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

Claude Ultracode is super intelligence.

Does a CEO need to understand his employees’ code? Vibecoding is 2025. Evolutionary coding is 2026. Let the code’s DNA evolve to find solutions that satisfy environmental pressure (tests). Genomes are an absolute mess but they work.

i'm tempted to soften the message around AI doomerism and say, look! everyone gets more leverage now! if you were 1x you're 10x now! but in the real world technology can displace. amazingly it's still not clear how AI will affect developers/designers/knowledge workers. this lack of resolution is reassuring. it might mean displacement is a myth. or maybe the models really sucked up until literally this month. that's a real possibility. i do know this: if you wanted to hire someone to pentest your server, would you rather hire a designer with AI, or a security researcher with AI? and if you wanted a design that converts, would you want a backend engineer prompting it, or a designer/marketer? one thing is certain: generalists can now rule the world.

Designers quoting this hanging on for dear life reminds me where most developers were in late 2025. “There’s more to design than X or Y.” “Sure AI can do A but can it do B??” Developers have since learned not to set aside particularities as reserved domains. It’s a strange new world. AI is better than us at most things. It’s super bitter. It’s super bizarre. It’s super science-fictiony. There’s lots to argue about AI. But technical superiority is no longer one of them.

Agent code quality may look worse to a human observer, but in my experience agent build quality is better. Features have less bugs on launch and tend to "just work", whereas human-driven builds always tended to be myopic and fail for embarrassing reasons.

Also available on YouTube: piped.video/dyEpDobnkmA

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.

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??

It's impossible for Jev to be good.