Searching...
13 results for “coding practices”
Product2 mentions across episodes
coding
And we were like, oh god. No. But it can generate the code, and you just gotta paste it in. You just gotta do all this stuff. Right? And they were like, that sounds kinda hard. And we're like, but it's faster, and they they wouldn't do it. And then n
12:04 / 13:11
from transcript12:04 – 13:11
I know that Cloud Code is, I think, a bit different. It's a bit more authentic. It touches more things. It does the whole project for you. I'm not quite there yet where I'm comfortable with that because, maybe I'm a control freak, but I still would l
36:40 / 37:46
from transcript36:40 – 37:46
of not just information, but also code and diffs. Right? Because if you're gonna put your IDE away, you actually do have to look at the diffs. Now I'm gonna tell you that once you get some expertise at this, you can actually tell from the shape of th
12:41 / 13:54
from transcript12:41 – 13:54
this is a dev tool. Developers are all different. Developers have different preferences. They have different environments. So there's just so many ways to use these tools. There's no one right way. You sort of have to find your own path. Luckily, you
1:08:57 / 1:10:06
from transcript1:08:57 – 1:10:06
free or substantially lower costs, or it'll breed creativity in terms of offerings, which is good for the ecosystem. But I just think the simple thing is The US models are currently better, and we use them. And I try Chinese I try these other open mo
35:55 / 37:11
from transcript35:55 – 37:11
if you use the most capable model, because it can just do the same thing much faster with less correction, less, less hand holding and so on. So that's the first step is just use the best model. The second one is use plan mode. I start almost all of
1:09:42 / 1:10:48
from transcript1:09:42 – 1:10:48
It writes the console logs, you rerun it, guess what? Now you have a full history of everything that was happening. You copy that, you paste it inside your chat. 99% of the time, that's enough. That's already enough. AI is like, okay, got it, found i
1:08:12 / 1:09:21
from transcript1:08:12 – 1:09:21
makes code a particularly good place to do this is that code is verifiable in a way that, you know, most other work is not. So, you know, with code, you can verify that the build works. Right? So you can say, hey. I wanna build this. I wanna build th
30:42 / 31:45
from transcript30:42 – 31:45
...back. For coding, that's probably less helpful, but there are trade offs. I both techniques work. I think fundamentally, the thing that is special about Cloud Code is not the compaction. Okay. It's the it's the ability to write and read files on your
21:35 / 22:49
from transcript21:35 – 22:49
And what that serves is a serves as a source of truth on, like, actual tasks and subtasks that it will need to execute to get to the finish line. Right? And then there's the final final layer, which is depending on what tool you use, Cloud Code or Cu
33:46 / 34:52
from transcript33:46 – 34:52
I would procrastinate, and then it grows to, like, 50. And so there's just, like, a a lot of code reviews. Codecs is really good at reviewing code. So actually, one thing that we've noticed that five two in particular has gotten extremely, strongly a
16:20 / 17:43
from transcript16:20 – 17:43
And sometimes it'd be over by one minute, and he would still delete the code and start over because his thinking was the right elegant solution should be able to be written in one hour. And so pair programming, I mean, that's an extreme version of it
23:53 / 25:10
from transcript23:53 – 25:10
Have a podcast?
Run your podcast through Clypt
Get ranked clips, hooks, and ready-to-post copy from your own episodes. Free to try.