WEBVTT

1
00:00:00.000 --> 00:00:03.680
Mickey, by the end of this episode, what are we gonna learn?

2
00:00:03.680 --> 00:00:07.760
We're going to know what's the best, what's the worst, what to use, what not to use,

3
00:00:07.760 --> 00:00:10.800
and this is just our non-professional professional opinion.

4
00:00:10.800 --> 00:00:15.280
Okay, so this is the definitive guide to vibe coding apps, right?

5
00:00:15.280 --> 00:00:19.760
Yes. This is the ultimate tier list, and if this offends you, I apologize in advance.

6
00:00:19.760 --> 00:00:31.120
Okay, any disclosures are you involved in any of these companies?

7
00:00:31.120 --> 00:00:36.320
Wait to the end.

8
00:00:36.320 --> 00:00:41.120
I'm actually, no, I'm not an investor in any.

9
00:00:41.120 --> 00:00:42.960
I do have a bias, but I'll explain later.

10
00:00:42.960 --> 00:00:47.520
A bias as we go on. Sounds good. I invested in Bolt in the last round.

11
00:00:47.520 --> 00:00:50.880
Actually, funny story. I had the opportunity to invest in Loveable.

12
00:00:50.880 --> 00:00:54.880
We both did. Yeah, but they hit me at a time where it's like, I never had done...

13
00:00:54.880 --> 00:00:59.040
I still haven't, but I was like, I don't know what this is, vibe coding.

14
00:00:59.040 --> 00:01:04.800
And then, yeah, they raised what? Some hundred billion at a six billion, two billion dollar valuation.

15
00:01:04.800 --> 00:01:07.520
So crazy. Yeah, you win some, you lose some.

16
00:01:07.520 --> 00:01:12.800
All right, so let's get into it. Okay, so, Loveable V-Zero Bolt,

17
00:01:12.800 --> 00:01:19.600
Cloud Code, Cursor, Codex, WinSurf, Vibe Code, Rourke. Let's just hit right out the hip.

18
00:01:20.400 --> 00:01:27.360
What's D tier? I mean, I see you touching WinSurf. Okay, so I don't think WinSurf is

19
00:01:27.360 --> 00:01:34.560
D tier in terms of tech, but with what happened with the team and the founder sort of dipping,

20
00:01:34.560 --> 00:01:40.320
and then Devon came scoop them up. It's one of those where I'm sure the tech's good,

21
00:01:40.320 --> 00:01:45.680
but like, is there any trust anymore? And I know two guys who work at WinSurf,

22
00:01:45.680 --> 00:01:51.440
awesome dudes, but I probably would never use WinSurf every again. And respectfully in the kindness

23
00:01:51.440 --> 00:01:56.400
of fashion, I would put a D tier. By the way, all these tools are amazing. Yeah, they're great.

24
00:01:56.400 --> 00:02:01.040
They do, you know, like again, this is our non-professional professional opinion, right?

25
00:02:01.040 --> 00:02:06.000
I just personally wouldn't use WinSurf simply for the fact that like again, you know,

26
00:02:06.080 --> 00:02:12.480
you're sort of trusting the team behind set tool you're building with, right? And when, I mean,

27
00:02:12.480 --> 00:02:17.760
you're a founder, like imagine just upping and leaving, like the type of confidence that instills

28
00:02:17.760 --> 00:02:23.280
with your users, investors, and all that type of stuff. So yeah, I would respectfully put WinSurf

29
00:02:23.280 --> 00:02:29.040
at D tier. It's also very technical. Yes, yes. So, and that's one thing too, right? We have

30
00:02:29.040 --> 00:02:36.240
this chart here and I would put WinSurf at a very technical, like you would have to be a technical

31
00:02:36.240 --> 00:02:42.560
person to get the best out of it. Now you have people who like Riley and others who are, you know,

32
00:02:42.560 --> 00:02:48.080
using these technical tools, but if you speak to the team at WinSurf or even cursor, they'll tell

33
00:02:48.080 --> 00:02:53.120
you, yeah, we're building for developers, right? Their focus is developers. I actually spoke to

34
00:02:53.120 --> 00:02:57.680
someone who works at cursor and I tell them like, you know, a lot of like non-technical people are

35
00:02:57.680 --> 00:03:03.440
using your tool. So is that like changing how you guys build and like, is that like sort of,

36
00:03:03.440 --> 00:03:07.600
you know, affecting your decisions? And he straight up was like, no, he's like, we're building for

37
00:03:07.600 --> 00:03:12.560
developers. He's like, it's cool to see non-developers use it, but the main demographic is developers.

38
00:03:13.120 --> 00:03:18.160
And from a team perspective and a business perspective, it makes sense, right? So you could do it,

39
00:03:18.160 --> 00:03:24.000
but I just want to use WinSurf. So I put it at D tier. Okay, so you're putting a D tier just because

40
00:03:24.000 --> 00:03:29.280
of the sort of how it played out. Yeah, like realistically, I would maybe, it would be between an A

41
00:03:29.280 --> 00:03:36.320
and a B for me, right? Because I used to, I used WinSurf for a bit. It was pretty cool. And if based on

42
00:03:36.320 --> 00:03:40.880
how it was back then, if I were to rate it, it'd be between an A and a B. Okay. So, but with all the

43
00:03:40.880 --> 00:03:45.600
business stuff, putting it in. Yeah, I'm putting it in a D just because it's pretty complicated.

44
00:03:45.600 --> 00:03:50.960
Okay. Well, then let's talk about another complicated tool cursor. Okay. I mean, to me,

45
00:03:51.920 --> 00:03:58.640
okay, I'll do this one. To me, I'm going to give it, it's either A tier or S tier for me.

46
00:03:59.520 --> 00:04:04.560
Well, so first, let's define it on the chart. It's definitely like, you have to be technical to use

47
00:04:04.560 --> 00:04:11.680
it, right? Like being able to even open it up and fork a repo and PM run and PM install. Like,

48
00:04:11.680 --> 00:04:18.160
these are like, I don't expect a non-technical person to use it, but you know, if there's a

49
00:04:18.160 --> 00:04:24.000
will, there's a way. And I've seen people use it. So I agree. If you are a vibe coder and

50
00:04:24.000 --> 00:04:31.280
non-technical person, you're going to experience pain. True, but what I will say about cursor versus

51
00:04:31.280 --> 00:04:39.360
WinSurf, there's a lot more tutorials on cursor. And that's one thing like, so in a bigger community

52
00:04:39.360 --> 00:04:45.840
around cursor, fair. And I'll give you an example in like the web dev world. Like, there are people

53
00:04:45.840 --> 00:04:52.080
who are pro next JS and anti next JS. And one of the biggest pros to next JS, you know, people can

54
00:04:52.080 --> 00:04:56.880
argue technicalities is the community, right? Especially even with React, like, let's go on level

55
00:04:56.880 --> 00:05:01.840
down React. There are people who love React to hate React. And the reason React's one is because

56
00:05:01.840 --> 00:05:06.160
the community is so huge, right? So there's a lot of support. There's a lot of documentation. There

57
00:05:06.160 --> 00:05:11.360
are a lot of external packages. That's why you go to any of these tools and you ask it, make me a

58
00:05:11.360 --> 00:05:17.120
website. It's going to use React, right? Even the LLMs have picked it, right? So I think that

59
00:05:17.120 --> 00:05:23.040
matters. And for the audience's sake, I'll give cursor an eight year. I'll, I can agree with that.

60
00:05:23.040 --> 00:05:30.400
But to me, this is like S++. Okay, cool. Sam Altman, the co-founder of OpenAI, just said that it is

61
00:05:30.400 --> 00:05:37.200
the era of the idea guy. And he is not wrong. I think that right now is an incredible time to be

62
00:05:37.200 --> 00:05:41.920
building a startup. And if you listen to this podcast, chances are you think so too. Now, I think

63
00:05:41.920 --> 00:05:48.480
that you can look at trends to basically figure out what are the startup ideas you should be building.

64
00:05:48.480 --> 00:05:54.480
So that's exactly why I built idea browser.com. Every single day, you're going to get a free startup

65
00:05:54.480 --> 00:06:02.880
idea in your inbox. And it's all backed by high quality data trends. How we do it? People always

66
00:06:02.880 --> 00:06:09.040
ask, we use AI agents to go and search, what are people looking for? And what are they screaming for

67
00:06:09.040 --> 00:06:14.640
in terms of products that you should be building? And then we hand it on a, you know, silver platter

68
00:06:14.640 --> 00:06:20.640
for you to go check out. We do have a few paid plans that, you know, take it to the next level,

69
00:06:21.280 --> 00:06:26.960
give you more ideas, give you more AI agents and more, almost like a chat chvt for ideas with it.

70
00:06:27.040 --> 00:06:32.320
But you can start for free idea browser.com. And if you're listening to this, I highly recommend it.

71
00:06:33.040 --> 00:06:34.800
What's next? Lovable.

72
00:06:37.920 --> 00:06:43.920
Lovable cloud, lovable AI. So I will, so explain what that is, because not everyone. Yeah. So

73
00:06:43.920 --> 00:06:49.520
basically the pain point with lovable and bolt was really the integrations, right? You would

74
00:06:49.520 --> 00:06:54.960
need a backend. And it was really difficult, right? You had to sign up and then you had to connect

75
00:06:54.960 --> 00:06:59.760
and copy API keys. Again, these are trivial things to the developer to a non-developer. This is

76
00:06:59.760 --> 00:07:04.560
a headache. And what they've done from my understanding is they've abstracted all this stuff away.

77
00:07:04.560 --> 00:07:10.240
So the moment you boot up a lovable project, I'm assuming they call APIs and they fetch all that

78
00:07:10.240 --> 00:07:18.960
information for you, which makes it easier. But I still have found people running to the

79
00:07:18.960 --> 00:07:27.520
cloud codes and the code X is in the cursor. So I will give lovable a B. Wow.

80
00:07:30.960 --> 00:07:36.960
I understand why you're giving it a B because you look at it from an engineering perspective

81
00:07:36.960 --> 00:07:42.320
and you're probably like, well, if I'm going to go and create a product, yeah, maybe lovable

82
00:07:42.400 --> 00:07:51.280
something I can get, you know, get going and pretty page, but I mean, from a prototyping

83
00:07:51.280 --> 00:07:57.920
perspective, if you know, I'll give you this. I think VZero is better than lovable. Why do you say

84
00:07:57.920 --> 00:08:04.800
that? Versels Marketplace, like their integrations, it gives you plethora of options, right? So with

85
00:08:04.800 --> 00:08:09.200
lovable, for example, they've sort of picked what backend you're going to use it's super based,

86
00:08:09.760 --> 00:08:13.520
and there's pros and cons to that, like the depending on the type of apps you're going to build,

87
00:08:13.520 --> 00:08:18.800
there's pros and cons to it. With Versel, you have all the type, all different types of

88
00:08:20.400 --> 00:08:23.520
what you might call it, back ends. And here's where the bias comes in,

89
00:08:23.520 --> 00:08:28.880
Convix is going to be on the Versel Marketplace soon, and I think Convix is the best back end.

90
00:08:28.880 --> 00:08:33.760
And the reason why there's biases, because I work there now, just full disclosure,

91
00:08:33.760 --> 00:08:36.480
because people are going to be like, oh, he's talking about it because he works there. Well,

92
00:08:36.480 --> 00:08:40.880
I started working there because I liked the product. Oh, homie didn't look at the camera once

93
00:08:40.880 --> 00:08:47.600
until he started saying, Convix, said the word Convix, and he was like, Convix is the number one.

94
00:08:47.600 --> 00:08:55.920
Yeah, PR trained. But I personally think, and I've, for example, had my wedding not too long ago,

95
00:08:56.560 --> 00:09:04.880
and I tried using all the AI tools to build like our RSVP site, and at some point all of them

96
00:09:04.880 --> 00:09:11.840
break except V0. So even if I were just to like vibe code and just go through it, I personally think

97
00:09:12.640 --> 00:09:18.400
out of the V0 bolt and lovable, I would pick V0. There's also templates and components that

98
00:09:18.400 --> 00:09:24.960
you can reuse with V0. Yes, yes. And just like the integration with Versel, it's one of those

99
00:09:24.960 --> 00:09:29.280
things to where I know this probably doesn't matter to a tierless, but I also sort of think about

100
00:09:29.440 --> 00:09:37.280
the future of the tool we're using. And it's like, it seems like Versel and V0 are going to be

101
00:09:37.280 --> 00:09:42.560
very tight knit, and that's like a bet I'm willing to make if I'm building a product that I want

102
00:09:42.560 --> 00:09:48.880
users to use. So are you giving V0 S tier? Is that what I'm hearing? If I was a vibe vibe

103
00:09:48.880 --> 00:09:53.920
coder, like let's say I did not know how to write code, I would maybe write there. I don't

104
00:09:54.080 --> 00:09:59.280
think I'd give it, like can we do an in-between? Okay, so I'll do it an in-between and this is definitely

105
00:09:59.280 --> 00:10:06.560
non-technical friendly, lovable of courses here as well. You sort of disagreed with lovable

106
00:10:06.560 --> 00:10:14.320
being a beat here. So we're no, no, no, I think it's A. I can give you like an A between B.

107
00:10:14.320 --> 00:10:17.920
That's what I think it really is. I'll give you an A between B. That's what I think it is.

108
00:10:17.920 --> 00:10:24.400
Bolt, I would just put them on par with lovable. Yeah, okay. Yeah, fair. See, not a bias investor,

109
00:10:24.400 --> 00:10:33.680
I respect that. Rork, I personally haven't used Rork, so I will trust your judgment. I know

110
00:10:33.680 --> 00:10:38.880
they do mobile apps. Right, so there's this new class of vibe coding apps for literal mobile apps.

111
00:10:38.960 --> 00:10:51.760
That's vibe code app by Riley, our friend Riley. Yeah, and Rork. I haven't played with both of them

112
00:10:51.760 --> 00:10:59.280
extensively but played with them enough to know that vibe code app is, it really is the lovable

113
00:10:59.280 --> 00:11:07.120
for mobile apps. I find the, oh, actually, there's also anything. Yes, I have seen anything.

114
00:11:07.120 --> 00:11:12.320
I maybe did one prompt and then I stopped just because I don't really do a lot of mobile app stuff.

115
00:11:13.040 --> 00:11:19.680
But I have realized that even at convex, there's a lot of like these mobile app vibe coding

116
00:11:19.680 --> 00:11:25.920
platforms that are popping up. Yeah, this seems to be the new thing. And for a reason, right?

117
00:11:25.920 --> 00:11:31.920
Like I think that there's a lot of opportunity to make money building apps. So you think mobile

118
00:11:31.920 --> 00:11:36.400
app, like if I wanted to, let's say I wanted to launch a consumer product, you think mobile is

119
00:11:36.400 --> 00:11:42.240
better than web. I don't think it's better. I think it depends what you're building. I just think

120
00:11:42.240 --> 00:11:50.000
that right now there's, there's just a lot of, you know, you're seeing the Cal AIs of the world

121
00:11:50.000 --> 00:11:54.720
making millions of dollars a month with relatively simple apps with AI baked in. So I think that

122
00:11:54.720 --> 00:11:58.800
there's going to be a lot of people who want to build something similar and different niches.

123
00:11:58.800 --> 00:12:03.840
And that's why I think that right now I'm actually coming up with a lot of mobile app ideas.

124
00:12:03.840 --> 00:12:10.240
And that's why, yeah. See, maybe I'm just thinking too, like I'm too much in my developer mind.

125
00:12:10.240 --> 00:12:15.440
But to me, it feels like downloading an app feels like too much commitment for me. Like I would

126
00:12:15.440 --> 00:12:19.920
really need a reason to download on that. But it seems like people are just downloading apps.

127
00:12:19.920 --> 00:12:24.480
They'll watch a TikTok video and they're like, yeah, I want to check this out. So am I wrong?

128
00:12:24.480 --> 00:12:29.760
Or is like why the push for apps because everyone's doing an app now a consumer app?

129
00:12:32.080 --> 00:12:38.000
I think I'm the same way to be honest. Like to me, it just feels like a lot of commitment.

130
00:12:38.000 --> 00:12:43.200
Yeah, it is a commitment. It is a commitment. But like if you are suffering from back pain and

131
00:12:43.200 --> 00:12:51.520
you're on TikTok and you searched, you know, back pain for tall people and then you see this ad

132
00:12:51.520 --> 00:12:54.960
that is just, hey, are you tall? And so I, as a matter of fact, I'm six foot three.

133
00:12:56.240 --> 00:13:02.480
You know, well, we have this AI that helps you like reduce back pain by 35% in this, you know,

134
00:13:02.480 --> 00:13:07.760
and we become your back pain coach. You know, do you want to download this? And it gets me at that

135
00:13:07.760 --> 00:13:14.880
moment. I might make sense. I might download it. And I find that in like observing my wife has

136
00:13:14.880 --> 00:13:18.960
helped me realize social trends. People use TikTok like a search engine. Yes.

137
00:13:20.240 --> 00:13:26.400
So that makes sense. So where do we put vibe code, rock, anything if you've used anything?

138
00:13:28.080 --> 00:13:36.400
I think we can put them right below, lovable and bolt. So beat your solid.

139
00:13:36.400 --> 00:13:43.680
Beat your solid. I think that you can use any of those and, you know, maybe one of them is

140
00:13:43.680 --> 00:13:48.400
slightly better on the day or slightly worse on the day. But I think that they, though,

141
00:13:48.400 --> 00:13:52.080
what's going to happen, I think, is those are, it's so relatively new, like I think,

142
00:13:52.080 --> 00:13:58.880
rock launch like a couple months ago. But I also remember another one. My boy Seth is A0,

143
00:13:58.880 --> 00:14:04.880
which is a mobile app one as well. So yeah, I think like to your point, I haven't tested any of them

144
00:14:04.880 --> 00:14:10.800
one to give a definitive opinion, but they're all fairly new and it's exciting stuff. And I'm sure

145
00:14:10.800 --> 00:14:15.920
they have free too. So Max, I think they're going to get better too over time, right? Do you know,

146
00:14:15.920 --> 00:14:22.400
are they all built on Expo? Yes. I think from my understanding, I know

147
00:14:23.280 --> 00:14:30.720
Rork is I'm pretty sure they are. It would be foolish for them to not be because you would want

148
00:14:30.720 --> 00:14:37.680
your app to be on both Android and, you know, App Store. And if you're doing a Swift app,

149
00:14:37.680 --> 00:14:41.920
then you're going to have to do the Google Play version. And that's two different code

150
00:14:41.920 --> 00:14:45.840
bases. So it would make sense for them to use Expo. And again, the ecosystem is growing,

151
00:14:45.840 --> 00:14:50.080
React is growing. There's a lot of money behind it. So I would think that they're all built on

152
00:14:50.080 --> 00:14:57.120
Expo. Cool. So that, and here's the funny part. All these guys are probably using the same

153
00:14:57.680 --> 00:15:02.800
model underneath the hood. It's either going to be Claude or it's going to be Codex, which

154
00:15:03.600 --> 00:15:07.360
is gaining a lot of hype. I'm interested to hear what you think about Codex.

155
00:15:07.360 --> 00:15:08.880
I mean, you're the front end developer.

156
00:15:11.760 --> 00:15:18.480
Little higher. Little higher. Yes. So I seen a lot of hype with GPT-5's Codex model. And I

157
00:15:18.480 --> 00:15:25.200
used it in cursor. It was okay. Like, it was pretty good. But I still think Claude's on it

158
00:15:25.200 --> 00:15:33.520
4.5 is the best coding model right now. So I would put Codex, like right below cursor,

159
00:15:33.520 --> 00:15:40.400
but above lovable and bolt. And for non-technical people, like, should they be using Codex?

160
00:15:40.400 --> 00:15:46.640
Yes. Codex does have like a web version. I would put it like somewhere around here. And there's

161
00:15:46.640 --> 00:15:52.400
to your point to like a cursor, there are a lot of videos on Codex because they seem to have

162
00:15:52.400 --> 00:15:58.960
gone both developer and non-developer attention. You can use like OpenAI's web-based cloud platform

163
00:15:59.600 --> 00:16:04.080
to run Codex. So I would put it like somewhere around here. Yeah. I still think there's a little

164
00:16:04.080 --> 00:16:08.720
feat. Like, there's a little difficulty to it if you're non-technical. But where there's a

165
00:16:08.720 --> 00:16:14.560
wheel, there's a way. My take on Codex is it's a bit, yeah, it's a little worse than cursor.

166
00:16:15.280 --> 00:16:23.200
But it's gains like the most, um, most improved award. Yes, 100% because it sucked in the big

167
00:16:23.200 --> 00:16:27.440
thing. It really did. And like, now people are comparing it to Claude, like Claude code. So

168
00:16:27.440 --> 00:16:33.680
they've definitely Sam's cooking. Sam's cooking and I wouldn't bet against them. No, no, they

169
00:16:33.680 --> 00:16:37.840
have trillions of dollars or whatever, but billions. Well, it's important, right? Because if you're

170
00:16:37.840 --> 00:16:46.240
going to pick something, you 100%, right? You don't want to be wind-surfed. I'm not me,

171
00:16:46.240 --> 00:16:51.840
and I swear. I'm actually a nice guy. Yeah, it's good, but I couldn't help it. Yeah.

172
00:16:53.040 --> 00:16:58.080
Claude code. Okay. All right. What do you think? I think cursor's king, man. Wow.

173
00:16:58.080 --> 00:17:02.960
That Claude code got nerfed. Claude code recently, though. Recently has got nerfed. Yes. Like,

174
00:17:03.040 --> 00:17:10.560
if this was four weeks ago, it'd be like this. Like, Claude code would be above S tier.

175
00:17:11.440 --> 00:17:16.560
But like, now, like, I don't know what's happening. Like, I rather, like, it'll use the same model,

176
00:17:16.560 --> 00:17:23.520
clots on a four, five. I'll get better results with it on cursor than with on Claude code. And the

177
00:17:23.520 --> 00:17:29.120
reason being is a lot of people think, like, oh, if they're using the same model to same output,

178
00:17:29.120 --> 00:17:35.600
but really the difference makers, like, yes, everyone's using the same model. But then you build

179
00:17:35.600 --> 00:17:42.080
the agent on top. And basically what that means is, like, when you tell, when you prompt, hey, fix

180
00:17:42.080 --> 00:17:47.680
this error, right? The LLM doesn't have the power to read a file. You have to give it a tool

181
00:17:47.680 --> 00:17:51.840
that gives it the ability to read a file. And then it reads that code, and then it gives you the

182
00:17:51.840 --> 00:17:56.800
output. And now you have to give it a tool to write that code, right? So it seems to me,

183
00:17:57.360 --> 00:18:02.080
cursor's agent, which is built on top of cloud code that gives it the ability to read right

184
00:18:02.080 --> 00:18:07.680
at and all that type of stuff, might actually be better than Claude, Claude, Claude code,

185
00:18:07.680 --> 00:18:12.240
right? So I think this is going to be a tug of war, right? Like, where Claude code will be

186
00:18:12.240 --> 00:18:18.160
better at one point than cursor, then Claude code, then cursor, right? But as a non-technical person,

187
00:18:20.240 --> 00:18:24.720
if I would be frank, if I was a non-technical person, cursor would be here,

188
00:18:24.720 --> 00:18:32.400
Claude code would be here, and this would be the tear list. We're missing one, one company here.

189
00:18:32.400 --> 00:18:38.480
Oh, replete. Are you an investor in replete? No, I'm not an investor. Okay, I'm going to

190
00:18:38.480 --> 00:18:44.080
ask a serious question. I don't know anyone who's used replete, but they're winning.

191
00:18:46.400 --> 00:18:50.800
I'm not even trying to be funny. Like, I actually don't know a single soul who's used replete.

192
00:18:50.800 --> 00:18:56.880
The one time I used replete was back when I, like, this is like three years ago, four years ago.

193
00:18:56.880 --> 00:19:03.120
Yeah. And I needed to run some sort of, like, file, some Python script. So who uses replete?

194
00:19:03.120 --> 00:19:06.960
I mean, I know two people who use replete. Okay, so they're winning then. Okay, it makes sense.

195
00:19:08.560 --> 00:19:14.240
I don't know where I'd put replete. I've never built anything fully with it. People seem to love it.

196
00:19:14.320 --> 00:19:19.360
They raise the bajillion dollars as well. So I'll trust your discretion.

197
00:19:19.360 --> 00:19:26.560
I mean, from what I understand, they have two modes with replete. They have your vibe code mode,

198
00:19:26.560 --> 00:19:32.080
and then they have agent mode. So you prompt it and it takes like 15 or 20 minutes and it goes

199
00:19:32.080 --> 00:19:37.840
and builds your app instead of one minute or two minutes, which is cool.

200
00:19:39.520 --> 00:19:43.440
So they built their own agent. Are they using their own model? Are they developing their own

201
00:19:43.440 --> 00:19:49.680
models? Or I'm not sure, like, if they're developing their own models, it's hard to, like, say,

202
00:19:49.680 --> 00:19:57.600
right? But I have seen, you know, my friend Billy Howell actually talks a lot about replete.

203
00:19:57.600 --> 00:20:03.520
And I've seen some of the output on it. And it's pretty impressive. So you're giving it an A.

204
00:20:07.280 --> 00:20:12.640
I'm giving it, I'm putting it like lovable replete. So, okay, yeah. So this is fair. So

205
00:20:12.640 --> 00:20:18.880
we have V0 close to, in my opinion, maybe a little in the A tier. But like, if I was a vibe code,

206
00:20:18.880 --> 00:20:26.640
or I'd go for V0, codex, lovable bolt, actually, can I add one more? Yeah. Have you heard of chef?

207
00:20:27.440 --> 00:20:36.800
No. Chef was actually built by convex. But what's funny is the reason shelf was built and we built

208
00:20:36.800 --> 00:20:42.160
chef was to show vibe coding platforms that if you use convex as your back end, it's better.

209
00:20:42.160 --> 00:20:46.960
So we didn't build it to compete. One or two people worked on chef. And it's actually pretty good.

210
00:20:46.960 --> 00:20:50.560
Like, off rip you'll get, and I won't, because people will be like, oh, you're being biased. So I

211
00:20:50.560 --> 00:20:55.520
won't even show you could check it out. It's free. So chef isn't meant to compete. But it was more

212
00:20:55.520 --> 00:21:02.400
so the showcase for tools to use convex as their back end. And a lot of the new tools, like, you have

213
00:21:02.400 --> 00:21:07.760
fly, you have bloom, like, a lot of the new vibe coding platforms are all built on convex because

214
00:21:07.760 --> 00:21:11.920
they saw this and they're like, oh, and we open source the repo to anyone can fork and build a vibe

215
00:21:11.920 --> 00:21:20.800
coding platform. And I non bias would put chef along these lines. The only thing is, again,

216
00:21:20.800 --> 00:21:25.920
we're not trying to compete. So at some point, these tools would get better. Like, for example,

217
00:21:25.920 --> 00:21:31.440
I don't think there's a way for you to sign a domain on chef, right? So it wasn't meant to impress

218
00:21:32.000 --> 00:21:39.200
users, but more so developers were building these tools. But yeah, I think I'm pretty happy with

219
00:21:39.200 --> 00:21:46.080
this list. Okay. So just to wrap this up, what advice do you have for non technical people and

220
00:21:46.080 --> 00:21:51.280
technical people if they're trying to choose a vibe coding platform? Yeah. So if you're technical,

221
00:21:51.280 --> 00:21:57.200
then man, it's like cursor or cloud code. Like, there's, there's no other option in my opinion. And

222
00:21:57.200 --> 00:22:02.720
that's simply because you're probably going to be steering the wheel anyway. So you're not going to

223
00:22:02.800 --> 00:22:10.800
be vibe, vibe coding. I know there's like open code by my uncle DAX. I haven't used it. Sorry,

224
00:22:10.800 --> 00:22:17.280
Uncle, I should. I hear a lot of developers talk, you know, highly of it. So like, you're probably

225
00:22:17.280 --> 00:22:21.840
using one of these tools and you're probably steering the ship, right? So no advice to you. Just do

226
00:22:21.840 --> 00:22:29.440
what you're supposed to do. Now, to non technical people, I think there has to be, I've noticed after

227
00:22:29.440 --> 00:22:34.000
last couple months with all the new tools and all that stuff happening, there has to be a mindset

228
00:22:34.000 --> 00:22:39.840
shift. And the mindset shift is a lot of people get frustrated if in five prompts, they don't build

229
00:22:39.840 --> 00:22:45.840
something. And it's like, respectfully, the audacity to think you're going to build software

230
00:22:45.840 --> 00:22:50.960
that's fully functional that people are going to use and care about borderline pay you money.

231
00:22:50.960 --> 00:22:56.240
I don't want to crash out. And you think you could do it in five, six prompts when, you know,

232
00:22:56.320 --> 00:23:00.080
it takes time. It takes planning. It takes testing. There's alpha. There's beta. Then there's

233
00:23:00.080 --> 00:23:07.760
a final version. And then like software is art. And, you know, think the Lord that there are tools

234
00:23:07.760 --> 00:23:14.480
that allow the non technical person to build stuff. But we need audacity. We need to treat it with

235
00:23:14.480 --> 00:23:20.640
care. Your first version doesn't work. You used, you know, you use the lovable and it broke. Okay,

236
00:23:20.640 --> 00:23:25.040
so what? You'll use another tool and try again, right? I think there needs to be a shift in

237
00:23:25.040 --> 00:23:30.480
understanding that software is difficult. Websites are easy, you know, landing pages are easy,

238
00:23:30.480 --> 00:23:35.680
but software is difficult, especially once people actually pay for, right? So when we

239
00:23:35.680 --> 00:23:39.680
enter this mindset, we're like, okay, I'm going to build something. It's going to be awesome.

240
00:23:39.680 --> 00:23:44.320
It's going to take me time because I'm going to make it awesome. Then we'll be okay. But I'll see

241
00:23:44.320 --> 00:23:51.520
people like, yeah, I prompted 10 times in a broke. Welcome to software development. So that's the

242
00:23:51.520 --> 00:23:55.680
one thing I would see. There are a lot of cool tutorials. I mean, you bring up a lot of awesome

243
00:23:55.680 --> 00:24:01.520
people that show people like the mindset, you know, planning, cursor has this one they call

244
00:24:01.520 --> 00:24:06.160
plan mode, which is pretty awesome. And all that stuff is great. And there are even tools that allow

245
00:24:06.160 --> 00:24:11.200
you to plan now. And, you know, chat GBT5 is great. If you want to like, just go back and forth

246
00:24:11.200 --> 00:24:18.080
and brainstorm. It's more about mindset now. A lot of non technical people fail to realize that

247
00:24:18.080 --> 00:24:22.000
it really takes time to build something awesome. It's like building a business, right? Or if you're

248
00:24:22.000 --> 00:24:26.240
a Jim bro, it's like going to the gym. You know, great things take time. They take patient,

249
00:24:26.240 --> 00:24:30.720
take calculation. There's mistakes. Mistakes lead to experience. Experience leads to you being a

250
00:24:30.720 --> 00:24:36.080
better builder. So take time and enjoy the ride. There you go. Well said, I want to say one last thing

251
00:24:36.080 --> 00:24:43.520
to end. My recommendation to people is actually to follow all the founders of these businesses.

252
00:24:43.520 --> 00:24:51.040
So VZero, Guillermo, Codex, M Altman, Loveable, Anton, Boltz, Eric Simons,

253
00:24:51.040 --> 00:24:57.680
Replett, Amjad, et cetera, et cetera. Follow them and then see who you believe in.

254
00:24:58.400 --> 00:25:02.320
Like if you really connect with Eric, if you really connected Amjad, if you really connect with

255
00:25:02.320 --> 00:25:08.000
Sam Altman, like, then pick that platform. In fact, because you are betting on someone.

256
00:25:08.000 --> 00:25:12.720
You're betting on a company, right? And this is why again, like, people who bet on Winstaff

257
00:25:12.720 --> 00:25:18.480
got Winstaffed. Yeah. God bless him. All right, that's the episode.

258
00:25:19.600 --> 00:25:23.680
Mickey, thanks for coming on. Greg, I appreciate you, man. It's been a fun year.

259
00:25:23.680 --> 00:25:28.960
It's been a fun year. You've had a busy year. I'm going to include links to follow you.

260
00:25:28.960 --> 00:25:34.320
I know you're getting to 100,000 subscribers on YouTube. We're trying. We'll include that there

261
00:25:34.320 --> 00:25:38.960
and see you next time. Appreciate you, bro. Thank you again. Later.