Building enjoy.dev - the best way to build with AI. Yapping at piped.video/@atmoio, atmoio.substack.com, and shipacademy.com.

Pinned Tweet
I’ve spoken to over 50 people 1:1 over the last several months to better understand how they code with AI. It’s an absolute mess. Here are the top 8 mistakes I see. 0:00 - Intro 1:19 - Mistake 1: Talking to 2026 models like they’re 2025 models 2:43 - Mistake 2: Devising funky metaphorical factories to orchestrate your agents 3:59 - Mistake 3: Treating context as sacred 6:02 - Mistake 4: Treating previous conversations as sacred 7:59 - Mistake 5: Having a todo list 10:00 - Mistake 6: Using funky tools 13:47 - Mistake 7: Stressing over code quality 24:27 - Mistake 8: Using branches and worktrees
162
118
1,785
303,361
Chinese man sues AI with AI after AI gives his mother a cursed burial
14
22
271
15,087
Best early SaaS advice: Don’t offer an annual plan. Monthly only.
143
20
1,294
111,225
New products are riddled with subtle UX frustrations and onboarding issues that will tank your entire operation if you wait a full year to find out churn.
9
155
11,378
If you set aside the politics, the propaganda, the fear-mongering, the economics, and the intellectual property theft, AI is pretty cool. It really shouldn't be possible. It shouldn't work. But these fuckers can use computers like Pantheon uploads.
16
8
172
15,014
I’ve spoken to over 50 people 1:1 over the last several months to better understand how they code with AI. It’s an absolute mess. Here are the top 8 mistakes I see. 0:00 - Intro 1:19 - Mistake 1: Talking to 2026 models like they’re 2025 models 2:43 - Mistake 2: Devising funky metaphorical factories to orchestrate your agents 3:59 - Mistake 3: Treating context as sacred 6:02 - Mistake 4: Treating previous conversations as sacred 7:59 - Mistake 5: Having a todo list 10:00 - Mistake 6: Using funky tools 13:47 - Mistake 7: Stressing over code quality 24:27 - Mistake 8: Using branches and worktrees
162
118
1,785
303,361
i'm appalled by how solo builders are approaching agentic engineering today. i've spoken to several people over the last couple months 1:1 to get an idea for how they're building with AI. every single one of them is vibecoding like it's january 2026. they're writing huge specs. they have a kanban board neatly organized with hundreds of todos. they're having their agents take detailed notes after every change. i'm like, what are you doing?? why are you giving it specs? why do you have a todo list?? if you're starting a business, code is the least important part. half of these people are worried about AI code quality. i'm like, what are you talking about?? why the fuck do you care about code quality??
269
25
1,140
260,511
It's impossible for Jev to be good.
91
52
1,078
101,088
Why is it always the next generation model that’s super scary? Once the scary model gets released it ceases to be scary and we look upon the next one as the truly scary one. Rinse and repeat since 2019.
72
70
699
27,050
you can just animate your app's dock icon
15
2
109
12,011
Delete your AGENTS.md. You don't need it anymore.
206
22
830
194,006
if only there was a way to work with all your agents and switch between them mid-task without having to do a context transfer oh wait
I keep switching between Codex and Claude. Why hasn't someone built a harness that works with both?
22
3
197
83,857
if only this exact product in the screenshot existed if only you were 1 click away from downloading this and being 10x more productive
11
2
36
11,215
This video does more to demonstrate the alignment problem in 2 minutes than the 3 million words Dario spews on this on a weekly basis. The problem is that an AI that acts like this isn't intelligent and isn't a good product, and thus won't survive economic contact.
Scalp Misalignment
37
46
636
91,083
Humans have been capable of creating machines of horrific destruction long before AI. I suppose one could argue unique about AI is its potential to escape containment and replicate. Though the physics constraints on that doesn't seem to have a solution in sight. We may be a few hundred years from this problem really starting to matter (counterargument: ny-times-man-wont-fly-for-a-million-years.jpeg)
5
1
54
4,361
I’m starting to suspect this whole “pace the frontier”/cooperation thing is a price fixing scheme. AI labs are hemorrhaging money but they can’t raise prices because their competitors will bleed them out. Only way out is a third party to regulate prices upward.
🚨 OBAMA ON AI: "If we are thinking about AI just in terms of how do we cure cancer or get better energy, you can do that without having agentic AI and having it just roaming free in the internet. The reason you are doing that is because you have to market a product that people will pay money for. That’s a misalignment between what our society needs and the commercial imperatives that these companies are facing, not because necessarily they’re trying to do bad things, but because they’ve got to justify these valuations. So, that’s one more reason why it is really important for us to have a competent government and a serious bipartisan conversation around this issue, and we have to do it fast. And I would encourage voters to pay attention to this. If somebody does not have a serious plan for how to deal with this, then they’re not meeting the moment, and you should probably look for somebody else."
79
59
721
54,967
We're adding support for AGENTS.md to Claude Code. Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md. You can toggle this behavior in /config.
13
8
186
17,617
I’m starting to wonder whether clean code and architecture was just something designed for humans. Does clean code matter to agents? It’s all chinese to them. I’ve yet to hit a wall where they’re like “sorry, can’t make sense of this codebase anymore.”
466
43
1,887
150,726
Claude vs Astra. It's crazy how unpleasant Claude 5 has become to use.
78
9
518
82,687