh? Wired magazine, baby.
90. 18:18And there's my there's my little Urban Desires magazine right there. There's a little article. There's me looking all [ __ ] hip, huh?
91. 18:30You see what you're dealing with here. All right. That's my my one qualification. I was in Myired magazine
92. 18:45once. Best practice go into chat GBT and give give you a list of all the work you have done together that can be used as
93. 18:57professional accomplishments. That's actually a great idea. An oldfashioned magazine. My grandma told me about
94. 19:03those. I like it. I like our trolls. Oh man. Impressive. All right.
95. 19:20All right. Let's go. Let's go watch some movies. I'll get drunk. We'll turn out the lights. I'll get drunk.
96. 19:35Excuse me. Anybody have any questions before we get started? Anyone want to run me down a rabbit hole? If you're new here, my name
97. 19:47is Kyle Shannon. This the AI learning lab. What we do here, it's the nickname of the channel is Chat Add.
98. 19:54Chances are low that I'll ever finish a sentence. Chances are low that I'll ever do what I say I'm going to do. Um,
99. 20:02occasionally something interesting happens here. But here's the deal. Here's why you're here. Anyone that tells you they're an expert in AI
100. 20:14is lying in generative AI. There's going to be there's there's experts in like building the models and in old school
101. 20:21AI, but generative AI, there are no experts right now because the shit's changing too fast. We don't know how to
102. 20:27use them. We don't know what AGI is. We don't know what super intelligence is. We can't handle the [ __ ] we have in our hands now. But
103. 20:37being in the conversation and being in a community of curious people that are trying to figure this stuff out, I think
104. 20:44is one of the most important things you could do with your life probably for the next three years, probably for the next
105. 20:50five years. PWC just came out with a report today or no yesterday uh talking about predicted job losses and all that
106. 20:59sort of [ __ ] One of the findings in the study was that current employees that had AI skills had a 56% premium on their salaries
107. 21:12compared to nonAI literate employees. So get get to a nunnery. Start hanging out in groups like this. Start hanging out
108. 21:21in the AI salon. All right. All right. [ __ ] All right. Why is he lecturing at us? He seems it seems very aggressive. I didn't I didn't
109. 21:33come here to be yelled at by some large man that looks like Alec Baldwin on a bad day. Jeez. Jiminy Christmas. Okay.
110. 21:48Need to get that 56%. No [ __ ] I know, right? I wish that applied to carpenters. I think carpenters are going
111. 21:55to be in good shape. Anyone in the handcrafts are going to be in good shape. All right. A B2B business.
112. 22:02There's this whole Johnny IV thing which I'm sure you know we can't really talk about. Johnny. Johnny. H. We got to
113. 22:06start. I got to start over. I can't do that. So, leave that in, please. No, no, no. We're going to All right. That's such a good
114. 22:14moment. It's such a brother moment. He calls him Joanie Ives. So far, we've got a consumer business, a
115. 22:23B2B business. There's this whole Johnny IV thing which I'm sure you you know we can't really talk about. Johnny, we got
116. 22:29to start. I got to start over. I can't do that. So, leave that in, please. No, no, no. We're gonna cut. All right. Today, I'm here
117. 22:37with Sam. Sam, before we start, do you have anything you need to say? You're my literal podcast bro now. Wow. This is
118. 22:43great. How did you come to this? It's so sad. You start a company, then you start being a VC, and now I'm here. Are you
119. 22:48disappointed? Well, I went the other way. What do you Well, I was like a VC and then I did a podcast and Yeah, it's
120. 22:54been good for you. It's great. I'm really proud of you. Okay, so but I think this is great for you. Thank you.
121. 22:58Okay. I think you're an incredible podcast. It's a very nice sweater, too. Thank you. Thank you. Okay, so uh I want
122. 23:04to start by talking about the Stop. What are you going to say? Go ahead. I'll say it later when we're done recording. I
123. 23:08wanted to start by talking about the future of AI and I'm I want to talk about the medium-term because the short
124. 23:14term is not as interesting to me. The long term, who knows? But like 5 10 years out is what I'm most interested in
125. 23:20talking about. And I kind of want to try to pull out from you your best guess of a bunch of specific things. One of the
126. 23:26places I wanted to start was in software. It seems like the most effective use cases. Yeah, Danielle and
127. 23:33Vicki both. I'm starting with this is the video that was out three days ago or two days ago with his brother. And then
128. 23:39I'll I'll go to the one that came out today. So I'll just play a little bit of this one until we get bored. Uh oh, what did I do?
129. 23:48um coding and then chat and code. Yeah, chat and code. I'm curious what's next like on the next sort of what's the next
130. 23:55set of things right after that that will come? Well, I think there will be incredible like other products like
131. 24:00there will be crazy new social experiences. There will be like Google Docs style AI workflows that are just way more
132. 24:09productive. You'll start to see like you'll have these like virtual employees. The thing that I think will
133. 24:13be the most impactful on that 5 to 10 year time frame is AI will actually discover new science. And this is a okay
134. 24:20so in case you missed that he he he mumbled through three things there. One was a social network was the first thing
135. 24:27he said. So some sort sort of social network. Mark I'm going to put money on it now that that social network will
136. 24:35have human verification as part of it. So like world ID. Um then he said a Google Docs like uh interface where it will just do your job
137. 24:47for you. So imagine I guess Google Docs where it's got agents built into it and it just does [ __ ] for you. And then now he's talking about
138. 24:57you know boring stuff like you know curing diseases and you know re rediscovering or discovering new kinds of physics.
139. 25:07a crazy claim to make, but I think it is true. And if it is correct, then over time, I think that will dwarf everything
140. 25:15else. Why do you think it'll discover new science? Well, I think we've cracked Tony Constant Costantino
141. 25:24or Constantino. Uh, I'm in the Matrix. I literally just watched this, then I watch your live and it's on again.
142. 25:33There are no coincidences, Tony. Tony, I thought you were informed. You come to the AI learning lab. We know everything
143. 25:40here. Oh, rather. Yes, it is rather singularity, isn't it? Yes. Reasoning. All right, we've got producer Brandon in
144. 25:50the house now. Models. We have a long way to go. I think we know what to do. And you know, 03 is already like pretty
145. 25:54smart. You hear people say like, "Wow, this is like a good PhD." What does it mean to crack reasoning? The models can
146. 26:00now do the kind of reasoning in a particular domain you'd expect a PhD in that field to be able to do. In some
147. 26:05sense, we're like, "Oh, okay. The AIs are like a top competitive programmer in the world now, or AIS can get like a top
148. 26:12score on the world's hardest math competitions." Or I know. We'll we'll I'll watch we'll watch this until he
149. 26:16says one particular thing which I think is really interesting. AIS can like, you know, do problems that I'd expect an
150. 26:21expert PhD on my PhD in my field to do. And we're like not that impressed. It's crazy. But it is sort of a crazy thing.
151. 26:27Yeah. You know, this reasoning ability of the models over the last year. Are you surprised? Yes. Yeah. You thought
152. 26:33that it was just going to be like the next token type? No, I thought it was going to take a little bit longer to get
153. 26:37where we are now. The last the last year of progress has been faster than I thought. Did the way reasoning happened
154. 26:42happen the way you thought it would happen? Like often has happened in the history of OpenAI sometime pretty often
155. 26:49the dumbest first approach turns out to work. So I don't I like I like that. So he's talking about 01 and 03 the
156. 26:56reasoning models. The dumbest first approach was the one that worked. I think I should which is why it happened
157. 27:01faster than they thought it would. be surprised by that anymore. And yet it's like a little surprising each time. So
158. 27:05reasoning will lead to science going faster or just new stuff or both? Both. I I mean you already hear scientists who
159. 27:12say they're faster with AI. Like we don't have AI maybe autonomously doing science, but if a human scientist is
160. 27:18three times as productive using 03, that's still a pretty big deal. Yeah. And then as that keeps going and the AI
161. 27:24can like autonomously do some science, figure out novel physics. Is it all that happening as a co-pilot right now? Yeah,
162. 27:30there's there's definitely not like you definitely can't go say like, "Hey, ChachiT, figure out new physics and
163. 27:36expect that to work." So, it is I think it is currently co-pilot like, but I've heard like anecdotal reports from
164. 27:43biologists where it's like, "Wow, it really did figure out an idea. I had to develop it a little bit more, but it
165. 27:47made like a fundamental leap." Yeah. Will it be easier to get AI to Wait, I'm toggling between Tik Tok and YouTube. If
166. 27:56you go over to YouTube, please welcome my friend Dave Jandelle. All right, welcome Dave Jandelle. Welcome to the AI
167. 28:07learning lab. My name is Kyle Shannon and you're gonna learn some stuff tonight. Is that Is that good, Kelly? Should I Is
168. 28:17he impressed? I have I have impressive qualifications and a set.
169. 28:31All right, back at it. Welcome, Dave. Show him your black bar skills. Build you a whole business like build you a
170. 28:43whole e-commerce business or like do like a hard piece of science or medium. I wonder about this. If you could like
171. 28:50build AI, a hundred billion dollar particle accelerator. Yeah. And say you make the decisions. You look at the
172. 28:58data. You tell us like uh you know what experiments to run and we'll go like find the stuff and do it. So you spend
173. 29:04$und00 million doing that. Yeah. This Yeah. The salaries Facebook offered OpenAI people is what I wanted to check out. A hundred million.
174. 29:15Facebook is offering Open AI OpenAI employees a hund00 million signing Bose bonus and as as much for a yearly salary
175. 29:24and Open AAI employees are turning it down. It's amazing. Or you spend hundred billion dollars like building it
176. 29:33infrastructure to like connect into the economy. Which of those will it have an easier time doing something remarkable
177. 29:38with? Yeah. And I think the physics is a cleaner problem. M you know I think if you could get like new high energy
178. 29:44physics data and then AI the ability to like run experiments I think that's like a a cleaner problem. Um, I've heard
179. 29:49people say that. I think that's a fascinating comment that he says that physics is a cleaner problem. Meaning I think meaning
180. 29:59you will know you will know if it worked more easily than say creating an intelligent swarm of agents that can just do all of the jobs of a
181. 30:12100,000 person consulting firm, right? that's not going to be as clean because people are going to keep employees just
182. 30:19because people trust people and they're not going to trust that the machine can do all the stuff even if the machine can
183. 30:25do all the stuff. So I I think that's a really fascinating it feels like a very scientist comment that the that the more
184. 30:35interesting problem to solve is the cleanest problem. I for me, you know, maybe it's a liberal arts thing. I think the problem that's
185. 30:44most interesting to solve is the messiest problem. They expect the first area of science and this is like I don't
186. 30:50know if this is accurate or not but I've heard people say that they expect the first area of science where AI makes
187. 30:54autonomous new discoveries to be astrophysics because there's just mountains of data and we don't have
188. 30:58enough PhDs to look at it and maybe it's not that hard to figure out new stuff but I don't really know. Okay. So
189. 31:03science gets better the coding and chat will just keep getting better. Does that lead on the business side? Do you also
190. 31:10then have the ability to just can you prompt a whole business like could you just say build me this type of business
191. 31:15it looks like this will happen that were there any people doing that for like small stuff. Oh by the way not for nothing.
192. 31:27I love that not for nothing corporate double speak line. Not for nothing. a single employee company today, I think it was today they closed
193. 31:40just sold for $80 million. And how long ago did that one person start that company? Anyone? Six months ago.
194. 31:53Six months ago, a dude started uh like a like a lovable kind of company and it sold today for $80 million. one employee, $80 million.
195. 32:08And if you know anyone who's like, "Yeah, AI is whatever." Okay. You know, you hear these stories of people who like
196. 32:17use AI to do market research and like figure out new products and then like email some manufacturer and get some
197. 32:25dumb thing made and sell it on Amazon and run ads. Like there are people that have actually figured out at small scale
198. 32:30in the most boring ways possible how to like put a dollar into AI and get the AI to like run a Mhm. toy business, but
199. 32:39it's actually working. Yeah. So that'll climb the gradient. Yeah. What about in the world of like physical stuff? Cuz
200. 32:45like I get that I mean it seems to me, you know, very clear that like software is just going this direction. Science I
201. 32:52know less. Take your word on it. What about like moving physical things around? behind, but I think we'll get
202. 32:57there. Uh, for example, I think we have some new technology that could just do self-driving for standard cars
203. 33:05way better than any current approach has worked. And that might not be quite what you meant by like humanoid robots, but
204. 33:11if our AI techniques can like really go drive a car, that's still pretty cool. Yeah. Um, humanoid robots are the dream.
205. 33:20Obviously, I really care about that. I think we will get there eventually. It's been like a hard mechanical engineering
206. 33:25challenge. That's more the issue. No, both things are hard. But like even if we had the perfect brain right now, I
207. 33:30don't think we have the body yet. Um we we actually very early on open we used to work on this robotic hand and it was
208. 33:37hard for all the wrong reasons. Like the thing just broke all the time. The simulator was like a little bit off.
209. 33:42Wow. But you know, we'll get there. Yeah. I think 5 to 10 years we'll have great humanoid robots. Yeah. Like
210. 33:47amazing. And they'll just like walk down the street be doing 5 to 10 years great humanoid robots. Um, how do I talk to
211. 33:53the $80 million man? Um, hang on. You go. Let me get get his name. He's a full stack developer. All these guys making
212. 34:03this money are full stack developers. Um, 80 million. Um, one person
213. 34:28I forget his name. It's somewhere in there. All right, back at this. Where is my There it is. Okay,
214. 34:42stuff. Yeah. I mean, you would think that's where a huge amount of step change unlocks, right? I think that will
215. 34:48be one of the moments that not only is unlocks a bunch of stuff in the world. I think that will feel the strangest. We
216. 34:56get used to a lot of things. We get used to like Chachi BT doing these things that would have sounded like a miracle 5
217. 35:01years ago. But if you walk down the street and it's like half robots, are you going to get used to that one right
218. 35:04away? I don't know. Probably you do, but it feels like a big difference. That's the one that will feel like there's like
219. 35:07a new species taking over us. Yeah, I think that'll feel I feel like a new species or that it's taken over, but I
220. 35:12think it will feel like the future in a way that CHBT still does not. I think also if we can figure out great new
221. 35:16computing devices to make that will feel maybe like the future, but as amazing as CHBT is or these new coding agents and
222. 35:23they are amazing. It's like still stuck in the form factor of the past. Yeah, it's also stuck in it's stuck in the
223. 35:27computer. Yeah, there's definitely something about that it only can do stuck out of the computer, but I don't
224. 35:30know like how much of the economic value in all the world do you think is like cognitive labor that can be done behind
225. 35:34the computer? Like half. I was going to say a quarter maybe half. I don't know, but some big number. Yeah. Does this
226. 35:38stuff get much riskier once we have like super embodied intelligence because the things are going to be way stronger than
227. 35:41us too. I don't know about way riskier. I think like the ability to make a boweapon or like take down a country's
228. 35:46whole grid you can do can do quite damaging things without physical stuff. It gets riskier in like sillier ways
229. 35:51like I would be afraid to have a humanoid robot walking around my house that might fall on my baby unless I like
230. 35:54really really trusted it. Yeah. What what like um if you're thinking about, you know, we're back here in 10 years
231. 35:58having another conversation and we're like M A O R M Mar Schlommo was the $80 million man. M A O R S H L O M O. Did AI do what we
232. 36:14thought it would do? What metrics are you expecting? Like is it that like the GDP growth curve has a kink in it? Is it
233. 36:20that like life expectancy is up? Is it like there's less poverty? Is it something completely different? So every
234. 36:24year before the last like maybe up until last year I would have said like hey I think this is going to go really far but
235. 36:27it still seems like there's a lot that we've got to figure out. I feel very confident at this point the most
236. 36:32confident I've ever felt that we kind of like know what to do to get the incredible AI systems that are just
237. 36:35super super capable. If something goes wrong wait I want you to hear that is it like there's less poverty is it
238. 36:49something completely different? So every year before the last like maybe up until last year I would have said like hey I
239. 36:54think this is going to go really far but it still seems like there's a lot that we've got to figure out. I feel very
240. 37:02confident at this point the most confident I've ever felt that we kind of like know what to do to get to incredible AI systems that are just
241. 37:08super super capable. So, we know what to do to get to I basically what he says in this interview is they know what to do
242. 37:15to get to super intelligence, which says to me they I they're either at AGI or they're on the path to get there and
243. 37:24they know how to get to super intelligence. If something goes wrong, I would say like somehow it's that we build
244. 37:31legitimate super intelligence and it doesn't make the world much better. Doesn't change things as much as it
245. 37:36sounds like it should. How would that happen? Seems like a crazy thing to say. Yeah. But like I don't know if I told
246. 37:41you in 2020, maybe I did tell you like we're going to make something like Chad GPT and it's going to be as smart as a
247. 37:50PhD student in most areas and we're going to deploy it and you know a significant fraction of the world is
248. 37:57going to use it and kind of use it a lot. Maybe you would have believed that, maybe you wouldn't have, but conditioned
249. 38:02on that, I bet you would say, "Okay, if that happens, the world looks more way more different than it does right now."
250. 38:07Yeah. So, it's like, and he's made this prediction before. I think it's really fascinating that, you know, we blew
251. 38:15through the Turing test, right? And and now we're going to blow through AGI and then at some point we're going to blow
252. 38:22through artificial super intelligence. And like one of his predictions here is well what if not that much changes that
253. 38:29some people go off and use it and make 80 million dollar companies in six months and sell them. But most of the
254. 38:36people just keep going and just keep doing what they do. It's a really that's a really fascinating thought. All right.
255. 38:41So that that that was that interview. I think it's that that's an interesting interview. This other one I haven't seen
256. 38:47at all. So this week we're hosting a free trading and investing workshop right here in Denver. Inside this
257. 38:53workshop, you'll learn you don't need to be a after that. I work with companies and individuals trying to figure out.
258. 39:00Welcome to the OpenAI podcast. My name is Andrew Maine. For several years, I worked at OpenAI first as an engineer on
259. 39:06the applied team and then as the science communicator. After that, I work with companies and individuals trying to
260. 39:11figure out how to incorporate artificial intelligence. With this podcast, we have the opportunity to talk to the people
261. 39:17working with and at OpenAI about what's going on behind the scenes and maybe get a glimpse of the future. My first guest,
262. 39:24someone said we didn't pass the touring test with AI. I don't know. It is there. They keep moving the goalpost on the
263. 39:31Turing test, but I swear to God, the first time I use Chat GBT, I'm like, well, there goes the Turing test
264. 39:38now. I I ain't no scientist. I ain't got them there books smarts. Um, but basically what they've got is um, how
265. 39:47they keep moving the B goalpost is the amount of time that you would interview a computer before you knew it was a
266. 39:55computer, right? So, it used to be, you know, 10 seconds, then it was like a minute, there was like five minutes.
267. 40:00Now, it's like now I think they've pushed it out to if if I could interact with a, you know, with a a machine for
268. 40:08eight hours and not be fooled, then we'd pass the turning test. I don't know. desktop computers were going to give us
269. 40:14were going to do all our work at one point. Uh to our point of boredom didn't happen. Here's the difference, Kelly, that
270. 40:22here's why I don't think we can predict with the generative A. It's the the G and GPT is the difference, right? The fact that computers now
271. 40:35are generating original work. generating original work even though it's prompted. Um, computers historically
272. 40:51have not been generators, they've been processor, they've been computers. They would compute the data we give them. So,
273. 40:57we would say, "Here's our spreadsheet. Go do the math faster." But we couldn't say, "Go invent a spreadsheet.
274. 41:07Go invent a spreadsheet. Go find all the data in the world, put it in that spreadsheet, have that spreadsheet do
275. 41:13all this [ __ ] and right, you know. So, we lost Tik Tok. Oh, wait. Did we frozen? Yes, I lost him, too. Uh,
276. 41:26I'm I'm restarting Tik Tok because it was janky before. All right. Am I back, Tik Tok?
277. 41:41Are we good now? It's back. Back. Back. Back. Back. Back. Back. Back. Back. Rejoin. Keeps dropping though. I think
278. 41:48it was dropping. I think it was [ __ ] up before. I just I just force quit it. No voice. Back. Back. We're And we're
279. 41:55back. Tik Tok is acting up. Agreed. But I think humans will always find work to do no matter what. No, I agree. Listen. Um,
280. 42:04snap. Watch this one today, too. That's pretty funny, Tony. Oh, don't tell me Tony, what was the other thing you did
281. 42:11today? Play with midjourney video. I guess I'm going to put on midjourney video and start playing with that.
282. 42:16You're gonna be like, "Oh, yeah. Been there, done that. Whatever, Kyle." Yeah, I'm ahead of you by like 10 minutes. All
283. 42:22right, fine. Fine, fine, Tony. Okay. Um, what was I talking about? Oh, is it possible that these these
284. 42:36machines, these AI machines, the generative AI stuff really does um make the need for work optional? I don't
285. 42:49know. I I think to someone's point, DQ Blizzard's point, um, humans will always want humans need to make meaning. Humans need to connect.
286. 43:01So, jobs in the future might look a lot less like they look today, but we'll I think we'll still have jobs in the future. I
287. 43:09just think they'll look very different. Okay. So, is is Tik Tok back? We're good on Tik Tok, right? All right. Let's watch Yan Yan movie.
288. 43:20Um, have you made AI videos of Champ as a musical performer playing guitar? Not yet, but we could probably do that
289. 43:26tonight. That's pretty easy. Is Sam Alman, CEO and co-founder of OpenAI. And we're going to find out a bit more about Stargate, how he uses
290. 43:36ChatgBT as a parent, and maybe get an idea of when GPT5 is coming. More and more people will think we've gotten to
291. 43:44an AGI system every year. what you want out of hardware and software is changing quite rapidly. If people knew what we
292. 43:50could do with comput, they would want way way more. One of my friends is a new parent and is using chat GBT a lot to ask questions.
293. 43:58It's become a very good resource and you are a new parent and how much has chatb been helping you with that? A lot. I I I
294. 44:07mean clearly people have been able to take care of babies without chatbt for a long time. I don't know how I would have
295. 44:14done that. Uh those first few weeks it was like every qu I mean constantly. Now I now I kind of ask it questions about
296. 44:20like developmental stages more because I kind of I can I can do the basics but uh is this normal? Yeah. But it was super
297. 44:27helpful for that. I I spend a lot of time thinking about how my kid will use AI in in the future. Um it it is sort of like
298. 44:37by the way extremely kidilled. I think every have a lot of kids. Yeah, a lot of my friends at OpenAI, former colleagues and current ones are
299. 44:45having kids and people go like, "Oh, you know what is with the comically small tables?" [Laughter] She would even helping you with that.
300. 44:55What What is with the comically small tables? Come on. Come on. You can you can pony up for the for the 18inch one, you know. [Laughter]
301. 45:12It's midcentury modern. Yeah. No, it's comically No, it's not even up to their knees. Sam's not a tall guy.
302. 45:29Oh my god. Okay, this is what happens when you send interns to IKEA to buy furniture. This is what happens people. Okay? It's why
303. 45:39you need a cranky Gen Xer in the corner. All right, back to your regularly scheduled programming using AI and
304. 45:49obviously I think about that a lot. Uh but I I think much more about the like what they will have that we didn't than
305. 45:56what is going to be taken away. Um, they're like I don't I don't think my kids will ever be bothered by the fact
306. 46:06that they're not smarter than AI. I I just like, you know, I there's this video that one. Let's see. Midjourney. I
307. 46:14just saw a midjourney thing. Midjourney update is insane. Have we talked about this? No, Gareth, that's that's the next
308. 46:19thing. We're just these are sort of some impromptu little movie watching, little movie night. Uh, and but midjourney
309. 46:25video is gonna is going to be the big thing we're going to do tonight or I'm going to do tonight. Um, budgets. Yeah, good thing. Good
310. 46:34thing they have pants on. Am I right? The Finnish vocal fry. Yeah. One of the things I think Yeah. Sure. um a baby or like a little toddler
311. 46:52with a one of those old glassy magazines um going like this on the screen. Is it because it's an iPad? Thought it was a
312. 46:58broken iPad. Um and you know, kids born now will just think the world always had extremist AI and they will use it
313. 47:06incredibly naturally. Yeah. And they will look back at this as like a very, you know, prehistoric time period. I I
314. 47:14saw something I it's that's when I mean it happened here live over a course of a couple of weeks but when when 01 came
315. 47:24out when the first reasoning model came out um I realized that it it was the first time that I would sit in front of something
316. 47:36you know one of these generative AI tools and I literally didn't know what to ask it like I I did I didn't have the right life
317. 47:46experiences and the right training and the right exposure to big complicated problems to need something like that. And
318. 47:58that was a trippy moment. And I think I think most people either by choice or by force are gonna are going to be forced to confront
319. 48:13um these machines are smarter than you. They're they're more empathetic than you. They're more compassionate than
320. 48:21you. They're smarter than you. They can work harder than you. They can work longer than you. And if you don't think that's true, get
321. 48:31over it. Like, like, is it there yet? Well, for me it is. Like, I these things are already beyond my capacity. If you
322. 48:39watch Manis, go open up a hundred websites, surf them all, read them all, capture all of that data, analyze all of
323. 48:49that data, and write a report on what it found and write it into a spreadsheet in 15 minutes. Yeah, it's smarter than me.
324. 49:02The table is the perfect height size for two glasses of water without holding without hiding the speakers. Yeah, but
325. 49:09they don't even have the water on it. It's just a tiny table. Just just sit there or put the table behind them
326. 49:18where, you know, so they could pick the water up and not kick it. Tik Tok pin. Some people don't have a $20 million
327. 49:26studio, Kyle. It's a good point. It's a good point on social media. All right, I'm bored by this interview already.
328. 49:31Well, let's hopefully we can get out of the the parenting mode here and get to some ASI [ __ ] where a guy talked about
329. 49:37he got tired of talking to his kid about Thomas the Tank Engine. So, he put it into chat GPT into voice mode. Kids love
330. 49:44voice mode. Chat and he was like an hour later the kid still talking about Thomas the train. Again, I suspect there this
331. 49:51is not all going to be good. There will be problems. people will develop these sort of somewhat problematic or maybe
332. 49:56very problematic parasocial relationships and well society will have to figure out new guardrails and uh but
333. 50:02the upsides will be tremendous and and we society in general is good at figuring out how to mitigate the downsides. Yeah. So uh yeah I think
334. 50:11optimistic we're seeing some interesting data where used along in classrooms with a good teacher good curriculum chat
335. 50:18becomes very good used solely by itself as sort of a homework crutch can lead to kids sort of just doing the same thing
336. 50:24as trying to Google stuff. I was one of those kids that everyone was worried I was just going to Google everything when
337. 50:30it came out and stop learning and you know it turns out like relatively quickly kids in schools adapt. So I think we'll figure this out.
338. 50:37Think of what you could have become if you didn't Google everything, Sam. You know, so we've seen this adoption
339. 50:43figures which are really insane. It's open's most popular product. Mr. Wonderful here. My friend Howard
340. 50:50Marx is the co-founder of Activision. The shut up you dipstick. I don't like him. [Music]
341. 51:04All right, let's go do mid Journey. Mid Journey, that's the name. Valerie Cox, I think that this that the most amazing
342. 51:12thing about this tool, it can be used to create shopping lists and research. Oh, to research the most complicated topics. Yeah. I
343. 51:22So, I'm I'm working on this book project um feed the prompt. Feed your prompt. And I was talking to a branding person today
344. 51:35and they were asking me questions about the book and she told me about her friend who's got a kid who's going
345. 51:42through a phase where he won't eat anything round like a hamburger. Won't eat it. and and she's going mad because she can't figure
346. 51:55out like there there's all these very specific rules, right? And you know, for the neurospicy people on this channel,
347. 52:01right? May seem familiar, right? You know, don't don't don't pick on the the neurospicy kids, but that's a really fascinating use case
348. 52:12where you could just vomit all of that uh context into chat GPT. Tell it, "I've got this kid. It's driving me crazy.
349. 52:21Here's what he used to eat. Here's what he likes. Here's the nutrition needs he has. Here's the special diet. And he
350. 52:27can't even eat anything round. I need recipes, creative ideas, and a shopping list for the next week." Bang. Done. You know,
351. 52:36so let's see. I tested the same prompt. Oh, this is cool. Toddweller on AI LLM and Manis and Manis one number one,
352. 52:45Gemini number two, Copilot 3, Deepseek 4, Chat GBT, Grock, Claude, Quen, Jen, Spark, and Perplexity. Oh, Chat GBT, Grock, Claude, Quen, Jen,
353. 52:59Spark, Perplexity all failed to complete the task. That's super cool, Todd. Very very cool. That those kind of tests are
354. 53:10important. Um, okay. My 88-year-old mom wouldn't access chat GBT today. Oh, couldn't. And I thought she was going to lose her
355. 53:20mind. Yeah, these parasocial uh relationships or something. Okay, let's go to let's go to midjourney, shall we?
356. 53:27Let's get rid of Mr. Wonderful there. Ah, so here this video is a midjourney video. So, this is a fictitious car I invented.
357. 53:41And then I just said make that a video. So, now here's how you do it. Let me let me flip back into create mode here.
358. 53:53All right. You can all see that, right? So, for live will end in five minutes. Do your physical dexterity challenge now.
359. 54:04Congratulations. You've passed. Mom is completely addicted to chat GBT. Oh, this was this one's beautiful.
360. 54:18This was just a cool image I did ages ago. And the the animation here is stunning.
361. 54:42Like the hair is all like you look down here like the individual strands of hair. There's no jankiness in them. Wait, when did Mid
362. 54:51Midjourney start doing video? I'm so behind. Cam, I can't believe you didn't know MidJourney did video. It's been out
363. 54:57for like an hour and a half. It dropped today. It dropped today. No one's behind. No one's behind. No one's
364. 55:07judging anyone for not knowing that Mid Journey did video. Um they announced it like a week ago and we we went in I
365. 55:14think last week and did some um some ranking. You could rank videos and then they dropped it today. That one's so cool. This one, this one
366. 55:27reminds me of like a 60s magazine ad and now she's blinking. That news was so three hours ago. I know. Yeah. Cam
367. 55:36really disappointed. Really falling behind in the lab. That one was crappy. I didn't like any of these. This one. Oh, yeah. Come on, people.
368. 55:53My daughter is flying here this weekend. I'm afraid it's for a chat GPT intervention. Dr. Jay's gonna get she's
369. 56:01gonna get sat down by the family. Listen, listen about this chat GBT thing. We've uninstalled it from your
370. 56:08phone and your iPad. We've restricted the domain on your computer. I'm going to the library. Oh, good lord. This is great for
371. 56:22consistent characters. Yeah, this is pretty cool. Um, why is that not going? Oh, because I'm probably not on the There we go.
372. 56:49[Laughter] You see, you see what happens? So, the history of this photo,
373. 57:06this little part of the photo right here, I made a really low res version of that in fall of 2022. And this this was an image that when I
374. 57:17made it, it it I got emotional. It took my breath away because I'd probably created 1,500 or 2,000 self-portraits using stable diffusion
375. 57:29and dream booth and they were all cool and I was writing stories about them and I had this art project and then this picture came up
376. 57:38and there was just something about it that it was the kind of it was the kind of image that I would have made without AI had I had the
377. 57:50skills. And it was just one of these weird moments where it's like that is something I would have created. And it felt very visceral.
378. 58:02And so now you can like upres these things and upscale them and now you can turn them into movies. And he's holding a manila envelope with
379. 58:11some creepy [ __ ] on it with his creepy hand. Crazy, right? Oh, these this this I want to tonight we might uh
380. 58:23we might make a a video tonight. We'll go write like some sort of sci-fi song. We'll put some of these
381. 58:32blueprint animations together. I think these things are just amazing. Look at that one. The bacteria just sort
382. 58:42of growing all over the thing. And I know I said I'm going to show you how to do this, didn't I? And I haven't.
383. 58:56And you're probably like, "Kyle, hey cow, cow cow cow cow cow cow cow cow, shut up.
384. 59:14Look at that. That's so cool. And the fact that it just made up these music notes because there's some music
385. 59:25notes down here and it just made this as sheet music. Be cool to go play that. I love MidJourney so much. Wow. Yeah, I know. Crazy, right?
386. 59:48How cool is this?
387. 1:00:12Come on. You kidding me? Look at that. I think this one where it opens its beak is just crazy.
388. 1:00:54very steampunk. Yeah, these are cool, aren't they? Looks like some 1840s science book just coming to life.
389. 1:01:12Look at that. No, Vicki, you can extend the video. You can extend the video. Okay, let me show you how you make these things. Now,
390. 1:01:25we got to show Vidy. Vicki, I figured I figured out extension. Okay. Yes, you can. Okay, so here's what you
391. 1:01:39do. So, let me go to let me go to organize. So, here we are in in in midJourney, right? And you can go to organize, which
392. 1:01:48just basically lets you flick flick through [ __ ] faster, right? Awesome 3D prototyping. Yeah, I know. Crazy. Crazy.
393. 1:01:57Um, all right. So, let me just flick down through these and find something cool that I like. Actually, you know
394. 1:02:03what would be cool? I did this vibe storytelling image.
395. 1:02:19I think that's the one. Okay. So, we're going to take this Vive storytelling image. So, the way it works is right
396. 1:02:24down here in the lower right hand corner. So, so you've always had these other buttons, right? You can vary the
397. 1:02:31image subtle and strong. You can scale the image. You can Oh, you use different images. And then um and then if I click on more
398. 1:02:44options, you can you can add other things like zoom and remix and things like that. So now you have this new area
399. 1:02:51called animate image. Let me see if I can make this any bigger. Yeah, there we go. So you've got this
400. 1:02:57thing called animate image and then you can have autoan animate, low motion, high motion. So it works the same way.
401. 1:03:04So you just click on it, bang, bang. And then you can do manual. And if you click manual low motion, you can say um
402. 1:03:16so it started writing the prompt for me. So the word storytelling should shatter. The word vibe should
403. 1:03:32float away. The sun glasses should turn
404. 1:03:48dark purple and go. And now I have not What's this new personalized? What's is there there's something new and personalized?
405. 1:03:59Anyway, okay. So that's how you make a video. And then basically you just go back to create and go to the top. And
406. 1:04:06then now it's making videos for us, right? And so I can go in and just now here we got Oh, these aren't done yet. Come on.
407. 1:04:23So that was just the auto one. This was this was low motion. Then I think the other one I did was high motion, which is this one.
408. 1:04:43That was kind of cool. I mean, they're they're a lot less janky than I thought they'd be. Oh, this is the one where I asked for
409. 1:04:56the text to fly off. So, we'll see how these do. Okay. So, Vicki, here's how you here's how you extend the video. So,
410. 1:05:04let me go find something that would be pretty. Okay, we'll do we'll do this girl. We'll do the one with the this one with the fire. So,
411. 1:05:11basically what you do is you just click low motion again. And now it makes four more videos that the front half of it is what it
412. 1:05:22was. And then it's going to add now another eight or five seconds, however long these are. Oh my god, I just made one of my
413. 1:05:29paintings come to life. Yeah, exactly. Yep. I've animated a ton. Just don't know how to extend. So, basically, you just you just extend
414. 1:05:40it. You just add animation to an existing video. I'm pretty sure that does it. We'll see here. All right, let's look at
415. 1:05:49our vibe storytell. Oh, cool. Right. Right. That's not bad. Didn't really do what we wanted it to.
416. 1:06:03Vibe
417. 1:06:24[Music] All right, 92% complete. Come on. Let's see if we got 10 second videos here.
418. 1:06:391 100 2 100 3 100 4 100 5 100 6 100 So yeah, this extended. So there's a second little bit here. So there and then right here's the
419. 1:06:53extension. Yeah. So that worked, Vicki. Now, can I extend and extend? Let's try it. Let's Let's pick the best one of these.
420. 1:07:12That one's pretty good. I like her looking up like that. Okay. So, here she is here. And now kind of the same.
421. 1:07:30Yeah, they're all pretty much the same. It's interesting. Oh, you know what I bet I can do? Yeah, I can bump up stylization. Okay,
422. 1:07:41here's what we're going to do. So, we're go to create. We're going to take this one. Wait, what did that say when we were out here?
423. 1:07:50Oh, look right here, Vicki. You can roll over it. I had the but but yeah, the button at the bottom of the video now
424. 1:07:57says extend auto. So, I'm going to say extend manual. I'm going to say girl looks into the camera
425. 1:08:11and Her irises iris as glow fire orange
426. 1:08:26and then I'm going to say um oops oh crap video extended. So we'll go auto extend.
427. 1:08:40Oh no, I didn't want auto extend. Damn it. Shut up. Extend manual. There's the prompt. I want to change our stylization. Oh, we can't.
428. 1:08:55All right, we'll do high motion for this set. All right, I got it. Just bear with me here, people. I'm trying to figure this out. Imagine
429. 1:09:10all the people [Music] living. [Music]
430. 1:09:31Are we done? No, we're not done. you can extend the extended video. So that's it. It's quite simple. There was
431. 1:09:39a really interesting statement put out by by MidJourney today. Let me go look at that. We'll go read that because I think it's worth it. Uh
432. 1:09:48Midjourney, that's the game. If you've made thousands and thousands and thousands and thousands of midjourney
433. 1:09:56images, like honest to God, just [ __ ] going back through your images and just animating them like that those blueprint
434. 1:10:05looking things I made. So those blueprint things, this is one of the the ways that I'll sometimes if I'm just
435. 1:10:13[ __ ] around rather than having to use my brain, I'll just go find an SREF that I like and then I just I just have chat
436. 1:10:20GPT modify the SRF. I like I'm like keep the style the same, but give me new subjects and then I just paste a bunch of the
437. 1:10:28chat GPT things into MidJourney. It just generates a pile of images. Sometimes they're really cool. Well, now I can
438. 1:10:34take those and turn those into those cool videos and all of a sudden, good lord, I've now paid 13 months of
439. 1:10:40MidJourney. Probably time to pay for an annual and save some money. Probably like MidJourney is one of the few, Todd,
440. 1:10:47that I would say, yeah, I would I would support that. I would support that. My it is my contention that in in no
441. 1:10:55uncertain terms, you should not be buying annual subscriptions to any of these AI tools just because they're
442. 1:11:01changing too fast. But Mid Journey's pretty consistent. Although, you know, they're being sued by the New York Times
443. 1:11:07and or no, by Disney and and Universal. So, who knows how that goes. Okay. Is this the one? As you might know, okay,
444. 1:11:15this is the one I wanted to read. So, as you know, our focus over the past few years has been images. What you
445. 1:11:24might not know is that we believe the inevitable destination of this technology are models capable of real time openworld simulations.
446. 1:11:36So where midjourney has been headed is to real time openw world simulations. I've said it on this channel before. We are not that many
447. 1:11:47years away from being able to speak a movie or a AAA video game into existence. So, so, so there's that. What's that?
448. 1:11:58Basically, imagine an AI system that generates imagery in real time. So they've got right now they've got um
449. 1:12:07image video generating tools that are generating videos faster than 24 frames a second. So 24 frames a second is is what film
450. 1:12:20film is. TV is generally 30 frames a second or or 60 if you're doing sports and want to slow-mo stuff. But 24 frames
451. 1:12:27a second is basically, you know, cinema. Um, they've got video systems now that are generating video faster than 24
452. 1:12:35frames a second. So that means you can start to buffer. You could prompt a scene into existence. It starts rendering that scene
453. 1:12:45and it's it's now buffering more more than it's you know than it's it's it's building it faster than you're
454. 1:12:54watching it, right? And so what that would allow you to do is just change the course of a movie. I'm bored. Make it a comedy.
455. 1:13:02Off it goes. Is everyone else ready for the holiday yet? Yeah, exactly. Okay. You can command it to move around 3D
456. 1:13:10space. The environments and characters also move and you can interact with everything. In order to do this, we need
457. 1:13:17building blocks. We need visuals, our first image models. We need to make those images move. Video models. We need
458. 1:13:25to be able to move ourselves through through space. 3D models and we need to be able to do this all fast real time models.
459. 1:13:35The next year involves building these pieces individually, releasing them, and then slowly putting it all together into
460. 1:13:43a single unified system. It might be expensive at first, but sooner than you'd think, it's something everyone
461. 1:13:49will be able to use. So, what about today? Today, we're taking the next step forward. We're releasing version one of
462. 1:13:54our video model to the entire community. From a technical standpoint, this model is a stepping stone, but for now, we had
463. 1:14:02to figure out what to actually concretely give you. Our goal is to give you something fun, easy, beautiful, and
464. 1:14:10affordable so that everyone can explore. It's 10 bucks a month, and you get the video thing as part of it. Um, we think
465. 1:14:17we've struck a solid balance, though. You may feel the need to upgrade at least one tier for more fast minutes.
466. 1:14:25Today's video workflow will be called image to video. This means you can turn images to video. Um there's an automatic
467. 1:14:32animation setting. There's high motion, low motion. Okay, that we've all played with. Pick what seems most appropriate.
468. 1:14:38Once you have the video, you can extend it roughly 4 seconds at a time, four times total. So there's your thing,
469. 1:14:44Vicki. You can you can go four times total for the extension. So, so basically you can make 16-second videos.
470. 1:14:53We're also also letting you animate images uploaded outside of midjourney. Ah, drag an image to the prompt bar and
471. 1:15:01mark it as start frame. Hang on. Hang on, people. Calm down everybody. Calm down. Just We're gonna It's gonna be so good.
472. 1:15:16people. I just need people to calm down. Wait, can we watch her eyes turn orange here? Let's see if it if it took our instructions.
473. 1:15:28Come on, girly. You can do it. I I am so impressed with the the smoothness and the coherence of the animation.
474. 1:15:40Like, nothing's really arai. There's not a lot of jankiness. Oh, she didn't turn orange. It's a bummer.
475. 1:15:54All right, whatever. Okay, we can upload an image. So, um, let's get rid of that. Oh, start frame. Look at that.
476. 1:16:08So, I gonna go grab something outside of here. That was made not in here. I could do that.
477. 1:16:30[Music] That's good. We'll do we'll do we'll do disco Kyle. Okay. Drag it in. Oh, and
478. 1:16:46you can put multiple images in. Wait a minute. Hang on. Okay. Video start. Um, man dances
479. 1:17:01like the old creepy guy at the club. women in the background.
480. 1:17:19Laugh at him. [Laughter] Settings. We'll go high motion. And And off we go.
481. 1:17:37And yeah, 70s muscle car. Yeah, exactly. I'll go find I'll go find some muscle cars. You know what we can test is if
482. 1:17:45the wheels actually roll. I'm off for Junth tomorrow. Going to use midjourney all day. Oh, that's fantastic. Yeah, perfect. Perfect. Uh
483. 1:17:55perfect use of a day off. Love it. Oh, look at me dancing. All right, this is going to be good. What's new and personaliz?
484. 1:18:05Oh, V7. Yeah. Yeah. Yeah. B7 mood boards now. Select.
485. 1:18:23Oh my god, I'm going to be so good. Oh, look. Look at the women laughing.
486. 1:18:37This is gonna be so good. Yeah. Yeah. Ladies.
487. 1:18:59Oh yeah. like the pied piper of [Music] Oh, if you're new here, one of the
488. 1:19:15things that that this channel is really about is me just entertaining myself. That's awesome. All right. Well,
489. 1:19:27there you go. He's a fun guy. He really is. All right. Let's go find Oh, these these are cool cars. All
490. 1:19:38right, let's let's animate one of these. So, we'll just do auto auto. We'll do low motion and high motion.
491. 1:19:54Why did that song I'm just a jigalo come to mind? I'm just a jigalo. [Music] [Laughter] I leave for two seconds and this is what
492. 1:20:09I return to. Kelly, we've talked about this. You can't leave the channel. Just like the Hotel California. You can't be late. You can't leave
493. 1:20:21midstream. You just never know. We've We've discussed this. We've discussed this. Everybody knows this. Okay,
494. 1:20:32let's see if we get Oh, this would be a cool one to animate, wouldn't it? Uh, some of these sci-fi things.
495. 1:20:38Let's see that. Let's see this one. We'll do We'll do low motion here. And then we'll do we're going to do manual
496. 1:20:45high motion. And we're going to do um we're going to do um camera pushes forward
497. 1:21:00and people walk majestically as Um
498. 1:21:16what are these called? Um transport craft elevate and
499. 1:21:35fly into the distance. I I I assume this is going to suck, but let's see. All right, that's that one.
500. 1:21:47Let's go find some more pitches. Pitches worth playing with. Oh, these were some cool ones.
501. 1:22:07Uh, let's do low motion with him. I think she's creepier. We'll do low motion with her and him. All right.
502. 1:22:23Beautiful. By the way, this just a fun way to play. Don't be precious with this [ __ ]
503. 1:22:39Like one of the ways you learn what this stuff does well and not is just go just [ __ ] vomit out work. Oh,
504. 1:22:49that one's cool. Let's do Let's do high motion on that one. That one's cool, too. We'll do low motion on that one.
505. 1:23:06Okay. Oh. Oh. Oh. People, we're gonna do a low motion and a high motion. That's [ __ ] trippy. Why aren't you doing Sydney
506. 1:23:21s? I know. I need to do Sydney. I know. Calm down. Oh my god. These are so cool. What the [ __ ] was this prompt?
507. 1:23:36This is This is like nothing. The prompt is collaborative group. Oh, I did a No, I just did a global profile. I just had personalization
508. 1:23:48turned on. Stylization 150. These are cool. Why are they so [ __ ] awesome? Seems like the Oh, high motion on that
509. 1:23:59one. Low motion on that one. Let's do low motion on that one. Those were cool. All right, I'm probably going to blow through my
510. 1:24:11credits here, which will suck, but whatever. There's me and Anne Murphy. Here's Pink Car. Here's some muscle car action.
511. 1:24:24All right, let's do let's let's figure out a muscle car here. We want to animate 70 Chevy Impala. That was my first car,
512. 1:24:31people. That was it. Olive green with keystone mags. That's a good shot.
513. 1:24:52All right, let's go back to that one. We're going to do low motion and then we're going to do high motion with a prompt. Then we'll say car
514. 1:25:09rolls forward as camera tracks and pans around
515. 1:25:23the back. All right, there's that. All right, let's go back up and look at some of the [ __ ] we've built.
516. 1:25:37I think it's important for us to watch Disco Kyle one more time. Oh yeah, ladies. I don't like to brag, but you
517. 1:25:48know, when you got it, you got it. Who's the creepy guy in the club? Oh, that's Kyle. He's unfortunate. He's harmless.
518. 1:26:00I had a 78 Chevy Impala. That was a good solid car. It was the 70 was was a blast to drive. Okay. That's actually super cool. Like
519. 1:26:17that's super cool. The wheel physics are not horrible. The wheel physics are not horrible. This is impressive. Like, I haven't had a
520. 1:26:30video model where the wheel physics have been decent at all. Wow. All right.
521. 1:26:47All right. That was bad. That's bad. Oh, look at this.
522. 1:27:07Why does it have eyes? The car. Cuz I was doing something like Cars. Like the Cars movie. This is really quite good. Wow.
523. 1:27:18Look at the Look at the the things in the distance flying away. How that's so cool. I know. This is so cool.
524. 1:27:38You could totally, you know what would be a really fun project to do? Do you guys remember the movie [ __ ]
525. 1:27:48Scotsy by Philip Glass and Jeffrey Reio where it was just like all these shots of like the world falling apart and
526. 1:27:57industrial pollution and [ __ ] like that. I think it's important to check your regulars. Oh no, it's never important to check. The
527. 1:28:11minute someone says it's important to check your regulars, that means this is at my expense. Fourth of July video I extended a few
528. 1:28:21times. Me laughing at Kyle. That's hilarious.
529. 1:28:36Oh, this is cool. Oh, damn that thing.
530. 1:28:50That's from Vicki. My nine-year-old will love this for something for homeschool. Yeah, this is
531. 1:29:05I mean, honest to God. So, so there's a there's a couple of thing actually. Let me show you a couple of things because
532. 1:29:12if you're doing some homeschool stuff, there might be something fun to play with here. I'll show you a couple of my
533. 1:29:16favorite things sort of in that genre. Um, when you're in midjourney, let's go look at what other videos do we
534. 1:29:26have here. Oh, we got the old crazy people. Oh my god, there's so Okay, there's so much to look at. Oh Jesus, this is all
535. 1:29:34so cool. Okay. So, when you're in midjourney, like one of the things you can do is um let me go to chat GPT and I'm going to say um I'm
536. 1:29:50homeschooling my son and we're at an 8th grade level and he's really
537. 1:30:04um into enmology and trucks. I want you to give me 20 esoteric words
538. 1:30:21related to those fields. That would be a good uh vocabulary uh starter. I don't I don't know
539. 1:30:38education, so forgive my stupidness. Um a good vocabulary starter for him. Okay. So now it's going to give me 20 words.
540. 1:30:54Enmology words. Elytra, the hardened four wings of beetles that protect delicate hard wings underneath.
541. 1:31:02Okay, so now we got cool words. I didn't think Midjourney had it in them, but this video model does some things that
542. 1:31:09others don't. This video model's really quite good. It's It really is quite good. Okay. So, here's here's our words right
543. 1:31:19now. Let's go over to Twitter. We're going to go to the Twitter and we're going to search for sref sf. And we'll
544. 1:31:29put two dashes in front of it. D- sref. Okay. And then we should, if we do our job right, see some cool style references from midjourney.
545. 1:31:44And so you can just scroll until you find one. That's cool. Or if you collect them like I do, you can just go grab one. Is that mine? Oh,
546. 1:31:53that's mine. That's cool. Maybe I need this in lower case. Sref. [Music]
547. 1:32:08It's a bunch of stuff I did. I don't know why my stuff's showing up here. All right, here's one. So, let's just
548. 1:32:15say that we got this cool this cool style we like. So, I'm going to grab this sref. So, I'm going to take that over to MidJourney.
549. 1:32:23I'm going to pop that in. And then I'm going to come back over here to chat GPT. And I'm going to go grab one of
550. 1:32:28these random words, elytra. In fact, we'll do we'll do three of the four of these things. So, we're going to go to midjourney
551. 1:32:41and then I'm going to just paste them in. Oh, I didn't copy. Dumb dumb. Copy. I'm going paste them in. And I'm going
552. 1:32:52to get rid of the definitions.
553. 1:33:15Okay. Get rid of the definition. Get rid of that thing. All right. So, we got four words. Let's put commas between them so it knows that
554. 1:33:27they're separate words. It might know this anyway. And then we got that sref, right? No fast hours left. Oh, you [ __ ] [Laughter]
555. 1:33:41I burned through all my fast hours. See what you did to me, people? Fast turbo. Relax. Can I do turbo? Do I have turbo hours go?
556. 1:33:57No, guess not.
557. 1:34:12Can I not do anything now? Am I totally locked out? Create. Why can't I do draft hours, relaxed hours? Does anybody know?
558. 1:34:27This sucks. But anyway, then you could turn those into midjourney is really good at just taking random words. He ran
559. 1:34:35out as you predicted. I did predict. I predict predicted it for myself. All right, let's go look at more movies. Oh, these are so cool.
560. 1:34:48This is so [ __ ] cool. PayPal, look at this. What money do you have? I'm on the $10 a month plan.
561. 1:35:07I mean, you could do a whole [ __ ] movie.
562. 1:35:37Wow. Tell me that wouldn't stop you in your tracks. In fact,
563. 1:35:54let's was it this one?
564. 1:36:08Yeah. So, we're going to download that.
565. 1:36:36These are trippy, man. All right, we like that one.
566. 1:37:01It's weird. Mary's grandmother. It really is. This smoke looks very realistic, too. Well, that one's a little janky.
567. 1:37:16God, I love these old characters, man. All right,
568. 1:37:30we'll download him. All right. So, what we're going to do, how do we do this the cheapest, easiest way? I know.
569. 1:37:41I'm going to just go into So, we did downloads. So, we're going to go bang. Then, we're going to go add video to end. Add clip to end.
570. 1:37:56And we're going to go bang. Did it do it? No.
571. 1:38:11Oh, it crashed. Like, why didn't that work? Because it crashed. All right. So, we'll do her first, then we'll go add clip to end downloads.
572. 1:38:26Yeah, we'll do him next. All right. And then we'll go add clip to end. Add clip after selection. We'll do this. Is that her?
573. 1:38:50Done. What's going on here? All right, then we'll do
574. 1:39:04add clip to end. Which one haven't we seen yet? Oh, the one with the house. Okay, done. Great. Now, let's go to Sunno and make a song.
575. 1:39:20I got to change tabs or you won't be able to see that dang thing. Oh, and by the way, Brandon, I haven't been looking
576. 1:39:25at the post-it note all night, which you're probably painfully aware of. It's been quiet. Oh, that's good. Yeah,
577. 1:39:36because I'm I'm busy doing [ __ ] Um, what am I gonna What am I Where am I going? Oh, I got to make a puno tab. So, we'll call this.
578. 1:39:48And then we're going to change that. And then we're gonna share Sunna with you so you can hear it. And then we're going to go create.
579. 1:39:56Um, okay. I need a description from all you creative people, all you creative writers. When I what I saw in the
580. 1:40:04bathroom mirror this morning, those old men. Um, I need a description for a song. Like what would be the what would
581. 1:40:10be the kind of music that would go with that? Like the the Weird Mary one could could work, but like how do we describe that? like dissonant
582. 1:40:21um dissonant janky um Appalachian something
583. 1:40:42mel Oh this good side hustle maybe melancholy melanch Kie. Oh, wait. Hang on. I got to turn on dark reader.
584. 1:40:58Come on. Is it on? Oh, here we go. Is it coming?
585. 1:41:14Yeah, there we go. Melancholy. Uhoh. Did it turn off? Loading. Please wait. On. Okay. Come on. Flip my flip my browser.
586. 1:41:28Melancholy dissonant appian folk. But I like dystopian unease with
587. 1:41:44dystopian unease. Melancholy dissonant appellacian. I just spelled that wrong. Epilian.
588. 1:42:00Appalian. Okay. Oh, we want instrumental create. Okay.
589. 1:42:17[Music] [Applause] [Music] All right. Let's So, here's our video. So, we're going to go save. We're going
590. 1:42:29to go save. We can't save it. Why can't we save it? QuickTime player. Close. Save to downloads. Uh, creepy.
591. 1:42:48Creepy into downloads. I wonder if it's saved. Creepy. Yes.
592. 1:43:16All right, there's our creepy movie. Now, can I just drop a longer audio file on that and have it work?
593. 1:43:26Hey, Kyle. Yeah, two things. One, fun fact from Ohio. It's actually Appalachin. Um, also we're still seeing Sunno. Yeah.
594. 1:43:36Yeah. Yeah. I was going to play it. [Music]
595. 1:44:08[Applause] I'm gonna add the word devastating at the beginning of this. Okay. Devastating.
596. 1:44:25Devastate Appalachin uh instrumental create and I'm going to go create. We'll create six of them. We'll get something good
597. 1:44:40out of this. You tell him, Brandon. Looks like how folks mis mispronounced Louisville. Lewisville. Champy jamming out. It's not
598. 1:44:51creepy sounding. Maybe a minor note. Yeah, that's why I put devastating. I know. [Music]
599. 1:45:13All right. [Music]
600. 1:45:46Oh, there's some good ones here. [Music]
601. 1:46:05Hey. [Music]
602. 1:46:20This one, right? [Music]
603. 1:46:39All right. This This is the one we're gonna We're gonna do this one because it's weird. It's not right, but it's
604. 1:46:46weird. Okay. So, that's downloaded. Okay. So, we're going to do this in iMovie. We're going to do this with
605. 1:46:50transitions and [ __ ] because I'm going to slow down. It's not weird. It's irregular. iMovie
606. 1:47:06tabs. I knew that. I knew that. I didn't need I didn't need a producer to tell me to do that. That's because I'm a professional.
607. 1:47:14I know exactly what I'm doing. I don't need I don't need fancy people telling me what to do with my life with a with a
608. 1:47:24audio production degree. Okay. New movie that's giving Fiddler on the roof. And Murphy, what's happening? We're doing
609. 1:47:38We're making a creepy movie, man. Look at these things. Okay, that one, that one, and that one. And echoes from the hollow. We're going
610. 1:47:51to drop him on in. All right, we're going to start with her. No, we're going to start with him. We're going to slow him down. So, let's get
611. 1:48:03our timer thing there and go slow and we go play. That's a little too slow.
612. 1:48:19Wait, let me do custom. Let's do 70%. Um, champ, stop whining.
613. 1:48:41I think we can just lose it. We can go right to there. All right, there's that. Now we're going to do her her because she's creepier
614. 1:48:58than [ __ ] We're going to slow her down to custom to 70. We'll slow her down to 85%.
615. 1:49:17I think we'll do a similar sort of cut. I don't like the double look back. So, she'll look into our eyes and pierce our
616. 1:49:25soul and melt our freaking minds. Okay. And then we grab melty house. And I think we lose the beginning here. No,
617. 1:49:36maybe not. Maybe we keep that. That's creepy, right? Yeah. Keep the whole thing here. But we're going to do custom speed of 80%.
618. 1:49:49That's going to slow that down. Now we're going to go get transitions and we're put in cross. Do we want cross blur or cross dissolve?
619. 1:50:00I think cross dissolve two. Can someone explain why I can't make a cross dissolve more than a second long?
620. 1:50:12Says there's not enough stuff, but there is. Well, whatever. I don't care. If anybody knows iMovie. Wait, why is she so short?
621. 1:50:36What? What? All right. Yeah, something something weird happened.
622. 1:50:51Okay. And let's make her 75%. Make it a little longer. All right. Now, let's go back to our media. Let's drop our little song in here
623. 1:51:05and we'll chop off the beginning of this. We'll come right in, but we're gonna All
624. 1:51:21[Music] right. [Music]
625. 1:51:39Not the right song. You told me that. I didn't listen. Hang on. You were right. I was wrong.
626. 1:52:14I know here.
627. 1:53:13Yeah, I know you can't hear. You're gonna have to just trust me on this one. It's called The Hollow Hills.
628. 1:53:20Come on, download. Download already. I know it's getting late, people. You got to hang in there. It's going to be
629. 1:53:28We're going to creep out the Twitter. Also, the video quality is only 480p and it looks this good. Yeah, I know. Bottleneck Banjo. I like
630. 1:54:09These are these are pseudo creations.
631. 1:54:39Okay, get rid of that. Oh, get rid of that. Delete media from project. Yes, I want it out of there. And you don't got time for that.
632. 1:55:02that. No, this is it. Okay. So, wait. Where's my iMovie? And then where's my finder? And then where's my H? And I And then I
633. 1:55:16go H. And I go and and I put H. And then I Wait. Uh oh. We got to make this thing smaller. And then we're going to go to there. Oh,
634. 1:55:31I see what it did. What did it do? I don't know what it did. Oh, we got to fade to black at the end. God, this is
635. 1:55:38There's so much work to do here, people. You don't understand how hard it is to be me. I say it night after night after
636. 1:55:46night and you're all like, "It's so easy. You just turn on the camera and talk. Marge showed you how to do it anyway." All right.
637. 1:55:57And then we're going to do this to here. And then we're going to do this to here. And we're going to go. [Music]
638. 1:56:19Is that too fast? [Music]
639. 1:56:34not as hard as your producer trying to watch you produce something. [Music]
640. 1:56:55That's cool. All right. Good enough. Good enough for internet work. And now it won't it won't upload to
641. 1:57:05[ __ ] Twitter anyway because Elon Musk can't fix his upload service. All right. Uh, so this is what's this called? This
642. 1:57:11is called Creepilacia. Creep Creepilacia. Yes, sir. Um, sorry. I can't let this stand like this. You've
643. 1:57:21got to fade that audio out. Oh, fine. Fine. [Music]
644. 1:57:40I got to do Hang on. And I got to put a point in there. And then another point there. And then drag that out and down. Drag
645. 1:57:52that over. And now drag it down. Okay. Fine. And you want to be the extra. You could put a title card on that black
646. 1:58:08screen with like produced in the AI learning lab by Kyle Shannon using the journey video. Just just you know, chef's kiss.
647. 1:58:18Yeah. All right. Uh let's see. All right. Um, AI learning lab productions
648. 1:58:34[Laughter] by Kyle. I know we'll say we'll say um I'll do by Kyle Shannon down here by Oops. By
649. 1:58:49Kyle Shannon. Uh, I'll say mid journey. How do we want to do this? Uh
650. 1:59:12so do this um AI learning lab. Thanks.
651. 1:59:26Midjourney and Suno and then let's see. We'll do this.
652. 1:59:45Oh no, it didn't save it. The hell. God. Thanks, Mid Journey and Suno
653. 2:00:01and then AI learning. Look how good that was. We all excited. [Music]
654. 2:00:15I'm still here. Side hustle maybe still here. Transition will be the amount of time you turn the clip. Okay, whatever. Export.
655. 2:00:31Export. Share file. Next. Creepy movie. Creepy Lacia. Replace. All right. Now, let's watch.
656. 2:00:45Oh, I got to change tabs. Oh, did you not see any of that? I'm such a loser. Oh, you did? Okay, good. It was iMovie. So.com
657. 2:01:00X. Can you see that? Yeah. Okay, you can see what I see. All right, good. G. Um, if you missed the AI learning lab
658. 2:01:15tonight, you missed a good one. Exclamation point uh atsuno.
659. 2:01:30Um, we'll do at scobilizer. Don't miss it
660. 2:01:46again or these people will be in your dreams.
661. 2:02:02[Laughter] I like being stupid. Stupid is my jam. Watch it. Try to upload. This should be comical.
662. 2:02:21Error. There's a surprise. Let's try to post it and see if it uploads with a post. 16 17 18 19 25 20 18 19 17 Dear Elon Musk.
663. 2:02:39Hey, quickly just quickly curious, could you uh what do they call it in uh software development? [ __ ] fix the upload to your Twitter.
664. 2:02:50Jesus good lord. 15 16. I think what we might have to do is save this in a different format. Yeah, we're going to have to. All right.
665. 2:03:06One of the things I've learned is that you can you can hack Twitter by saving it in a non-Apple format. [Laughter]
666. 2:03:18Oh my god, this is so painful. Uh, is this 480p? I think it's 720p. creepily. And then let's go back to the Twitter.
667. 2:03:33Did it upload? No. So, we're gonna get rid of it here. We're going to go grab it here. We're going to go Why? Wait, where did it go?
668. 2:03:43Where did it go? There it is. Oh, I got an error. There's a surprise. Dear Elon,
669. 2:03:59hey, I know catching a rocket with chopsticks is hard, but I didn't realize that uploading a video to your stupid
670. 2:04:08[ __ ] social media site was harder than catching a rocket with chopsticks. Elon, dear Elon, dear, dear Mr. Musk, congratulations
671. 2:04:21on the Doge savings and catching rockets. Quick curious wondering, could we fix the upload to X?
672. 2:04:40Losing federal funding for SpaceX. Maybe they could take the federal funding for SpaceX SpaceX and fix their upload
673. 2:04:46button. Anybody know how to do this? This is unbelievable. It really like it's just it's just stunning. It's stunning how bad this is.
674. 2:05:00I It's a 19-second video. anyone
675. 2:05:17dear dear anyone dear Mr. Musk post post.
676. 2:05:31Jeff Flanigan shakes head. And the sad thing is there's still 33 people watching on on Tik Tok. 47 people
677. 2:05:49watching on other streaming platforms. Oh, we're at 87%. It might just go. Come on. You can do it. You can do it. Please. Yes.
678. 2:06:06Okay. So, now could you all please go like this? Uh, let's let's edit this so we say something about the new video feature.
679. 2:06:21You missed a good one. Um, we played around with midjourney V1 V1
680. 2:06:36video generation and wow, it's impressive. Thanks also to
681. 2:06:52Sununo Music for your musical swellness. [Laughter] Hey, Scoilizer.
682. 2:07:06Cool. A question mark. Okay. Don't miss the learning. Don't miss the AI learning lab again or these people
683. 2:07:24will haunt your dreams. I know how to write. Okay. Update. Beautiful. Fantastic. Fantastic. Bob, why don't you tell them
684. 2:07:38what they want? Well, they haven't really won anything. Seriously, cuz you know. [Music] All right. Now, do me a favor, people.
685. 2:07:48Go find this post. Go to my Twitter, Kyle Shannon. Find this post of the creepy people. I got some hearty hearts. Got a comment here.
686. 2:08:01I think, huh? Said there's a comment. [Music] Anyway, all right.
687. 2:08:15I'm out of here, good people. [Music] The fade on credits is great. Awesome. All right. All right, everybody. Uh,
688. 2:08:28Wednesday night, it'll be normal time tomorrow. Who knows what we're going to do? Should be fun. But that was that was
689. 2:08:34cool. That midjourney video stuff's pretty swell. Um, I kind of feel like with V3 doing acting and voice and sound effects, like I feel
690. 2:08:45like every other video model right now feels very thin to me. Like I shouldn't have to go make sound effects. I
691. 2:08:52shouldn't have to go make music. It should just do it for me. Uh, but you know, we'll get there. All right, peace out everybody.
692. 2:09:00Midjourney rabbit hole time. Yeah, everybody go off. Go play. Um, burn through your credits like I did. They're all gone. I lost them all.
693. 2:09:11All right, take care everyone. Bye.